Tag Archives: speech

Google at Interspeech 2022

This week, the 23rd Annual Conference of the International Speech Communication Association (INTERSPEECH 2022) is being held in Incheon, South Korea, representing one of the world’s most extensive conferences on research and technology of spoken language understanding and processing. Over 2,000 experts in speech-related research fields gather to take part in oral presentations and poster sessions and to collaborate with streamed events across the globe.

We are excited to be a Diamond Sponsor of INTERSPEECH 2022, where we will be showcasing nearly 50 research publications and supporting a number of workshops, special sessions and tutorials. We welcome in-person attendees to drop by the Google booth to meet our researchers and participate in Q&As and demonstrations of some of our latest speech technologies, which help to improve accessibility and provide convenience in communication for billions of users. In addition, online attendees are encouraged to visit our virtual booth in GatherTown where you can get up-to-date information on research and opportunities at Google. You can also learn more about the Google research being presented at INTERSPEECH 2022 below (Google affiliations in bold).


Organizing Committee

Industry Liaisons include: Bhuvana Ramabahdran

Area Chairs include: John Hershey, Heiga Zen, Shrikanth Narayanan, Bastiaan Kleijn


ISCA Fellows

Include: Tara Sainath, Heiga Zen


Publications

Production Federated Keyword Spotting via Distillation, Filtering, and Joint Federated-Centralized Training
Andrew Hard, Kurt Partridge, Neng Chen, Sean Augenstein, Aishanee Shah, Hyun Jin Park, Alex Park, Sara Ng, Jessica Nguyen, Ignacio Lopez Moreno, Rajiv Mathews, Françoise Beaufays

Leveraging Unsupervised and Weakly-Supervised Data to Improve Direct Speech-to-Speech Translation
Ye Jia, Yifan Ding, Ankur Bapna, Colin Cherry, Yu Zhang, Alexis Conneau, Nobu Morioka

Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition
W. Ronny Huang, Cal Peyser, Tara N. Sainath, Ruoming Pang, Trevor Strohman, Shankar Kumar

UserLibri: A Dataset for ASR Personalization Using Only Text
Theresa Breiner, Swaroop Ramaswamy, Ehsan Variani, Shefali Garg, Rajiv Mathews, Khe Chai Sim, Kilol Gupta, Mingqing Chen, Lara McConnaughey

SNRi Target Training for Joint Speech Enhancement and Recognition
Yuma Koizumi, Shigeki Karita, Arun Narayanan, Sankaran Panchapagesan, Michiel Bacchiani

Turn-Taking Prediction for Natural Conversational Speech
Shuo-Yiin Chang, Bo Li, Tara Sainath, Chao Zhang, Trevor Strohman, Qiao Liang, Yanzhang He

Streaming Intended Query Detection Using E2E Modeling for Continued Conversation
Shuo-Yiin Chang, Guru Prakash, Zelin Wu, Tara Sainath, Bo Li, Qiao Liang, Adam Stambler, Shyam Upadhyay, Manaal Faruqui, Trevor Strohman

Improving Distortion Robustness of Self-Supervised Speech Processing Tasks with Domain Adaptation
Kuan Po Huang, Yu-Kuan Fu, Yu Zhang, Hung-yi Lee

XLS-R: Self-Supervised Cross-Lingual Speech Representation Learning at Scale
Arun Babu, Changhan Wang, Andros Tjandra, Kushal Lakhotia, Qiantong Xu, Naman Goyal, Kritika Singh, Patrick von Platen, Yatharth Saraf, Juan Pino, Alexei Baevski, Alexis Conneau, Michael Auli

Extracting Targeted Training Data from ASR Models, and How to Mitigate It
Ehsan Amid, Om Thakkar, Arun Narayanan, Rajiv Mathews, Françoise Beaufays

Detecting Unintended Memorization in Language-Model-Fused ASR
W. Ronny Huang, Steve Chien, Om Thakkar, Rajiv Mathews

AVATAR: Unconstrained Audiovisual Speech Recognition
Valentin Gabeur, Paul Hongsuck Seo, Arsha Nagrani, Chen Sun, Karteek Alahari, Cordelia Schmid

End-to-End Multi-talker Audio-Visual ASR Using an Active Speaker Attention Module
Richard Rose, Olivier Siohan

Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Multi-person Video
Dmitriy Serdyuk, Otavio Braga, Olivier Siohan

Unsupervised Data Selection via Discrete Speech Representation for ASR
Zhiyun Lu, Yongqiang Wang, Yu Zhang, Wei Han, Zhehuai Chen, Parisa Haghani

Non-parallel Voice Conversion for ASR Augmentation
Gary Wang, Andrew Rosenberg, Bhuvana Ramabhadran, Fadi Biadsy, Jesse Emond, Yinghui Huang, Pedro J. Moreno

Ultra-Low-Bitrate Speech Coding with Pre-trained Transformers
Ali Siahkoohi, Michael Chinen, Tom Denton, W. Bastiaan Kleijn, Jan Skoglund

Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification
Chao Zhang, Bo Li, Tara Sainath, Trevor Strohman, Sepand Mavandadi, Shuo-Yiin Chang, Parisa Haghani

Improving Deliberation by Text-Only and Semi-supervised Training
Ke Hu, Tara N. Sainath, Yanzhang He, Rohit Prabhavalkar, Trevor Strohman, Sepand Mavandadi, Weiran Wang

E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR
W. Ronny Huang, Shuo-yiin Chang, David Rybach, Rohit Prabhavalkar, Tara N. Sainath, Cyril Allauzen, Cal Peyser, Zhiyun Lu

CycleGAN-Based Unpaired Speech Dereverberation
Alexis Conneau, Ankur Bapna, Yu Zhang, Min Ma, Patrick von Platen, Anton Lozhkov, Colin Cherry, Ye Jia, Clara Rivera, Mihir Kale, Daan van Esch, Vera Axelrod, Simran Khanuja, Jonathan Clark, Orhan Firat, Michael Auli, Sebastian Ruder, Jason Riesa, Melvin Johnson

TRILLsson: Distilled Universal Paralinguistic Speech Representations (see blog post)
Joel Shor, Subhashini Venugopalan

Learning Neural Audio Features Without Supervision
Sarthak Yadav, Neil Zeghidour

SpeechPainter: Text-Conditioned Speech Inpainting
Zalan Borsos, Matthew Sharifi, Marco Tagliasacchi

SpecGrad: Diffusion Probabilistic Model-Based Neural Vocoder with Adaptive Noise Spectral Shaping
Yuma Koizumi, Heiga Zen, Kohei Yatabe, Nanxin Chen, Michiel Bacchiani

Distance-Based Sound Separation
Katharine Patterson, Kevin Wilson, Scott Wisdom, John R. Hershey

Analysis of Self-Attention Head Diversity for Conformer-Based Automatic Speech Recognition
Kartik Audhkhasi, Yinghui Huang, Bhuvana Ramabhadran, Pedro J. Moreno

Improving Rare Word Recognition with LM-Aware MWER Training
Wang Weiran, Tongzhou Chen, Tara Sainath, Ehsan Variani, Rohit Prabhavalkar, W. Ronny Huang, Bhuvana Ramabhadran, Neeraj Gaur, Sepand Mavandadi, Cal Peyser, Trevor Strohman, Yanzhang He, David Rybach

MAESTRO: Matched Speech Text Representations Through Modality Matching
Zhehuai Chen, Yu Zhang, Andrew Rosenberg, Bhuvana Ramabhadran, Pedro J. Moreno, Ankur Bapna, Heiga Zen

Pseudo Label is Better Than Human Label
Dongseong Hwang, Khe Chai Sim, Zhouyuan Huo, Trevor Strohman

On the Optimal Interpolation Weights for Hybrid Autoregressive Transducer Model
Ehsan Variani, Michael Riley, David Rybach, Cyril Allauzen, Tongzhou Chen, Bhuvana Ramabhadran

Streaming Align-Refine for Non-autoregressive Deliberation
Wang Weiran, Ke Hu, Tara Sainath

Federated Pruning: Improving Neural Network Efficiency with Federated Learning
Rongmei Lin*, Yonghui Xiao, Tien-Ju Yang, Ding Zhao, Li Xiong, Giovanni Motta, Françoise Beaufays

A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes
Shaojin Ding, Weiran Wang, Ding Zhao, Tara N Sainath, Yanzhang He, Robert David, Rami Botros, Xin Wang, Rina Panigrahy, Qiao Liang, Dongseong Hwang, Ian McGraw, Rohit Prabhavalkar, Trevor Strohman

4-Bit Conformer with Native Quantization Aware Training for Speech Recognition
Shaojin Ding, Phoenix Meadowlark, Yanzhang He, Lukasz Lew, Shivani Agrawal, Oleg Rybakov

Visually-Aware Acoustic Event Detection Using Heterogeneous Graphs
Amir Shirian, Krishna Somandepalli, Victor Sanchez, Tanaya Guha

A Conformer-Based Waveform-Domain Neural Acoustic Echo Canceller Optimized for ASR Accuracy
Sankaran Panchapagesan, Arun Narayanan, Turaj Zakizadeh Shabestary, Shuai Shao, Nathan Howard, Alex Park, James Walker, Alexander Gruenstein

Reducing Domain Mismatch in Self-Supervised Speech Pre-training
Murali Karthick Baskar, Andrew Rosenberg, Bhuvana Ramabhadran, Yu Zhang, Nicolás Serrano

On-the-Fly ASR Corrections with Audio Exemplars
Golan Pundak, Tsendsuren Munkhdalai, Khe Chai Sim

A Language Agnostic Multilingual Streaming On-Device ASR System
Bo Li, Tara Sainath, Ruoming Pang*, Shuo-Yiin Chang, Qiumin Xu, Trevor Strohman, Vince Chen, Qiao Liang, Heguang Liu, Yanzhang He, Parisa Haghani, Sameer Bidichandani

XTREME-S: Evaluating Cross-Lingual Speech Representations
Alexis Conneau, Ankur Bapna, Yu Zhang, Min Ma, Patrick von Platen, Anton Lozhkov, Colin Cherry, Ye Jia, Clara Rivera, Mihir Kale, Daan van Esch, Vera Axelrod, Simran Khanuja, Jonathan Clark, Orhan Firat, Michael Auli, Sebastian Ruder, Jason Riesa, Melvin Johnson

Towards Disentangled Speech Representations
Cal Peyser, Ronny Huang, Andrew Rosenberg, Tara Sainath, Michael Picheny, Kyunghyun Cho

Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition
Shaojin Ding, Rajeev Rikhye, Qiao Liang, Yanzhang He, Quan Wang, Arun Narayanan, Tom O'Malley, Ian McGraw

A Universally-Deployable ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement, and Voice Separation
Tom O’Malley, Arun Narayanan, Quan Wang

Training Text-To-Speech Systems From Synthetic Data: A Practical Approach For Accent Transfer Tasks
Lev Finkelstein, Heiga Zen, Norman Casagrande, Chun-an Chan, Ye Jia, Tom Kenter, Alex Petelin, Jonathan Shen*, Vincent Wan, Yu Zhang, Yonghui Wu, Robert Clark

A Scalable Model Specialization Framework for Training and Inference Using Submodels and Its Application to Speech Model Personalization
Fadi Biadsy, Youzheng Chen, Xia Zhang, Oleg Rybakov, Andrew Rosenberg, Pedro Moreno

Text-Driven Separation of Arbitrary Sounds
Kevin Kilgour, Beat Gfeller, Qingqing Huang, Aren Jansen, Scott Wisdom, Marco Tagliasacchi


Workshops, Tutorials & Special Sessions

The VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC-22)
Organizers include: Arsha Nagrani

Self-Supervised Representation Learning for Speech Processing
Organizers include: Tara Sainath

Learning from Weak Labels
Organizers include: Ankit Shah

RNN Transducers for Named Entity Recognition with Constraints on Alignment for Understanding Medical Conversations
Authors: Hagen Soltau, Izhak Shafran, Mingqiu Wang, Laurent El Shafey

Listening with Googlears: Low-Latency Neural Multiframe Beamforming and Equalization for Hearing Aids
Authors: Samuel Yang, Scott Wisdom, Chet Gnegy, Richard F. Lyon, Sagar Savla

Using Rater and System Metadata to Explain Variance in the VoiceMOS Challenge 2022 Dataset
Authors: Michael Chinen, Jan Skoglund, Chandan K. A. Reddy, Alessandro Ragano, Andrew Hines

Incremental Layer-Wise Self-Supervised Learning for Efficient Unsupervised Speech Domain Adaptation On Device
Authors: Zhouyuan Huo, Dongseong Hwang, Khe Chai Sim, Shefali Garg, Ananya Misra, Nikhil Siddhartha, Trevor Strohman, Françoise Beaufays

Trustworthy Speech Processing
Organizers include: Shrikanth Narayanan



*Work done while at Google.  

Source: Google AI Blog


Introducing CVSS: A Massively Multilingual Speech-to-Speech Translation Corpus

Automatic translation of speech from one language to speech in another language, called speech-to-speech translation (S2ST), is important for breaking down the communication barriers between people speaking different languages. Conventionally, automatic S2ST systems are built with a cascade of automatic speech recognition (ASR), text-to-text machine translation (MT), and text-to-speech (TTS) synthesis sub-systems, so that the system overall is text-centric. Recently, work on S2ST that doesn’t rely on intermediate text representation is emerging, such as end-to-end direct S2ST (e.g., Translatotron) and cascade S2ST based on learned discrete representations of speech (e.g., Tjandra et al.). While early versions of such direct S2ST systems obtained lower translation quality compared to cascade S2ST models, they are gaining traction as they have the potential both to reduce translation latency and compounding errors, and to better preserve paralinguistic and non-linguistic information from the original speech, such as voice, emotion, tone, etc. However, such models usually have to be trained on datasets with paired S2ST data, but the public availability of such corpora is extremely limited.

To foster research on such a new generation of S2ST, we introduce a Common Voice-based Speech-to-Speech translation corpus, or CVSS, which includes sentence-level speech-to-speech translation pairs from 21 languages into English. Unlike existing public corpora, CVSS can be directly used for training such direct S2ST models without any extra processing. In “CVSS Corpus and Massively Multilingual Speech-to-Speech Translation”, we describe the dataset design and development, and demonstrate the effectiveness of the corpus through training of baseline direct and cascade S2ST models and showing performance of a direct S2ST model that approaches that of a cascade S2ST model.

Building CVSS
CVSS is directly derived from the CoVoST 2 speech-to-text (ST) translation corpus, which is further derived from the Common Voice speech corpus. Common Voice is a massively multilingual transcribed speech corpus designed for ASR in which the speech is collected by contributors reading text content from Wikipedia and other text corpora. CoVoST 2 further provides professional text translation for the original transcript from 21 languages into English and from English into 15 languages. CVSS builds on these efforts by providing sentence-level parallel speech-to-speech translation pairs from 21 languages into English (shown in the table below).

To facilitate research with different focuses, two versions of translation speech in English are provided in CVSS, both are synthesized using state-of-the-art TTS systems, with each version providing unique value that doesn’t exist in other public S2ST corpora:

  • CVSS-C: All the translation speech is in a single canonical speaker’s voice. Despite being synthetic, the speech is highly natural, clean, and consistent in speaking style. These properties ease the modeling of the target speech and enable trained models to produce high quality translation speech suitable for general user-facing applications where speech quality is of higher importance than accurately reproducing the speakers' voices.
  • CVSS-T: The translation speech captures the voice from the corresponding source speech. Each S2ST pair has a similar voice on the two sides, despite being in different languages. Because of this, the dataset is suitable for building models where accurate voice preservation is desired, such as for movie dubbing.

Together with the source speech, the two S2ST datasets contain 1,872 and 1,937 hours of speech, respectively.

Source
Language    
Code     Source
  speech (X)  
CVSS-C
  target speech (En)  
CVSS-T
  target speech (En)  
French fr 309.3 200.3 222.3
German de 226.5 137.0 151.2
Catalan ca 174.8 112.1 120.9
Spanish es 157.6 94.3 100.2
Italian it 73.9 46.5 49.2
Persian fa 58.8 29.9 34.5
Russian ru 38.7 26.9 27.4
Chinese zh 26.5 20.5 22.1
Portuguese     pt 20.0 10.4 11.8
Dutch nl 11.2 7.3 7.7
Estonian et 9.0 7.3 7.1
Mongolian mn 8.4 5.1 5.7
Turkish tr 7.9 5.4 5.7
Arabic ar 5.8 2.7 3.1
Latvian lv 4.9 2.6 3.1
Swedish sv 4.3 2.3 2.8
Welsh cy 3.6 1.9 2.0
Tamil ta 3.1 1.7 2.0
Indonesian id 3.0 1.6 1.7
Japanese ja 3.0 1.7 1.8
Slovenian sl 2.9 1.6 1.9
Total 1,153.2 719.1 784.2
Amount of source and target speech of each X-En pair in CVSS (hours).

In addition to translation speech, CVSS also provides normalized translation text matching the pronunciation in the translation speech (on numbers, currencies, acronyms, etc., see data samples below, e.g., where “100%” is normalized as “one hundred percent” or “King George II” is normalized as “king george the second”), which can benefit both model training as well as standardizing the evaluation.

CVSS is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license and it can be freely downloaded online.

Data Samples

Example 1:
Source audio (French)   
Source transcript (French)    Le genre musical de la chanson est entièrement le disco.
CVSS-C translation audio (English)   
CVSS-T translation audio (English)   
Translation text (English)    The musical genre of the song is 100% Disco.
Normalized translation text (English)        the musical genre of the song is one hundred percent disco
   
   
Example 2:
Source audio (Chinese)       
Source transcript (Chinese)        弗雷德里克王子,英国王室成员,为乔治二世之孙,乔治三世之幼弟。
CVSS-C translation audio (English)       
CVSS-T translation audio (English)       
Translation text (English)        Prince Frederick, member of British Royal Family, Grandson of King George II, brother of King George III.
Normalized translation text (English)        prince frederick member of british royal family grandson of king george the second brother of king george the third

Baseline Models
On each version of CVSS, we trained a baseline cascade S2ST model as well as two baseline direct S2ST models and compared their performance. These baselines can be used for comparison in future research.

Cascade S2ST: To build strong cascade S2ST baselines, we trained an ST model on CoVoST 2, which outperforms the previous states of the art by +5.8 average BLEU on all 21 language pairs (detailed in the paper) when trained on the corpus without using extra data. This ST model is connected to the same TTS models used for constructing CVSS to compose very strong cascade S2ST baselines (ST → TTS).

Direct S2ST: We built two baseline direct S2ST models using Translatotron and Translatotron 2. When trained from scratch with CVSS, the translation quality from Translatotron 2 (8.7 BLEU) approaches that of the strong cascade S2ST baseline (10.6 BLEU). Moreover, when both use pre-training the gap decreases to only 0.7 BLEU on ASR transcribed translation. These results verify the effectiveness of using CVSS to train direct S2ST models.

Translation quality of baseline direct and cascade S2ST models built on CVSS-C, measured by BLEU on ASR transcription from speech translation. The pre-training was done on CoVoST 2 without other extra data sets.

Conclusion
We have released two versions of multilingual-to-English S2ST datasets, CVSS-C and CVSS-T, each with about 1.9K hours of sentence-level parallel S2ST pairs, covering 21 source languages. The translation speech in CVSS-C is in a single canonical speaker’s voice, while the same in CVSS-T is in voices transferred from the source speech. Each of these datasets provides unique value not existing in other public S2ST corpora.

We built baseline multilingual direct S2ST models and cascade S2ST models on both datasets, which can be used for comparison in future works. To build strong cascade S2ST baselines, we trained an ST model on CoVoST 2, which outperforms the previous states of the art by +5.8 average BLEU when trained on the corpus without extra data. Nevertheless, the performance of the direct S2ST models approaches the strong cascade baselines when trained from scratch, and with only 0.7 BLEU difference on ASR transcribed translation when utilized pre-training. We hope this work helps accelerate the research on direct S2ST.

Acknowledgments
We acknowledge the volunteer contributors and the organizers of the Common Voice and LibriVox projects for their contribution and collection of recordings, the creators of Common Voice, CoVoST, CoVoST 2, Librispeech and LibriTTS corpora for their previous work. The direct contributors to the CVSS corpus and the paper include Ye Jia, Michelle Tadmor Ramanovich, Quan Wang, Heiga Zen. We also thank Ankur Bapna, Yiling Huang, Jason Pelecanos, Colin Cherry, Alexis Conneau, Yonghui Wu, Hadar Shemtov and Françoise Beaufays for helpful discussions and support.

Source: Google AI Blog


Introducing CVSS: A Massively Multilingual Speech-to-Speech Translation Corpus

Automatic translation of speech from one language to speech in another language, called speech-to-speech translation (S2ST), is important for breaking down the communication barriers between people speaking different languages. Conventionally, automatic S2ST systems are built with a cascade of automatic speech recognition (ASR), text-to-text machine translation (MT), and text-to-speech (TTS) synthesis sub-systems, so that the system overall is text-centric. Recently, work on S2ST that doesn’t rely on intermediate text representation is emerging, such as end-to-end direct S2ST (e.g., Translatotron) and cascade S2ST based on learned discrete representations of speech (e.g., Tjandra et al.). While early versions of such direct S2ST systems obtained lower translation quality compared to cascade S2ST models, they are gaining traction as they have the potential both to reduce translation latency and compounding errors, and to better preserve paralinguistic and non-linguistic information from the original speech, such as voice, emotion, tone, etc. However, such models usually have to be trained on datasets with paired S2ST data, but the public availability of such corpora is extremely limited.

To foster research on such a new generation of S2ST, we introduce a Common Voice-based Speech-to-Speech translation corpus, or CVSS, which includes sentence-level speech-to-speech translation pairs from 21 languages into English. Unlike existing public corpora, CVSS can be directly used for training such direct S2ST models without any extra processing. In “CVSS Corpus and Massively Multilingual Speech-to-Speech Translation”, we describe the dataset design and development, and demonstrate the effectiveness of the corpus through training of baseline direct and cascade S2ST models and showing performance of a direct S2ST model that approaches that of a cascade S2ST model.

Building CVSS
CVSS is directly derived from the CoVoST 2 speech-to-text (ST) translation corpus, which is further derived from the Common Voice speech corpus. Common Voice is a massively multilingual transcribed speech corpus designed for ASR in which the speech is collected by contributors reading text content from Wikipedia and other text corpora. CoVoST 2 further provides professional text translation for the original transcript from 21 languages into English and from English into 15 languages. CVSS builds on these efforts by providing sentence-level parallel speech-to-speech translation pairs from 21 languages into English (shown in the table below).

To facilitate research with different focuses, two versions of translation speech in English are provided in CVSS, both are synthesized using state-of-the-art TTS systems, with each version providing unique value that doesn’t exist in other public S2ST corpora:

  • CVSS-C: All the translation speech is in a single canonical speaker’s voice. Despite being synthetic, the speech is highly natural, clean, and consistent in speaking style. These properties ease the modeling of the target speech and enable trained models to produce high quality translation speech suitable for general user-facing applications where speech quality is of higher importance than accurately reproducing the speakers' voices.
  • CVSS-T: The translation speech captures the voice from the corresponding source speech. Each S2ST pair has a similar voice on the two sides, despite being in different languages. Because of this, the dataset is suitable for building models where accurate voice preservation is desired, such as for movie dubbing.

Together with the source speech, the two S2ST datasets contain 1,872 and 1,937 hours of speech, respectively.

Source
Language    
Code     Source
  speech (X)  
CVSS-C
  target speech (En)  
CVSS-T
  target speech (En)  
French fr 309.3 200.3 222.3
German de 226.5 137.0 151.2
Catalan ca 174.8 112.1 120.9
Spanish es 157.6 94.3 100.2
Italian it 73.9 46.5 49.2
Persian fa 58.8 29.9 34.5
Russian ru 38.7 26.9 27.4
Chinese zh 26.5 20.5 22.1
Portuguese     pt 20.0 10.4 11.8
Dutch nl 11.2 7.3 7.7
Estonian et 9.0 7.3 7.1
Mongolian mn 8.4 5.1 5.7
Turkish tr 7.9 5.4 5.7
Arabic ar 5.8 2.7 3.1
Latvian lv 4.9 2.6 3.1
Swedish sv 4.3 2.3 2.8
Welsh cy 3.6 1.9 2.0
Tamil ta 3.1 1.7 2.0
Indonesian id 3.0 1.6 1.7
Japanese ja 3.0 1.7 1.8
Slovenian sl 2.9 1.6 1.9
Total 1,153.2 719.1 784.2
Amount of source and target speech of each X-En pair in CVSS (hours).

In addition to translation speech, CVSS also provides normalized translation text matching the pronunciation in the translation speech (on numbers, currencies, acronyms, etc., see data samples below, e.g., where “100%” is normalized as “one hundred percent” or “King George II” is normalized as “king george the second”), which can benefit both model training as well as standardizing the evaluation.

CVSS is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license and it can be freely downloaded online.

Data Samples

Example 1:
Source audio (French)   
Source transcript (French)    Le genre musical de la chanson est entièrement le disco.
CVSS-C translation audio (English)   
CVSS-T translation audio (English)   
Translation text (English)    The musical genre of the song is 100% Disco.
Normalized translation text (English)        the musical genre of the song is one hundred percent disco
   
   
Example 2:
Source audio (Chinese)       
Source transcript (Chinese)        弗雷德里克王子,英国王室成员,为乔治二世之孙,乔治三世之幼弟。
CVSS-C translation audio (English)       
CVSS-T translation audio (English)       
Translation text (English)        Prince Frederick, member of British Royal Family, Grandson of King George II, brother of King George III.
Normalized translation text (English)        prince frederick member of british royal family grandson of king george the second brother of king george the third

Baseline Models
On each version of CVSS, we trained a baseline cascade S2ST model as well as two baseline direct S2ST models and compared their performance. These baselines can be used for comparison in future research.

Cascade S2ST: To build strong cascade S2ST baselines, we trained an ST model on CoVoST 2, which outperforms the previous states of the art by +5.8 average BLEU on all 21 language pairs (detailed in the paper) when trained on the corpus without using extra data. This ST model is connected to the same TTS models used for constructing CVSS to compose very strong cascade S2ST baselines (ST → TTS).

Direct S2ST: We built two baseline direct S2ST models using Translatotron and Translatotron 2. When trained from scratch with CVSS, the translation quality from Translatotron 2 (8.7 BLEU) approaches that of the strong cascade S2ST baseline (10.6 BLEU). Moreover, when both use pre-training the gap decreases to only 0.7 BLEU on ASR transcribed translation. These results verify the effectiveness of using CVSS to train direct S2ST models.

Translation quality of baseline direct and cascade S2ST models built on CVSS-C, measured by BLEU on ASR transcription from speech translation. The pre-training was done on CoVoST 2 without other extra data sets.

Conclusion
We have released two versions of multilingual-to-English S2ST datasets, CVSS-C and CVSS-T, each with about 1.9K hours of sentence-level parallel S2ST pairs, covering 21 source languages. The translation speech in CVSS-C is in a single canonical speaker’s voice, while the same in CVSS-T is in voices transferred from the source speech. Each of these datasets provides unique value not existing in other public S2ST corpora.

We built baseline multilingual direct S2ST models and cascade S2ST models on both datasets, which can be used for comparison in future works. To build strong cascade S2ST baselines, we trained an ST model on CoVoST 2, which outperforms the previous states of the art by +5.8 average BLEU when trained on the corpus without extra data. Nevertheless, the performance of the direct S2ST models approaches the strong cascade baselines when trained from scratch, and with only 0.7 BLEU difference on ASR transcribed translation when utilized pre-training. We hope this work helps accelerate the research on direct S2ST.

Acknowledgments
We acknowledge the volunteer contributors and the organizers of the Common Voice and LibriVox projects for their contribution and collection of recordings, the creators of Common Voice, CoVoST, CoVoST 2, Librispeech and LibriTTS corpora for their previous work. The direct contributors to the CVSS corpus and the paper include Ye Jia, Michelle Tadmor Ramanovich, Quan Wang, Heiga Zen. We also thank Ankur Bapna, Yiling Huang, Jason Pelecanos, Colin Cherry, Alexis Conneau, Yonghui Wu, Hadar Shemtov and Françoise Beaufays for helpful discussions and support.

Source: Google AI Blog


TRILLsson: Small, Universal Speech Representations for Paralinguistic Tasks

In recent years, we have seen dramatic improvements on lexical tasks such as automatic speech recognition (ASR). However, machine systems still struggle to understand paralinguistic aspects — such as tone, emotion, whether a speaker is wearing a mask, etc. Understanding these aspects represents one of the remaining difficult problems in machine hearing. In addition, state-of-the-art results often come from ultra-large models trained on private data, making them impractical to run on mobile devices or to release publicly.

In “Universal Paralinguistic Speech Representations Using Self-Supervised Conformers”, to appear in ICASSP 2022, we introduce CAP12— the 12th layer of a 600M parameter model trained on the YT-U training dataset using self-supervision. We demonstrate that the CAP12 model outperforms nearly all previous results in our paralinguistic benchmark, sometimes by large margins, even though previous results are often task-specific. In “TRILLsson: Distilled Universal Paralinguistic Speech Representations'', we introduce the small, performant, publicly-available TRILLsson models and demonstrate how we reduced the size of the high-performing CAP12 model by 6x-100x while maintaining 90-96% of the performance. To create TRILLsson, we apply knowledge distillation on appropriately-sized audio chunks and use different architecture types to train smaller, faster networks that are small enough to run on mobile devices.

1M-Hour Dataset to Train Ultra-Large Self-Supervised Models
We leverage the YT-U training dataset to train the ultra-large, self-supervised CAP12 model. The YT-U dataset is a highly varied, 900M+ hour dataset that contains audio of various topics, background conditions, and speaker acoustic properties.

Video categories by length (outer) and number (inner), demonstrating the variety in the YT-U dataset (figure from BigSSL)

We then modify a Wav2Vec 2.0 self-supervised training paradigm, which can solve tasks using raw data without labels, and combine it with ultra-large Conformer models. Because self-training doesn't require labels, we can take full advantage of YT-U by scaling up our models to some of the largest model sizes ever trained, including 600M, 1B, and 8B parameters.

NOSS: A Benchmark for Paralinguistic Tasks
We demonstrate that an intermediate representation of one of the previous models contains a state-of-the-art representation for paralinguistic speech. We call the 600M parameter Conformer model without relative attention Conformer Applied to Paralinguistics (CAP). We exhaustively search through all intermediate representations of six ultra-large models and find that layer 12 (CAP12) outperforms previous representations by significant margins.

To measure the quality of the roughly 300 candidate paralinguistic speech representations, we evaluate on an expanded version of the NOn-Semantic Speech (NOSS) benchmark, which is a collection of well-studied paralinguistic speech tasks, such as speech emotion recognition, language identification, and speaker identification. These tasks focus on paralinguistics aspects of speech, which require evaluating speech features on the order of 1 second or longer, rather than lexical features, which require 100ms or shorter. We then add to the benchmark a mask-wearing task introduced at Interspeech 2020, a fake speech detection task (ASVSpoof 2019), a task to detect the level of dysarthria from project Euphonia, and an additional speech emotion recognition task (IEMOCAP). By expanding the benchmark and increasing the diversity of the tasks, we empirically demonstrate that CAP12 is even more generally useful than previous representations.

Simple linear models on time-averaged CAP12 representations even outperform complex, task-specific models on five out of eight paralinguistic tasks. This is surprising because comparable models sometimes use additional modalities (e.g., vision and speech, or text and speech) as well. Furthermore, CAP12 is exceptionally good at emotion recognition tasks. CAP12 embeddings also outperform all other embeddings on all other tasks with only a single exception: for one embedding from a supervised network on the dysarthria detection task.

Model Voxceleb   Voxforge   Speech Commands   ASVSpoof2019∗∗   Euphonia#   CREMA-D   IEMOCAP
Prev SoTA - 95.4 97.9 5.11 45.9 74.0 67.6+
TRILL 12.6 84.5 77.6 74.6 48.1 65.7 54.3
ASR Embedding 5.2 98.9 96.1 11.2 54.5 71.8 65.4
Wav2Vec2 layer 6†† 17.9 98.5 95.0 6.7 48.2 77.4 65.8
CAP12 51.0 99.7 97.0 2.5 51.5 88.2 75.0
Test performance on the NOSS Benchmark and extended tasks. “Prev SoTA” indicates the previous best performing state-of-the-art model, which has arbitrary complexity, but all other rows are linear models on time-averaged input. Filtered according to YouTube’s privacy guidelines. ∗∗ Uses equal error rate [20]. # The only non-public dataset. We exclude it from aggregate scores. Audio and visual features used in previous state-of-the-art models. + The previous state-of-the-art model performed cross-validation. For our evaluation, we hold out two specific speakers as a test. †† Wav2Vec 2.0 model from HuggingFace. Best overall layer was layer 6.

TRILLsson: Small, High Quality, Publicly Available Models
Similar to FRILL, our next step was to make an on-device, publicly available version of CAP12. This involved using knowledge distillation to train smaller, faster, mobile-friendly architectures. We experimented with EfficientNet, Audio Spectrogram Transformer (AST), and ResNet. These model types are very different, and cover both fixed-length and arbitrary-length inputs. EfficientNet comes from a neural architecture search over vision models to find simultaneously performant and efficient model structures. AST models are transformers adapted to audio inputs. ResNet is a standard architecture that has shown good performance across many different models.

We trained models that performed on average 90-96% as well as CAP12, despite being 1%-15% the size and trained using only 6% the data. Interestingly, we found that different architecture types performed better at different sizes. ResNet models performed best at the low end, EfficientNet in the middle, and AST models at the larger end.

Aggregate embedding performance vs. model size for various student model architectures and sizes. We demonstrate that ResNet architectures perform best for small sizes, EfficientNetV2 performs best in the midsize model range, up to the largest model size tested, after which the larger AST models are best.

We perform knowledge distillation with the goal of matching a student, with a fixed-size input, to the output of a teacher, with a variable-size input, for which there are two methods of generating student targets: global matching and local matching. Global matching produces distillation targets by generating CAP12 embeddings for an entire audio clip, and then requires that a student match the target from just a small segment of audio (e.g., 2 seconds). Local matching requires that the student network match the average CAP12 embedding just over the smaller portion of the audio that the student sees. In our work, we focused on local matching.

Two types of generating distillation targets for sequences. Left: Global matching uses the average CAP12 embedding over the whole clip for the target for each local chunk. Right: Local matching uses CAP12 embeddings averaged just over local clips as the distillation target.

Observation of Bimodality and Future Directions
Paralinguistic information shows an unexpected bimodal distribution. For the CAP model that operates on 500 ms input segments, and two of the full-input Conformer models, intermediate representations gradually increase in paralinguistic information, then decrease, then increase again, and finally lose this information towards the output layer. Surprisingly, this pattern is also seen when exploring the intermediate representations of networks trained on retinal images.

500 ms inputs to CAP show a relatively pronounced bimodal distribution of paralinguistic information across layers.
Two of the conformer models with full inputs show a bimodal distribution of paralinguistic information across layers.

We hope that smaller, faster models for paralinguistic speech unlock new applications in speech recognition, text-to-speech generation, and understanding user intent. We also expect that smaller models will be more easily interpretable, which will allow researchers to understand what aspects of speech are important for paralinguistics. Finally, we hope that our open-sourced speech representations are used by the community to improve paralinguistic speech tasks and user understanding in private or small datasets.

Acknowledgements
I'd like to thank my co-authors Aren Jansen, Wei Han, Daniel Park, Yu Zhang, and Subhashini Venugopalan for their hard work and creativity on this project. I'd also like to thank the members of the large collaboration for the BigSSL work, without which these projects would not be possible. The team includes James Qin, Anmol Gulati, Yuanzhong Xu, Yanping Huang, Shibo Wang, Zongwei Zhou, Bo Li, Min Ma, William Chan, Jiahui Yu, Yongqiang Wang, Liangliang Cao, Khe Chai Sim, Bhuvana Ramabhadran, Tara N. Sainath, Françoise Beaufays, Zhifeng Chen, Quoc V. Le, Chung-Cheng Chiu, Ruoming Pang, and Yonghui Wu.

Source: Google AI Blog


Recreating Natural Voices for People with Speech Impairments

On June 2nd, 2021, Major League Baseball in the United States celebrated Lou Gehrig Day, commemorating both the day in 1925 that Lou Gehrig became the Yankees’ starting first baseman, and the day in 1941 that he passed away from amyotrophic lateral sclerosis (ALS, also known as Lou Gehrig’s disease) at the age of 37. ALS is a progressive neurodegenerative disease that affects motor neurons, which connect the brain with the muscles throughout the body, and govern muscle control and voluntary movements. When voluntary muscle control is affected, people may lose their ability to speak, eat, move and breathe.

In honor of Lou Gehrig, former NFL player and ALS advocate Steve Gleason, who lost his ability to speak due to ALS, recited Gehrig’s famous “Luckiest Man” speech at the June 2nd event using a recreation of his voice generated by a machine learning (ML) model. Gleason’s voice recreation was developed in collaboration with Google’s Project Euphonia, which aims to empower people who have impaired speaking ability due to ALS to better communicate using their own voices.

Steve Gleason, who lost his voice to ALS, worked with Google’s Project Euphonia to generate a speech in his own voice in honor of Lou Gehrig. A portion of Gleason’s speech was broadcast in ballparks across the country during the 4th inning on June 2nd, 2021.

Today we describe PnG NAT, the model adopted by Project Euphonia to recreate Steve Gleason’s voice. PnG NAT is a new text-to-speech synthesis (TTS) model that merges two state-of-the-art technologies, PnG BERT and Non-Attentive Tacotron (NAT), into a single model. It demonstrates significantly better quality and fluency than previous technologies, and represents a promising approach that can be extended to a wider array of users.

Recreating a Voice
Non-Attentive Tacotron (NAT) is the successor to Tacotron 2, a sequence-to-sequence neural TTS model proposed in 2017. Tacotron 2 used an attention module to connect the input text sequence and the output speech spectrogram frame sequence, so that the model knows which part of the text to pay attention to when generating each time step of the synthesized speech spectrogram. Tacotron 2 was the first TTS model that was able to synthesize speech that sounds as natural as a person speaking. However, with extensive experimentation we discovered that there is a small probability that the model can suffer from robustness issues — such as babbling, repeating, or skipping part of the text — due to the inherent flexibility of the attention mechanism.

NAT improves upon Tacotron 2 by replacing the attention module with a duration-based upsampler, which predicts a duration for each input phoneme and upsamples the encoded phoneme representation so that the output length corresponds to the length of the predicted speech spectrogram. Such a change both resolves the robustness issue, and improves the naturalness of the synthesized speech. This approach also enables precise control of the speech duration for each phoneme of the input text while still maintaining highly natural synthesis quality. Because recordings of people with ALS often exhibit disfluent speech, this ability to exert per-phoneme control is key for achieving the fluency of the recreated voice.

Non-Attentive Tacotron (NAT) model.

While NAT addresses the robustness issue and enables precise duration control in neural TTS, we build upon it to further improve the natural language understanding of the TTS input. For this, we apply PnG BERT, which uses an approach similar to BERT, but is specifically designed for TTS. It is pre-trained with self-supervision on both the phoneme representation and the grapheme representation of the same content from a large text corpus, and then is used as the encoder of the TTS model. This results in a significant improvement of the prosody and pronunciation of the synthesized speech, especially in difficult cases.

Take, for example, the following audio, which was synthesized from a regular NAT model that takes only phonemes as input:

In comparison, the audio synthesized from PnG NAT on the same input text includes an additional pause that makes the meaning more clear.

The input text to both models is, “To cancel the payment, press one; or to continue, two.” Notice the different pause lengths before the ending “two” in the two versions. The word “two” in the version output by the regular NAT model could be confused for “too”. Because “too” and “two” have identical pronunciation (and thus the same phoneme representation), the regular NAT model does not understand which of the two is appropriate, and assumes it to be the word that more frequently follows a comma, “too”. In contrast, the PnG NAT model can more easily tell the difference, because it takes graphemes in addition to phonemes as input, and thus makes more appropriate pause.

The PnG NAT model integrates the pre-trained PnG BERT model as the encoder to the NAT model. The hidden representations output from the encoder are used by NAT to predict the duration of each phoneme, and are then upsampled to match the length of the audio spectrogram, as outlined above. In the final step, a non-attentive decoder converts the upsampled hidden representations into audio speech spectrograms, which are finally converted into audio waveforms by a neural vocoder.

PnG BERT and the pre-training objectives. Yellow boxes represent phonemes, and pink boxes represent graphemes.
PnG NAT: PnG BERT replaces the original encoder in the NAT model. The random masking for the Masked Language Model (MLM) pre-training is removed.

To recreate Steve Gleason’s voice, we first trained a PnG NAT model with recordings from 31 professional speakers, and then fine-tuned it with 30 minutes of Gleason’s recordings. Because these latter recordings were made after he was diagnosed with ALS, they exhibit signs of slurring. The fine tuned model was able to synthesize speech that sounds very similar to these recordings. However, because the symptoms of ALS were already present in Gleason’s speech, they exhibited some similar disfluencies.

To mitigate this, we leveraged the phoneme duration control of NAT as well as the model trained with professional speakers. We first predicted the durations of each phoneme for both a professional speaker and for Gleason, and then used the geometric mean of the two durations for each phoneme to guide the NAT output. As a result, the model is able to speak in Gleason’s voice, but more fluently than in the original recordings.

Here is the full version of the synthesized Lou Gehrig speech in Gleason’s voice:

Besides recreating voices for people with ALS, PnG NAT is also powering voices for a variety of customers through Google Cloud Custom Voice.

Project Euphonia
Of the millions of people around the world who have neurologic conditions that may impact their speech, such as ALS, cerebral palsy or Down syndrome, many may find it difficult to be understood, which can make face-to-face communication challenging. Using voice-activated technologies can be frustrating too, as they don’t always work reliably. Project Euphonia is a Google Research initiative focused on helping people with impaired speech be better understood. The team is researching ways to improve speech recognition for individuals with speech impairments (see recent blog post and segment in TODAY show), as well as customized text-to-speech technology (see Age of AI documentary featuring former NFL player Tim Shaw).

Acknowledgements
Many people across Google Research, Google Cloud and Consumer Apps, and Google Accessibility teams contributed to this project and the event, including Michael Brenner, Bob MacDonald, Heiga Zen, Yu Zhang, Jonathan Shen, Isaac Elias‎, Yonghui Wu, Anne Keck, Danielle Notaro, Kevin Hogan, Zack Kaplan, KR Liu, Kyndra Price, Zoe Ortiz.

Source: Google AI Blog


Two New Datasets for Conversational NLP: TimeDial and Disfl-QA

A key challenge in natural language processing (NLP) is building conversational agents that can understand and reason about different language phenomena that are unique to realistic speech. For example, because people do not always premeditate exactly what they are going to say, a natural conversation often includes interruptions to speech, called disfluencies. Such disfluencies can be simple (like interjections, repetitions, restarts, or corrections), which simply break the continuity of a sentence, or more complex semantic disfluencies, in which the underlying meaning of a phrase changes. In addition, understanding a conversation also often requires knowledge of temporal relationships, like whether an event precedes or follows another. However, conversational agents built on today’s NLP models often struggle when confronted with temporal relationships or with disfluencies, and progress on improving their performance has been slow. This is due, in part, to a lack of datasets that involve such interesting conversational and speech phenomena.

To stir interest in this direction within the research community, we are excited to introduce TimeDial, for temporal commonsense reasoning in dialog, and Disfl-QA, which focuses on contextual disfluencies. TimeDial presents a new multiple choice span filling task targeted for temporal understanding, with an annotated test set of over ~1.1k dialogs. Disfl-QA is the first dataset containing contextual disfluencies in an information seeking setting, namely question answering over Wikipedia passages, with ~12k human annotated disfluent questions. These benchmark datasets are the first of their kind and show a significant gap between human performance and current state of the art NLP models.

TimeDial
While people can effortlessly reason about everyday temporal concepts, such as duration, frequency, or relative ordering of events in a dialog, such tasks can be challenging for conversational agents. For example, current NLP models often make a poor selection when tasked with filling in a blank (as shown below) that assumes a basic level of world knowledge for reasoning, or that requires understanding explicit and implicit inter-dependencies between temporal concepts across conversational turns.

It is easy for a person to judge that “half past one” and “quarter to two” are more plausible options to fill in the blank than “half past three” and “half past nine”. However, performing such temporal reasoning in the context of a dialog is not trivial for NLP models, as it requires appealing to world knowledge (i.e., knowing that the participants are not yet late for the meeting) and understanding the temporal relationship between events (“half past one” is before “three o’clock”, while “half past three” is after it). Indeed, current state-of-the-art models like T5 and BERT end up picking the wrong answers — “half past three” (T5) and “half past nine” (BERT).

The TimeDial benchmark dataset (derived from the DailyDialog multi-turn dialog corpus) measures models’ temporal commonsense reasoning abilities within a dialog context. Each of the ~1.5k dialogs in the dataset is presented in a multiple choice setup, in which one temporal span is masked out and the model is asked to find all correct answers from a list of four options to fill in the blank.

In our experiments we found that while people can easily answer these multiple choice questions (at 97.8% accuracy), state-of-the-art pre-trained language models still struggle on this challenge set. We experiment across three different modeling paradigms: (i) classification over the provided 4 options using BERT, (ii) mask filling for the masked span in the dialog using BERT-MLM, (iii) generative methods using T5. We observe that all the models struggle on this challenge set, with the best variant only scoring 73%.

Model   2-best Accuracy
Human   97.8%
BERT - Classification   50.0%
BERT - Mask Filling   68.5%
T5 - Generation   73.0%

Qualitative error analyses show that the pre-trained language models often rely on shallow, spurious features (particularly text matching), instead of truly doing reasoning over the context. It is likely that building NLP models capable of performing the kind of temporal commonsense reasoning needed for TimeDial requires rethinking how temporal objects are represented within general text representations.

Disfl-QA
As disfluency is inherently a speech phenomenon, it is most commonly found in text output from speech recognition systems. Understanding such disfluent text is key to building conversational agents that understand human speech. Unfortunately, research in the NLP and speech community has been impeded by the lack of curated datasets containing such disfluencies, and the datasets that are available, like Switchboard, are limited in scale and complexity. As a result, it’s difficult to stress test NLP models in the presence of disfluencies.

Disfluency   Example
Interjection   When is, uh, Easter this year?
Repetition   When is EasEaster this year?
Correction   When is Lent, I mean Easter, this year?
Restart   How much, no wait, when is Easter this year?
Different kinds of disfluencies. The reparandum (words intended to be corrected or ignored; in red), interregnum (optional discourse cues; in grey) and repair (the corrected words; in blue).

Disfl-QA is the first dataset containing contextual disfluencies in an information seeking setting, namely question answering over Wikipedia passages from SQuAD. Disfl-QA is a targeted dataset for disfluencies, in which all questions (~12k) contain disfluencies, making for a much larger disfluent test set than prior datasets. Over 90% of the disfluencies in Disfl-QA are corrections or restarts, making it a much more difficult test set for disfluency correction. In addition, compared to earlier disfluency datasets, it contains a wider variety of semantic distractors, i.e., distractors that carry semantic meaning as opposed to simpler speech disfluencies. 

Passage: …The Normans (Norman: Nourmands; French: Normands; Latin: Normanni) were the people who in the 10th and 11th centuries gave their name to Normandy, a region in France. They were descended from Norse ("Norman" comes from "Norseman") raiders and pirates from Denmark, Iceland and Norway who, under their leader Rollo, …
Q1:   In what country is Normandy located? France ✓
DQ1:   In what country is Norse found no wait Normandy not Norse? Denmark X
Q2:   When were the Normans in Normandy? 10th and 11th centuries ✓
DQ2:   From which countries no tell me when were the Normans in Normandy? Denmark, Iceland and Norway X
A passage and questions (Qi) from SQuAD dataset, along with their disfluent versions (DQi), consisting of semantic distractors (like “Norse” and “from which countries”) and predictions from a T5 model.

Here, the first question (Q1) is seeking an answer about the location of Normandy. In the disfluent version (DQ1) Norse is mentioned before the question is corrected. The presence of this correctional disfluency confuses the QA model, which tends to rely on shallow textual cues from the question for making predictions.

Disfl-QA also includes newer phenomena, such as coreference (expression referring to the same entity) between the reparandum and the repair.

SQuAD  Disfl-QA
Who does BSkyB have an operating license from?  Who removed [BSkyB’s] operating license, no scratch that, who do [they] have [their] operating license from?

Experiments show that the performance of existing state-of-the-art language model–based question answering systems degrades significantly when tested on Disfl-QA and heuristic disfluencies (presented in the paper) in a zero-shot setting.

Dataset   F1
SQuAD   89.59
Heuristics   65.27 (-24.32)
Disfl-QA   61.64 (-27.95)

We show that data augmentation methods partially recover the loss in performance and also demonstrate the efficacy of using human-annotated training data for fine-tuning. We argue that researchers need large-scale disfluency datasets in order for NLP models to be robust to disfluencies.

Conclusion
Understanding language phenomena that are unique to human speech, like disfluencies and temporal reasoning, among others, is a key ingredient for enabling more natural human–machine communication in the near future. With TimeDial and Disfl-QA, we aim to fill a major research gap by providing these datasets as testbeds for NLP models, in order to evaluate their robustness to ubiquitous phenomena across different tasks. It is our hope that the broader NLP community will devise generalized few-shot or zero-shot approaches to effectively handle these phenomena, without requiring task-specific human-annotated training datasets, constructed specifically for these challenges.

Acknowledgments
The TimeDial work has been a team effort involving Lianhui Qi, Luheng He, Yenjin Choi, Manaal Faruqui and the authors. The Disfl-QA work has been a collaboration involving Jiacheng Xu, Diyi Yang, Manaal Faruqui.

Source: Google AI Blog


Two New Datasets for Conversational NLP: TimeDial and Disfl-QA

A key challenge in natural language processing (NLP) is building conversational agents that can understand and reason about different language phenomena that are unique to realistic speech. For example, because people do not always premeditate exactly what they are going to say, a natural conversation often includes interruptions to speech, called disfluencies. Such disfluencies can be simple (like interjections, repetitions, restarts, or corrections), which simply break the continuity of a sentence, or more complex semantic disfluencies, in which the underlying meaning of a phrase changes. In addition, understanding a conversation also often requires knowledge of temporal relationships, like whether an event precedes or follows another. However, conversational agents built on today’s NLP models often struggle when confronted with temporal relationships or with disfluencies, and progress on improving their performance has been slow. This is due, in part, to a lack of datasets that involve such interesting conversational and speech phenomena.

To stir interest in this direction within the research community, we are excited to introduce TimeDial, for temporal commonsense reasoning in dialog, and Disfl-QA, which focuses on contextual disfluencies. TimeDial presents a new multiple choice span filling task targeted for temporal understanding, with an annotated test set of over ~1.1k dialogs. Disfl-QA is the first dataset containing contextual disfluencies in an information seeking setting, namely question answering over Wikipedia passages, with ~12k human annotated disfluent questions. These benchmark datasets are the first of their kind and show a significant gap between human performance and current state of the art NLP models.

TimeDial
While people can effortlessly reason about everyday temporal concepts, such as duration, frequency, or relative ordering of events in a dialog, such tasks can be challenging for conversational agents. For example, current NLP models often make a poor selection when tasked with filling in a blank (as shown below) that assumes a basic level of world knowledge for reasoning, or that requires understanding explicit and implicit inter-dependencies between temporal concepts across conversational turns.

It is easy for a person to judge that “half past one” and “quarter to two” are more plausible options to fill in the blank than “half past three” and “half past nine”. However, performing such temporal reasoning in the context of a dialog is not trivial for NLP models, as it requires appealing to world knowledge (i.e., knowing that the participants are not yet late for the meeting) and understanding the temporal relationship between events (“half past one” is before “three o’clock”, while “half past three” is after it). Indeed, current state-of-the-art models like T5 and BERT end up picking the wrong answers — “half past three” (T5) and “half past nine” (BERT).

The TimeDial benchmark dataset (derived from the DailyDialog multi-turn dialog corpus) measures models’ temporal commonsense reasoning abilities within a dialog context. Each of the ~1.5k dialogs in the dataset is presented in a multiple choice setup, in which one temporal span is masked out and the model is asked to find all correct answers from a list of four options to fill in the blank.

In our experiments we found that while people can easily answer these multiple choice questions (at 97.8% accuracy), state-of-the-art pre-trained language models still struggle on this challenge set. We experiment across three different modeling paradigms: (i) classification over the provided 4 options using BERT, (ii) mask filling for the masked span in the dialog using BERT-MLM, (iii) generative methods using T5. We observe that all the models struggle on this challenge set, with the best variant only scoring 73%.

Model   2-best Accuracy
Human   97.8%
BERT - Classification   50.0%
BERT - Mask Filling   68.5%
T5 - Generation   73.0%

Qualitative error analyses show that the pre-trained language models often rely on shallow, spurious features (particularly text matching), instead of truly doing reasoning over the context. It is likely that building NLP models capable of performing the kind of temporal commonsense reasoning needed for TimeDial requires rethinking how temporal objects are represented within general text representations.

Disfl-QA
As disfluency is inherently a speech phenomenon, it is most commonly found in text output from speech recognition systems. Understanding such disfluent text is key to building conversational agents that understand human speech. Unfortunately, research in the NLP and speech community has been impeded by the lack of curated datasets containing such disfluencies, and the datasets that are available, like Switchboard, are limited in scale and complexity. As a result, it’s difficult to stress test NLP models in the presence of disfluencies.

Disfluency   Example
Interjection   When is, uh, Easter this year?
Repetition   When is EasEaster this year?
Correction   When is Lent, I mean Easter, this year?
Restart   How much, no wait, when is Easter this year?
Different kinds of disfluencies. The reparandum (words intended to be corrected or ignored; in red), interregnum (optional discourse cues; in grey) and repair (the corrected words; in blue).

Disfl-QA is the first dataset containing contextual disfluencies in an information seeking setting, namely question answering over Wikipedia passages from SQuAD. Disfl-QA is a targeted dataset for disfluencies, in which all questions (~12k) contain disfluencies, making for a much larger disfluent test set than prior datasets. Over 90% of the disfluencies in Disfl-QA are corrections or restarts, making it a much more difficult test set for disfluency correction. In addition, compared to earlier disfluency datasets, it contains a wider variety of semantic distractors, i.e., distractors that carry semantic meaning as opposed to simpler speech disfluencies. 

Passage: …The Normans (Norman: Nourmands; French: Normands; Latin: Normanni) were the people who in the 10th and 11th centuries gave their name to Normandy, a region in France. They were descended from Norse ("Norman" comes from "Norseman") raiders and pirates from Denmark, Iceland and Norway who, under their leader Rollo, …
Q1:   In what country is Normandy located? France ✓
DQ1:   In what country is Norse found no wait Normandy not Norse? Denmark X
Q2:   When were the Normans in Normandy? 10th and 11th centuries ✓
DQ2:   From which countries no tell me when were the Normans in Normandy? Denmark, Iceland and Norway X
A passage and questions (Qi) from SQuAD dataset, along with their disfluent versions (DQi), consisting of semantic distractors (like “Norse” and “from which countries”) and predictions from a T5 model.

Here, the first question (Q1) is seeking an answer about the location of Normandy. In the disfluent version (DQ1) Norse is mentioned before the question is corrected. The presence of this correctional disfluency confuses the QA model, which tends to rely on shallow textual cues from the question for making predictions.

Disfl-QA also includes newer phenomena, such as coreference (expression referring to the same entity) between the reparandum and the repair.

SQuAD  Disfl-QA
Who does BSkyB have an operating license from?  Who removed [BSkyB’s] operating license, no scratch that, who do [they] have [their] operating license from?

Experiments show that the performance of existing state-of-the-art language model–based question answering systems degrades significantly when tested on Disfl-QA and heuristic disfluencies (presented in the paper) in a zero-shot setting.

Dataset   F1
SQuAD   89.59
Heuristics   65.27 (-24.32)
Disfl-QA   61.64 (-27.95)

We show that data augmentation methods partially recover the loss in performance and also demonstrate the efficacy of using human-annotated training data for fine-tuning. We argue that researchers need large-scale disfluency datasets in order for NLP models to be robust to disfluencies.

Conclusion
Understanding language phenomena that are unique to human speech, like disfluencies and temporal reasoning, among others, is a key ingredient for enabling more natural human–machine communication in the near future. With TimeDial and Disfl-QA, we aim to fill a major research gap by providing these datasets as testbeds for NLP models, in order to evaluate their robustness to ubiquitous phenomena across different tasks. It is our hope that the broader NLP community will devise generalized few-shot or zero-shot approaches to effectively handle these phenomena, without requiring task-specific human-annotated training datasets, constructed specifically for these challenges.

Acknowledgments
The TimeDial work has been a team effort involving Lianhui Qi, Luheng He, Yenjin Choi, Manaal Faruqui and the authors. The Disfl-QA work has been a collaboration involving Jiacheng Xu, Diyi Yang, Manaal Faruqui.

Source: Google AI Blog


FRILL: On-Device Speech Representations using TensorFlow-Lite

Representation learning is a machine learning (ML) method that trains a model to identify salient features that can be applied to a variety of downstream tasks, ranging from natural language processing (e.g., BERT and ALBERT) to image analysis and classification (e.g., Inception layers and SimCLR). Last year, we introduced a benchmark for comparing speech representations and a new, generally-useful speech representation model (TRILL). TRILL is based on temporal proximity, and tries to map speech that occurs close together in time to a lower-dimensional embedding that captures temporal proximity in the embedding space. Since its release, the research community has used TRILL on a diverse set of tasks, such as age classification, video thumbnail selection, and language identification. However, despite achieving state-of-the-art performance, TRILL and other neural network-based approaches require more memory and take longer to compute than signal processing operations that deal with simple features, like loudness, average energy, pitch, etc.

In our recent paper "FRILL: A Non-Semantic Speech Embedding for Mobile Devices", to appear at Interspeech 2021, we create a new model that is 40% the size of TRILL and and a feature set that can be computed over 32x faster on mobile phone, with an average decrease in accuracy of less than 2%. This marks an important step towards fully on-device applications of speech ML models, which will lead to better personalization, improved user experiences and greater privacy, an important aspect of developing AI responsibly. We release the code to create FRILL on github, and a pre-trained FRILL model on TensorFlow Hub.

FRILL: Smaller, Faster TRILL
The TRILL architecture is based on a modified version of ResNet50, an architecture that is computationally taxing for constrained hardware, like mobile phones or smart home devices. On the other hand, architectures like MobileNetV3 have been designed with hardware-aware AutoML to perform well on mobile devices. To take advantage of this, we leverage knowledge distillation to combine the benefits of MobileNetV3’s performance with TRILL’s representations.

In the distillation process, the smaller model (i.e., the "student") tries to match the output of the larger model ("teacher") on the AudioSet dataset. Whereas the original TRILL model learned its weights by optimizing a self-supervised loss that clustered audio segments close in time, the student model learns its weights through a fully-supervised loss that ignores temporal matching and instead tries to match TRILL outputs on the training data. The fully-supervised learning signal is often stronger than self-supervision, and allows us to train more quickly.

Knowledge distillation for non-semantic speech embeddings. The dashed line shows the student model output. The "teacher network" is the TRILL network, where "Layer 19" was the best-performing internal representation. The "Student Hyperparameters" on the left are the options explored in this study, the result of which are 144 distinct models. These models were trained with mean-squared error (MSE) to try to match TRILL's Layer 19.

Choosing the Best Student Model
We perform distillation with a variety of student models, each trained with a specific combination of architecture choices (explained below). To measure each student model’s latency, we leverage TensorFlow Lite (TFLite), a framework that enables execution of TensorFlow models on edge devices. Each candidate model is first converted into TFLite’s flatbuffer format for 32-bit floating point inference and then sent to the target device (in this case, a Pixel 1) for benchmarking. These measurements help us to accurately assess the latency versus quality tradeoffs across all student models and to minimize the loss of quality in the conversion process.

Architecture Choices and Optimizations
We explored different neural network architectures and features that balance latency and accuracy — models with fewer parameters are usually smaller and faster, but have less representational power and therefore generate less generally-useful representations. We trained 144 different models across a number of hyperparameters, all based on the MobileNetV3 architecture:

  1. MobileNetV3 size and width: MobileNetV3 was released in different sizes for use in different environments. The size refers to which MobileNetV3 architecture we used. The width, sometimes known as alpha, proportionally decreases or increases the number of filters in each layer. A width of 1.0 corresponds to the number of filters in the original paper.
  2. Global average pooling: MobileNetV3 normally produces a set of two-dimensional feature maps. These are flattened, concatenated, and passed to the bottleneck layer. However, this bottleneck is often still too large to be computed quickly. We reduce the size of the bottleneck layer kernel by taking the global average of all ”pixels” in each output feature map. Our intuition is that the discarded temporal information is less important for learning a non-semantic speech representation due to the fact that relevant aspects of the signal are stable across time.
  3. Bottleneck compression: A significant portion of the student model’s weights are located in the bottleneck layer. To reduce the size of this layer, we apply a compression operator based on singular value decomposition (SVD) that learns a low-rank approximation of the bottleneck weight matrix.
  4. Quantization-aware training: Since the bottleneck layer has most of the model weights, we use quantization-aware training (QAT) to gradually reduce the numerical precision of the bottleneck weights during training. QAT allows the model to adjust to the lower numerical precision during training, instead of potentially causing performance degradation by introducing quantization after training finishes.

Results
We evaluated each of these models on the Non-Semantic Speech Benchmark (NOSS) and two new tasks — a challenging task to detect whether a speaker is wearing a mask and the human-noise subset of the Environment Sound Classification dataset, which includes labels like “coughing” and “sneezing”. After eliminating models that have strictly better alternatives, we are left with eight ”frontier” models on the quality vs. latency curve, which are the models that had no faster and better performance alternatives at a corresponding quality threshold or latency in our batch of 144 models. We plot the latency vs. quality curve of only these "frontier" models below, and we ignore models that are strictly worse.

Embedding quality and latency tradeoff. The x-axis represents the inference latency and the y-axis shows the difference in accuracy from TRILL’s performance, averaged across benchmark datasets.

FRILL is the best performing sub-10ms inference model, with an inference time of 8.5 ms on a Pixel 1 (about 32x faster than TRILL), and is also roughly 40% the size of TRILL. The frontier curve plateaus at about 10ms latency, which means that at low latency, one can achieve much better performance with minimal latency costs, while achieving improved performance at latencies beyond 10ms is more difficult. This supports our choice of experiment hyperparameters. FRILL's per-task performance is shown in the table below.

FRILL TRILL

Size (MB) 38.5 98.1
Latency (ms) 8.5 275.3

Voxceleb1* 45.5 46.8
Voxforge 78.8 84.5
Speech Commands 81.0 81.7
CREMA-D 71.3 65.9
SAVEE 63.3 70.0
Masked Speech 68.0 65.8
ESC-50 HS 87.9 86.4
Accuracy on each of the classification tasks (higher is better).
*Results in our study use a small subset of Voxceleb1 filtered according to internal privacy guidelines. Interested readers can run our study on the full dataset using TensorFlow Datasets and our open-source evaluation code.

Finally, we evaluate the relative contribution of each of our hyperparameters. We find that for our experiments, quantization-aware training, bottleneck compression and global average pooling most reduced the latency of the resulting models. At the same time bottleneck compression most reduced the quality of the resulting model, while pooling reduced the model performance the least. The architecture width parameter was an important factor in reducing the model size, with minimal performance degradation.

Linear regression weight magnitudes for predicting model quality, latency, and size. The weights indicate the expected impact of changing the input hyperparameter. A higher weight magnitude indicates a greater expected impact.

Our work is an important step in bringing the full benefits of speech machine learning research to mobile devices. We also provide our public model, corresponding model card, and evaluation code to help the research community responsibly develop even more applications for on-device speech representation research.

Acknowledgements
We'd like to thank our paper co-authors: Jacob Peplinksi and Shwetak Patel. We'd like to thank Aren Jansen for his technical support on this project, Françoise Beaufays, and Tulsee Doshi for help open sourcing the model, and Google Research, Tokyo for logistical support.

Source: Google AI Blog


Stabilizing Live Speech Translation in Google Translate

The transcription feature in the Google Translate app may be used to create a live, translated transcription for events like meetings and speeches, or simply for a story at the dinner table in a language you don’t understand. In such settings, it is useful for the translated text to be displayed promptly to help keep the reader engaged and in the moment.

However, with early versions of this feature the translated text suffered from multiple real-time revisions, which can be distracting. This was because of the non-monotonic relationship between the source and the translated text, in which words at the end of the source sentence can influence words at the beginning of the translation.

Transcribe (old) — Left: Source transcript as it arrives from speech recognition. Right: Translation that is displayed to the user. The frequent corrections made to the translation interfere with the reading experience.

Today, we are excited to describe some of the technology behind a recently released update to the transcribe feature in the Google Translate app that significantly reduces translation revisions and improves the user experience. The research enabling this is presented in two papers. The first formulates an evaluation framework tailored to live translation and develops methods to reduce instability. The second demonstrates that these methods do very well compared to alternatives, while still retaining the simplicity of the original approach. The resulting model is much more stable and provides a noticeably improved reading experience within Google Translate.

Transcribe (new) — Left: Source transcript as it arrives from speech recognition. Right: Translation that is displayed to the user. At the cost of a small delay, the translation now rarely needs to be corrected.

Evaluating Live Translation
Before attempting to make any improvements, it was important to first understand and quantifiably measure the different aspects of the user experience, with the goal of maximizing quality while minimizing latency and instability. In “Re-translation Strategies For Long Form, Simultaneous, Spoken Language Translation”, we developed an evaluation framework for live-translation that has since guided our research and engineering efforts. This work presents a performance measure using the following metrics:

  • Erasure: Measures the additional reading burden on the user due to instability. It is the number of words that are erased and replaced for every word in the final translation.
  • Lag: Measures the average time that has passed between when a user utters a word and when the word’s translation displayed on the screen becomes stable. Requiring stability avoids rewarding systems that can only manage to be fast due to frequent corrections.
  • BLEU score: Measures the quality of the final translation. Quality differences in intermediate translations are captured by a combination of all metrics.

It is important to recognize the inherent trade-offs between these different aspects of quality. Transcribe enables live-translation by stacking machine translation on top of real-time automatic speech recognition. For each update to the recognized transcript, a fresh translation is generated in real time; several updates can occur each second. This approach placed Transcribe at one extreme of the 3 dimensional quality framework: it exhibited minimal lag and the best quality, but also had high erasure. Understanding this allowed us to work towards finding a better balance.

Stabilizing Re-translation
One straightforward solution to reduce erasure is to decrease the frequency with which translations are updated. Along this line, “streaming translation” models (for example, STACL and MILk) intelligently learn to recognize when sufficient source information has been received to extend the translation safely, so the translation never needs to be changed. In doing so, streaming translation models are able to achieve zero erasure.

The downside with such streaming translation models is that they once again take an extreme position: zero erasure necessitates sacrificing BLEU and lag. Rather than eliminating erasure altogether, a small budget for occasional instability may allow better BLEU and lag. More importantly, streaming translation would require retraining and maintenance of specialized models specifically for live-translation. This precludes the use of streaming translation in some cases, because keeping a lean pipeline is an important consideration for a product like Google Translate that supports 100+ languages.

In our second paper, “Re-translation versus Streaming for Simultaneous Translation”, we show that our original “re-translation” approach to live-translation can be fine-tuned to reduce erasure and achieve a more favorable erasure/lag/BLEU trade-off. Without training any specialized models, we applied a pair of inference-time heuristics to the original machine translation models — masking and biasing.

The end of an on-going translation tends to flicker because it is more likely to have dependencies on source words that have yet to arrive. We reduce this by truncating some number of words from the translation until the end of the source sentence has been observed. This masking process thus trades latency for stability, without affecting quality. This is very similar to delay-based strategies used in streaming methods such as Wait-k, but applied only during inference and not during training.

Neural machine translation often “see-saws” between equally good translations, causing unnecessary erasure. We improve stability by biasing the output towards what we have already shown the user. On top of reducing erasure, biasing also tends to reduce lag by stabilizing translations earlier. Biasing interacts nicely with masking, as masking words that are likely to be unstable also prevents the model from biasing toward them. However, this process does need to be tuned carefully, as a high bias, along with insufficient masking, may have a negative impact on quality.

The combination of masking and biasing, produces a re-translation system with high quality and low latency, while virtually eliminating erasure. The table below shows how the metrics react to the heuristics we introduced and how they compare to the other systems discussed above. The graph demonstrates that even with a very small erasure budget, re-translation surpasses zero-flicker streaming translation systems (MILk and Wait-k) trained specifically for live-translation.

System     BLEU     Lag (s)     Erasure
Re-translation (old)     20.4     4.1     2.1
+ Stabilization (new)     20.2     4.1     0.1
Evaluation of re-translation on IWSLT test 2018 Engish-German (TED talks) with and without the inference-time stabilization heuristics of masking and biasing. Stabilization drastically reduces erasure. Translation quality, measured in BLEU, is very slightly impacted due to biasing. Despite masking, the effective lag remains the same because the translation stabilizes sooner.
Comparison of re-translation with stabilization and specialized streaming models (Wait-k and MILk) on WMT 14 English-German. The BLEU-lag trade-off curve for re-translation is obtained via different combinations of bias and masking while maintaining an erasure budget of less than 2 words erased for every 10 generated. Re-translation offers better BLEU / lag trade-offs than streaming models which cannot make corrections and require specialized training for each trade-off point.

Conclusion
The solution outlined above returns a decent translation very quickly, while allowing it to be revised as more of the source sentence is spoken. The simple structure of re-translation enables the application of our best speech and translation models with minimal effort. However, reducing erasure is just one part of the story — we are also looking forward to improving the overall speech translation experience through new technology that can reduce lag when the translation is spoken, or that can enable better transcriptions when multiple people are speaking.

Acknowledgements
Thanks to Te I, Dirk Padfield, Pallavi Baljekar, Goerge Foster, Wolfgang Macherey, John Richardson, Kuang-Che Lee, Byran Lin, Jeff Pittman, Sami Iqram, Mengmeng Niu, Macduff Hughes, Chris Kau, Nathan Bain.

Source: Google AI Blog


Audiovisual Speech Enhancement in YouTube Stories

While tremendous efforts are invested in improving the quality of videos taken with smartphone cameras, the quality of audio in videos is often overlooked. For example, the speech of a subject in a video where there are multiple people speaking or where there is high background noise might be muddled, distorted, or difficult to understand. In an effort to address this, two years ago we introduced Looking to Listen, a machine learning (ML) technology that uses both visual and audio cues to isolate the speech of a video’s subject. By training the model on a large-scale collection of online videos, we are able to capture correlations between speech and visual signals such as mouth movements and facial expressions, which can then be used to separate the speech of one person in a video from another, or to separate speech from background sounds. We showed that this technology not only achieves state-of-the-art results in speech separation and enhancement (a noticeable 1.5dB improvement over audio-only models), but in particular can improve the results over audio-only processing when there are multiple people speaking, as the visual cues in the video help determine who is saying what.

We are now happy to make the Looking to Listen technology available to users through a new audiovisual Speech Enhancement feature in YouTube Stories (on iOS), allowing creators to take better selfie videos by automatically enhancing their voices and reducing background noise. Getting this technology into users’ hands was no easy feat. Over the past year, we worked closely with users to learn how they would like to use such a feature, in what scenarios, and what balance of speech and background sounds they would like to have in their videos. We heavily optimized the Looking to Listen model to make it run efficiently on mobile devices, overall reducing the running time from 10x real-time on a desktop when our paper came out, to 0.5x real-time performance on the phone. We also put the technology through extensive testing to verify that it performs consistently across different recording conditions and for people with different appearances and voices.

From Research to Product
Optimizing Looking to Listen to allow fast and robust operation on mobile devices required us to overcome a number of challenges. First, all processing needed to be done on-device within the client app in order to minimize processing time and to preserve the user’s privacy; no audio or video information would be sent to servers for processing. Further, the model needed to co-exist alongside other ML algorithms used in the YouTube app in addition to the resource-consuming video recording itself. Finally, the algorithm needed to run quickly and efficiently on-device while minimizing battery consumption.

The first step in the Looking to Listen pipeline is to isolate thumbnail images that contain the faces of the speakers from the video stream. By leveraging MediaPipe BlazeFace with GPU accelerated inference, this step is now able to be executed in just a few milliseconds. We then switched the model part that processes each thumbnail separately to a lighter weight MobileNet (v2) architecture, which outputs visual features learned for the purpose of speech enhancement, extracted from the face thumbnails in 10 ms per frame. Because the compute time to embed the visual features is short, it can be done while the video is still being recorded. This avoids the need to keep the frames in memory for further processing, thereby reducing the overall memory footprint. Then, after the video finishes recording, the audio and the computed visual features are streamed to the audio-visual speech separation model which produces the isolated and enhanced speech.

We reduced the total number of parameters in the audio-visual model by replacing “regular” 2D convolutions with separable ones (1D in the frequency dimension, followed by 1D in the time dimension) with fewer filters. We then optimized the model further using TensorFlow Lite — a set of tools that enable running TensorFlow models on mobile devices with low latency and a small binary size. Finally, we reimplemented the model within the Learn2Compress framework in order to take advantage of built-in quantized training and QRNN support.

Our Looking to Listen on-device pipeline for audiovisual speech enhancement

These optimizations and improvements reduced the running time from 10x real-time on a desktop using the original formulation of Looking to Listen, to 0.5x real-time performance using only an iPhone CPU; and brought the model size down from 120MB to 6MB now, which makes it easier to deploy. Since YouTube Stories videos are short — limited to 15 seconds — the result of the video processing is available within a couple of seconds after the recording is finished.

Finally, to avoid processing videos with clean speech (so as to avoid unnecessary computation), we first run our model only on the first two seconds of the video, then compare the speech-enhanced output to the original input audio. If there is sufficient difference (meaning the model cleaned up the speech), then we enhance the speech throughout the rest of the video.

Researching User Needs
Early versions of Looking to Listen were designed to entirely isolate speech from the background noise. In a user study conducted together with YouTube, we found that users prefer to leave in some of the background sounds to give context and to retain some the general ambiance of the scene. Based on this user study, we take a linear combination of the original audio and our produced clean speech channel: output_audio = 0.1 x original_audio + 0.9 x speech. The following video presents clean speech combined with different levels of the background sounds in the scene (10% background is the balance we use in practice).

Below are additional examples of the enhanced speech results from the new Speech Enhancement feature in YouTube Stories. We recommend watching the videos with good speakers or headphones.

Fairness Analysis
Another important requirement is that the model be fair and inclusive. It must be able to handle different types of voices, languages and accents, as well as different visual appearances. To this end, we conducted a series of tests exploring the performance of the model with respect to various visual and speech/auditory attributes: the speaker’s age, skin tone, spoken language, voice pitch, visibility of the speaker’s face (% of video in which the speaker is in frame), head pose throughout the video, facial hair, presence of glasses, and the level of background noise in the (input) video.

For each of the above visual/auditory attributes, we ran our model on segments from our evaluation set (separate from the training set) and measured the speech enhancement accuracy, broken down according to the different attribute values. Results for some of the attributes are summarized in the following plots. Each data point in the plots represents hundreds (in most cases thousands) of videos fitting the criteria.

Speech enhancement quality (signal-to-distortion ratio, SDR, in dB) for different spoken languages, sorted alphabetically. The average SDR was 7.89 dB with a standard deviation of 0.42 dB — deviation that for human listeners is considered hard to notice.
Left: Speech enhancement quality as a function of the speaker’s voice pitch. The fundamental voice frequency (pitch) of an adult male typically ranges from 85 to 180 Hz, and that of an adult female ranges from 165 to 255 Hz. Right: speech enhancement quality as a function of the speaker’s predicted age.
As our method utilizes facial cues and mouth movements to isolate the speech, we tested whether facial hair (e.g., a moustache, beard) may obstruct those visual cues and affect the method’s performance. Our evaluations show that the quality of speech enhancement is maintained well also in the presence of facial hair.

Using the Feature
YouTube creators who are eligible for YouTube Stories creation may record a video on iOS, and select “Enhance speech” from the volume controls editing tool. This will immediately apply speech enhancement to the audio track and will play back the enhanced speech in a loop. It is then possible to toggle the feature on and off multiple times to compare the enhanced speech with the original audio.

In parallel to this new feature in YouTube, we are also exploring additional venues for this technology. More to come later this year — stay tuned!

Acknowledgements
This feature is a collaboration across multiple teams at Google. Key contributors include: from Research-IL: Oran Lang; from VisCAM: Ariel Ephrat, Mike Krainin, JD Velasquez, Inbar Mosseri, Michael Rubinstein; from Learn2Compress: Arun Kandoor; from MediaPipe: Buck Bourdon, Matsvei Zhdanovich, Matthias Grundmann; from YouTube: Andy Poes, Vadim Lavrusik, Aaron La Lau, Willi Geiger, Simona De Rosa, and Tomer Margolin.

Source: Google AI Blog