Tag Archives: speech

Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model



Google's mission is not just to organize the world's information but to make it universally accessible, which means ensuring that our products work in as many of the world's languages as possible. When it comes to understanding human speech, which is a core capability of the Google Assistant, extending to more languages poses a challenge: high-quality automatic speech recognition (ASR) systems require large amounts of audio and text data — even more so as data-hungry neural models continue to revolutionize the field. Yet many languages have little data available.

We wondered how we could keep the quality of speech recognition high for speakers of data-scarce languages. A key insight from the research community was that much of the "knowledge" a neural network learns from audio data of a data-rich language is re-usable by data-scarce languages; we don't need to learn everything from scratch. This led us to study multilingual speech recognition, in which a single model learns to transcribe multiple languages.

In “Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model”, published at Interspeech 2019, we present an end-to-end (E2E) system trained as a single model, which allows for real-time multilingual speech recognition. Using nine Indian languages, we demonstrated a dramatic improvement in the ASR quality on several data-scarce languages, while still improving performance for the data-rich languages.

India: A Land of Languages
For this study, we focused on India, an inherently multilingual society where there are more than thirty languages with at least a million native speakers. Many of these languages overlap in acoustic and lexical content due to the geographic proximity of the native speakers and shared cultural history. Additionally, many Indians are bilingual or trilingual, making the use of multiple languages within a conversation a common phenomenon, and a natural case for training a single multilingual model. In this work, we combined nine primary Indian languages, namely Hindi, Marathi, Urdu, Bengali, Tamil, Telugu, Kannada, Malayalam and Gujarati.

A Low-latency All-neural Multilingual Model
Traditional ASR systems contain separate components for acoustic, pronunciation, and language models. While there have been attempts to make some or all of the traditional ASR components multilingual [1,2,3,4], this approach can be complex and difficult to scale. E2E ASR models combine all three components into a single neural network and promise scalability and ease of parameter sharing. Recent works have extended E2E models to be multilingual [1,2], but they did not address the need for real-time speech recognition, a key requirement for applications such as the Assistant, Voice Search and GBoard dictation. For this, we turned to recent research at Google that used a Recurrent Neural Network Transducer (RNN-T) model to achieve streaming E2E ASR. The RNN-T system outputs words one character at a time, just as if someone was typing in real time, however this was not multilingual. We built upon this architecture to develop a low-latency model for multilingual speech recognition.
[Left] A traditional monolingual speech recognizer comprising of Acoustic, Pronunciation and Language Models for each language. [Middle] A traditional multilingual speech recognizer where the Acoustic and Pronunciation model is multilingual, while the Language model is language-specific. [Right] An E2E multilingual speech recognizer where the Acoustic, Pronunciation and Language Model is combined into a single multilingual model.
Large-Scale Data Challenges
Using large-scale, real-world data for training a multilingual model is complicated by data imbalance. Given the steep skew in the distribution of speakers across the languages and speech product maturity, it is not surprising to have varying amounts of transcribed data available per language. As a result, a multilingual model can tend to be more influenced by languages that are over-represented in the training set. This bias is more prominent in an E2E model, which unlike a traditional ASR system, does not have access to additional in-language text data and learns lexical characteristics of the languages solely from the audio training data.
Histogram of training data for the nine languages showing the steep skew in the data available.
We addressed this issue with a few architectural modifications. First, we provided an extra language identifier input, which is an external signal derived from the language locale of the training data; i.e. the language preference set in an individual’s phone. This signal is combined with the audio input as a one-hot feature vector. We hypothesize that the model is able to use the language vector not only to disambiguate the language but also to learn separate features for separate languages, as needed, which helped with data imbalance.

Building on the idea of language-specific representations within the global model, we further augmented the network architecture by allocating extra parameters per language in the form of residual adapter modules. Adapters helped fine-tune a global model on each language while maintaining parameter efficiency of a single global model, and in turn, improved performance.
[Left] Multilingual RNN-T architecture with a language identifier. [Middle] Residual adapters inside the encoder. For a Tamil utterance, only the Tamil adapters are applied to each activation. [Right] Architecture details of the Residual Adapter modules. For more details please see our paper.
Putting all of these elements together, our multilingual model outperforms all the single-language recognizers, with especially large improvements in data-scarce languages like Kannada and Urdu. Moreover, since it is a streaming E2E model, it simplifies training and serving, and is also usable in low-latency applications like the Assistant. Building on this result, we hope to continue our research on multilingual ASRs for other language groups, to better assist our growing body of diverse users.

Acknowledgements
We would like to thank the following for their contribution to this research: Tara N. Sainath, Eugene Weinstein, Bo Li, Shubham Toshniwal, Ron Weiss, Bhuvana Ramabhadran, Yonghui Wu, Ankur Bapna, Zhifeng Chen, Seungji Lee, Meysam Bastani, Mikaela Grace, Pedro Moreno, Yanzhang (Ryan) He, Khe Chai Sim.

Source: Google AI Blog


Assessing the Quality of Long-Form Synthesized Speech



Automatically generated speech is everywhere, from directions being read out aloud while you are driving, to virtual assistants on your phone or smart speaker devices at home. While much research is being done to try to make synthesized speech sound as natural as possible—such as generating speech for low-resource languages and creating human-like speech with Tacotron 2—how does one evaluate the generated speech? The best way to find out is to ask people, who are very good at telling if something sounds natural or not.

In the field of speech synthesis, subjects are routinely asked to listen to samples of synthesized speech and rate their quality. Yet, until now, evaluation of synthesized speech has been done on a sentence-by-sentence basis. But often one wants to know the quality of a series of sentences that belong together, such as a paragraph in a news article or a turn in a conversation. This is where it gets interesting, as there is more than one way of evaluating sentences that naturally occur in a sequence, and, surprisingly, a rigorous comparison of these different methods has not been carried out. This in turn can hinder research progress in developing products that rely on generated speech.

To address this challenge, we present “Evaluating Long-form Text-to-Speech: Comparing the Ratings of Sentences and Paragraphs”, a publication to appear at SSW10 in which we compare several ways of evaluating synthesized speech for multi-line texts. We find that when a sentence is evaluated as part of a longer text involving several sentences, the outcome is influenced by the way in which the audio sample is presented to the people evaluating it. For example, when the sentence is presented by itself, without any context, the rating people give on average is substantially different from the rating they give when they listen to the same sentence with some context (while the context doesn't have to be rated).

Evaluating Automatically Generated Speech
To determine the quality of speech signals, it is common practice to ask several human raters to give their opinion for a particular sample, on a 1-to-5 scale. This sample can be automatically generated, but it can also be natural speech (i.e., an actual person saying a sentence out loud), which serves as a control. The scores of all reviewers rating a particular speech sample are averaged to get a Mean Opinion Score (MOS).

Until now, MOS ratings were typically collected per sentence, i.e., raters listened to sentences in isolation to form their opinion. Instead of this typical approach, we consider three different ways of presenting speech samples to raters—both with and without context—and we show that each approach yields different results. The first, presenting the sentence in isolation, is the default method commonly used in the field. An alternative method is to provide the full context for the sentence. In this case, the entire paragraph to which the sentence belongs is included and the ensemble is rated. The final approach is to provide a context-stimulus pair. Here, rather than providing full context, only some context is provided, such as the preceding sentence(s) from the original paragraph.

Interestingly, these three different approaches for presenting speech give different results even when applied to natural speech. This is demonstrated in the figure below, where the MOS scores are presented for natural speech samples rated using the three different methods of presentation. Even though the sentences being rated are identical across the three different settings, the scores are different on average, depending on the context in which they were presented.
MOS results for natural speech from a dataset consisting of news articles. Though the differences appear small, they are significant between all conditions (two-tailed t-test with α=0.05).
Examination of the figure above reveals that raters rarely give top scores (a five) even to recorded human speech, which may be surprising. However, this is a typical result seen in sentence evaluation studies and probably has to do with a more generic pattern of behavior, that people tend to avoid using the extreme ends of a scale, regardless of the task or setting.

When evaluated synthesized speech, the differences are more pronounced.
MOS results for synthesized speech on the same news article dataset used above. All lines are synthesized speech, unless indicated otherwise.
To see if the way context is presented makes a difference, we tried several different ways of providing it: one or two sentences leading up to the sentence to be evaluated, provided as generated speech or real speech. When context is added, the scores get higher (the four blue bars on the left) except when the context presented is real speech, in which case the score drops (the rightmost blue bar). Our hypothesis is that this has to do with an anchoring effect—if the context is very good (real speech) the synthesized speech, in comparison, is perceived as less natural.

Predicting Paragraph Score
When an entire paragraph of synthesized speech is played (the yellow bar), this is perceived as even less natural than in the other settings. Our original hypothesis was a weakest-link argument—the rating is probably as bad as the worst sentence in the paragraph. If that were the case, it should be easy to predict the rating of a paragraph by considering the ratings of the individual sentences in it, perhaps simply taking the minimum value to get the paragraph rating. It turns out, however, that does not work.

The failure of the weakest-link hypothesis may be due to more subtle factors that are difficult to tease out with such a simple approach. To test this, we also trained a machine learning algorithm to predict the paragraph score from the individual sentences. However, this approach, too, was unable to successfully predict paragraph scores reliably.

Conclusion
Evaluating synthesized speech is not straightforward when multiple sentences are involved. The traditional paradigm of rating sentences in isolation does not give the full picture, and one should be aware of anchoring effects when context is provided. Rating full paragraphs might be the most conservative approach. We hope our findings help advance future work in speech synthesis where long-form content is concerned, such as audio book readers and conversational agents.

Acknowledgments
Many thanks to all authors of the paper: Rob Clark, Hanna Silen, Ralph Leith.

Source: Google AI Blog


Assessing the Quality of Long-Form Synthesized Speech



Automatically generated speech is everywhere, from directions being read out aloud while you are driving, to virtual assistants on your phone or smart speaker devices at home. While much research is being done to try to make synthesized speech sound as natural as possible—such as generating speech for low-resource languages and creating human-like speech with Tacotron 2—how does one evaluate the generated speech? The best way to find out is to ask people, who are very good at telling if something sounds natural or not.

In the field of speech synthesis, subjects are routinely asked to listen to samples of synthesized speech and rate their quality. Yet, until now, evaluation of synthesized speech has been done on a sentence-by-sentence basis. But often one wants to know the quality of a series of sentences that belong together, such as a paragraph in a news article or a turn in a conversation. This is where it gets interesting, as there is more than one way of evaluating sentences that naturally occur in a sequence, and, surprisingly, a rigorous comparison of these different methods has not been carried out. This in turn can hinder research progress in developing products that rely on generated speech.

To address this challenge, we present “Evaluating Long-form Text-to-Speech: Comparing the Ratings of Sentences and Paragraphs”, a publication to appear at SSW10 in which we compare several ways of evaluating synthesized speech for multi-line texts. We find that when a sentence is evaluated as part of a longer text involving several sentences, the outcome is influenced by the way in which the audio sample is presented to the people evaluating it. For example, when the sentence is presented by itself, without any context, the rating people give on average is substantially different from the rating they give when they listen to the same sentence with some context (while the context doesn't have to be rated).

Evaluating Automatically Generated Speech
To determine the quality of speech signals, it is common practice to ask several human raters to give their opinion for a particular sample, on a 1-to-5 scale. This sample can be automatically generated, but it can also be natural speech (i.e., an actual person saying a sentence out loud), which serves as a control. The scores of all reviewers rating a particular speech sample are averaged to get a Mean Opinion Score (MOS).

Until now, MOS ratings were typically collected per sentence, i.e., raters listened to sentences in isolation to form their opinion. Instead of this typical approach, we consider three different ways of presenting speech samples to raters—both with and without context—and we show that each approach yields different results. The first, presenting the sentence in isolation, is the default method commonly used in the field. An alternative method is to provide the full context for the sentence. In this case, the entire paragraph to which the sentence belongs is included and the ensemble is rated. The final approach is to provide a context-stimulus pair. Here, rather than providing full context, only some context is provided, such as the preceding sentence(s) from the original paragraph.

Interestingly, these three different approaches for presenting speech give different results even when applied to natural speech. This is demonstrated in the figure below, where the MOS scores are presented for natural speech samples rated using the three different methods of presentation. Even though the sentences being rated are identical across the three different settings, the scores are different on average, depending on the context in which they were presented.
MOS results for natural speech from a dataset consisting of news articles. Though the differences appear small, they are significant between all conditions (two-tailed t-test with α=0.05).
Examination of the figure above reveals that raters rarely give top scores (a five) even to recorded human speech, which may be surprising. However, this is a typical result seen in sentence evaluation studies and probably has to do with a more generic pattern of behavior, that people tend to avoid using the extreme ends of a scale, regardless of the task or setting.

When evaluated synthesized speech, the differences are more pronounced.
MOS results for synthesized speech on the same news article dataset used above. All lines are synthesized speech, unless indicated otherwise.
To see if the way context is presented makes a difference, we tried several different ways of providing it: one or two sentences leading up to the sentence to be evaluated, provided as generated speech or real speech. When context is added, the scores get higher (the four blue bars on the left) except when the context presented is real speech, in which case the score drops (the rightmost blue bar). Our hypothesis is that this has to do with an anchoring effect—if the context is very good (real speech) the synthesized speech, in comparison, is perceived as less natural.

Predicting Paragraph Score
When an entire paragraph of synthesized speech is played (the yellow bar), this is perceived as even less natural than in the other settings. Our original hypothesis was a weakest-link argument—the rating is probably as bad as the worst sentence in the paragraph. If that were the case, it should be easy to predict the rating of a paragraph by considering the ratings of the individual sentences in it, perhaps simply taking the minimum value to get the paragraph rating. It turns out, however, that does not work.

The failure of the weakest-link hypothesis may be due to more subtle factors that are difficult to tease out with such a simple approach. To test this, we also trained a machine learning algorithm to predict the paragraph score from the individual sentences. However, this approach, too, was unable to successfully predict paragraph scores reliably.

Conclusion
Evaluating synthesized speech is not straightforward when multiple sentences are involved. The traditional paradigm of rating sentences in isolation does not give the full picture, and one should be aware of anchoring effects when context is provided. Rating full paragraphs might be the most conservative approach. We hope our findings help advance future work in speech synthesis where long-form content is concerned, such as audio book readers and conversational agents.

Acknowledgments
Many thanks to all authors of the paper: Rob Clark, Hanna Silen, Ralph Leith.

Source: Google AI Blog


Introducing Translatotron: An End-to-End Speech-to-Speech Translation Model



Speech-to-speech translation systems have been developed over the past several decades with the goal of helping people who speak different languages to communicate with each other. Such systems have usually been broken into three separate components: automatic speech recognition to transcribe the source speech as text, machine translation to translate the transcribed text into the target language, and text-to-speech synthesis (TTS) to generate speech in the target language from the translated text. Dividing the task into such a cascade of systems has been very successful, powering many commercial speech-to-speech translation products, including Google Translate.

In “Direct speech-to-speech translation with a sequence-to-sequence model”, we propose an experimental new system that is based on a single attentive sequence-to-sequence model for direct speech-to-speech translation without relying on intermediate text representation. Dubbed Translatotron, this system avoids dividing the task into separate stages, providing a few advantages over cascaded systems, including faster inference speed, naturally avoiding compounding errors between recognition and translation, making it straightforward to retain the voice of the original speaker after translation, and better handling of words that do not need to be translated (e.g., names and proper nouns).

Translatotron
The emergence of end-to-end models on speech translation started in 2016, when researchers demonstrated the feasibility of using a single sequence-to-sequence model for speech-to-text translation. In 2017, we demonstrated that such end-to-end models can outperform cascade models. Many approaches to further improve end-to-end speech-to-text translation models have been proposed recently, including our effort on leveraging weakly supervised data. Translatotron goes a step further by demonstrating that a single sequence-to-sequence model can directly translate speech from one language into speech in another language, without relying on an intermediate text representation in either language, as is required in cascaded systems.

Translatotron is based on a sequence-to-sequence network which takes source spectrograms as input and generates spectrograms of the translated content in the target language. It also makes use of two other separately trained components: a neural vocoder that converts output spectrograms to time-domain waveforms, and, optionally, a speaker encoder that can be used to maintain the character of the source speaker’s voice in the synthesized translated speech. During training, the sequence-to-sequence model uses a multitask objective to predict source and target transcripts at the same time as generating target spectrograms. However, no transcripts or other intermediate text representations are used during inference.

Model architecture of Translatotron.
Performance
We validated Translatotron’s translation quality by measuring the BLEU score, computed with text transcribed by a speech recognition system. Though our results lag behind a conventional cascade system, we have demonstrated the feasibility of the end-to-end direct speech-to-speech translation.

Compared in the audio clips below are the direct speech-to-speech translation output from Translatotron to that of the baseline cascade method. In this case, both systems provide a suitable translation and speak naturally using the same canonical voice.


Input (Spanish)
Reference translation (English)
Baseline cascade translation
Translatotron translation

You can listen to more audio samples here.

Preserving Vocal Characteristics
By incorporating a speaker encoder network, Translatotron is also able to retain the original speaker’s vocal characteristics in the translated speech, which makes the translated speech sound more natural and less jarring. This feature leverages previous Google research on speaker verification and speaker adaptation for TTS. The speaker encoder is pretrained on the speaker verification task, learning to encode speaker characteristics from a short example utterance. Conditioning the spectrogram decoder on this encoding makes it possible to synthesize speech with similar speaker characteristics, even though the content is in a different language.

The audio clips below demonstrate the performance of Translatotron when transferring the original speaker’s voice to the translated speech. In this example, Translatotron gives more accurate translation than the baseline cascade model, while being able to retain the original speaker’s vocal characteristics. The Translatotron output that retains the original speaker’s voice is trained with less data than the one using the canonical voice, so that they yield slightly different translations.

Input (Spanish)
Reference translation (English)
Baseline cascade translation
Translatotron translation (canonical voice)
Translatotron translation (original speaker’s voice)

More audio samples are available here.

Conclusion
To the best of our knowledge, Translatotron is the first end-to-end model that can directly translate speech from one language into speech in another language. It is also able to retain the source speaker’s voice in the translated speech. We hope that this work can serve as a starting point for future research on end-to-end speech-to-speech translation systems.

Acknowledgments
This research was a joint work between the Google Brain, Google Translate, and Google Speech teams. Contributors include Ye Jia, Ron J. Weiss, Fadi Biadsy, Wolfgang Macherey, Melvin Johnson, Zhifeng Chen, Mengmeng Niu, Quan Wang, Jason Pelecanos, Ignacio Lopez Moreno, Tom Walters, Heiga Zen, Patrick Nguyen, Yu Zhang, Jonathan Shen, Orhan Firat, and Yonghui Wu. We also thank Jorge Pereira and Stella Laurenzo for verifying the quality of the translation from Translatotron.

Source: Google AI Blog


Accurate Online Speaker Diarization with Supervised Learning



Speaker diarization, the process of partitioning an audio stream with multiple people into homogeneous segments associated with each individual, is an important part of speech recognition systems. By solving the problem of “who spoke when”, speaker diarization has applications in many important scenarios, such as understanding medical conversations, video captioning and more. However, training these systems with supervised learning methods is challenging — unlike standard supervised classification tasks, a robust diarization model requires the ability to associate new individuals with distinct speech segments that weren't involved in training. Importantly, this limits the quality of both online and offline diarization systems. Online systems usually suffer more, since they require diarization results in real time.
Online speaker diarization on streaming audio input. Different colors in the bottom axis indicate different speakers.
In “Fully Supervised Speaker Diarization”, we describe a new model that seeks to make use of supervised speaker labels in a more effective manner. Here “fully” implies that all components in the speaker diarization system, including the estimation of the number of speakers, are trained in supervised ways, so that they can benefit from increasing the amount of labeled data available. On the NIST SRE 2000 CALLHOME benchmark, our diarization error rate (DER) is as low as 7.6%, compared to 8.8% DER from our previous clustering-based method, and 9.9% from deep neural network embedding methods. Moreover, our method achieves this lower error rate based on online decoding, making it specifically suitable for real-time applications. As such we are open sourcing the core algorithms in our paper to accelerate more research along this direction.

Clustering versus Interleaved-state RNN
Modern speaker diarization systems are usually based on clustering algorithms such as k-means or spectral clustering. Since these clustering methods are unsupervised, they could not make good use of the supervised speaker labels available in data. Moreover, online clustering algorithms usually have worse quality in real-time diarization applications with streaming audio inputs. The key difference between our model and common clustering algorithms is that in our method, all speakers’ embeddings are modeled by a parameter-sharing recurrent neural network (RNN), and we distinguish different speakers using different RNN states, interleaved in the time domain.

To understand how this works, consider the example below in which there are four possible speakers: blue, yellow, pink and green (this is arbitrary, and in fact there may be more — our model uses the Chinese restaurant process to accommodate the unknown number of speakers). Each speaker starts with its own RNN instance (with a common initial state shared among all speakers) and keeps updating the RNN state given the new embeddings from this speaker. In the example below, the blue speaker keeps updating its RNN state until a different speaker, yellow, comes in. If blue speaks again later, it resumes updating its RNN state. (This is just one of the possibilities for speech segment y7 in the figure below. If new speaker green enters, it will start with a new RNN instance.)
The generative process of our model. Colors indicate labels for speaker segments.
Representing speakers as RNN states enables us to learn the high-level knowledge shared across different speakers and utterances using RNN parameters, and this promises the usefulness of more labeled data. In contrast, common clustering algorithms almost always work with each single utterance independently, making it difficult to benefit from a large amount of labeled data.

The upshot of all this is that given time-stamped speaker labels (i.e. we know who spoke when), we can train the model with standard stochastic gradient descent algorithms. A trained model can be used for speaker diarization on new utterances from unheard speakers. Furthermore, the use of online decoding makes it more suitable for latency-sensitive applications.

Future Work
Although we've already achieved impressive diarization performance with this system, there are still many exciting directions we are currently exploring. First, we are refining our model so it can easily integrate contextual information to perform offline decoding. This will likely further reduce the DER, which is more useful for latency-insensitive applications. Second, we would like to model acoustic features directly instead of using d-vectors. In this way, the entire speaker diarization system can be trained in an end-to-end way.

To learn more about this work, please see our paper. To download the core algorithm of this system, please visit the Github page.

Acknowledgments
This work was done as a close collaboration between Google AI and Speech & Assistant teams. Contributors include Aonan Zhang (intern), Quan Wang, Zhengyao Zhu and Chong Wang.

Source: Google AI Blog


Text-to-Speech for Low-Resource Languages (Episode 4): One Down, 299 to Go



This is the fourth episode in the series of posts reporting on the work we are doing to build text-to-speech (TTS) systems for low resource languages. In the first episode, we described the crowdsourced acoustic data collection effort for Project Unison. In the second episode, we described how we built parametric voices based on that data. In the third episode, we described the compilation of a pronunciation lexicon for a TTS system. In this episode, we describe how to make a single TTS system speak many languages.

Developing TTS systems for any given language is a significant challenge, and requires large amounts of high quality acoustic recordings and linguistic annotations. Because of this, these systems are only available for a tiny fraction of the world's languages. A natural question that arises in this situation is, instead of attempting to build a high quality voice for a single language using monolingual data from multiple speakers, as we described in the previous three episodes, can we somehow combine the limited monolingual data from multiple speakers of multiple languages to build a single multilingual voice that can speak any language?

Building upon an initial investigation into creating a multilingual TTS system that can synthesize speech in multiple languages from a single model, we developed a new model that uses uniform phonological representation for all languages — the International Phonetic Alphabet (IPA). The model trained using this representation can synthesize both the languages seen in the training data as well as languages not observed in training. This has two main benefits: First, pooling training data from related languages increases phonemic coverage which results in improved synthesis quality of the languages observed in training. Finally, because the model contains many languages pooled together, there is a better chance that an “unseen” language will have a “related” language present in the model that will guide and aid the synthesis.

Exploring the Closely Related Languages of Indonesia
We applied this multilingual approach first to languages of Indonesia, where Standard Indonesian is the official national language, and is spoken natively or as a second language by more than 200 million people. Javanese, with roughly 90 million native speakers, and Sundanese, with approximately 40 million native speakers, constitute the two largest regional languages of Indonesia. Unlike Indonesian, which received a lot of attention by the computational linguists and speech scientists over the years, both Javanese and Sundanese are currently low-resourced due to the lack of openly available high-quality corpora. We collaborated with universities in Indonesia to collect crowd-sourced Javanese and Sundanese recordings.

Since our corpus of Standard Indonesian was much larger and recorded in a professional studio, our hypothesis was that combining three languages may result in significant improvements over the systems constructed using a “classical” monolingual approach. To test this, we first proceeded to analyze the similarities and crucial differences between the phonologies of these three languages (shown below) and used this information to design the phonological representation that allows maximum degree of sharing between the languages while preserving their crucial differences.
Joint phoneme inventory of Indonesian, Javanese, and Sundanese in International Phonetic Alphabet notation.
The resulting Javanese and Sundanese voices trained jointly with Standard Indonesian strongly outperformed our corresponding monolingual multispeaker voices that we used as a baseline. This allowed us to launch Javanese and Sundanese TTS in Google products, such as Google Translate and Android.

Expanding to the More Diverse Language Families of South Asia
Next, we focused on the languages of South Asia spanning two very different language families: Indo-Aryan and Dravidian. Unlike the languages of Indonesia described above, these languages are much more diverse. In particular, they have significantly smaller overlap in their phonologies. The table below shows a superset of the languages in our experiment, including the variety of orthographies used, as well as modern words related to the Sanskrit word for “culture”. These languages show considerable variation within each group, but also such similarities across groups.
Descendants of Sanskrit word for “culture” across languages.
In this work, we leveraged the unified phonological representation mentioned above to make the most of the data we have and eliminate scarcity of data for certain phonemes. This was accomplished by conflating similar phonemes into a single representative phoneme in the multilingual phoneme inventory. Where possible, we use the same inventory for phonologically close languages. For example we have an identical phoneme inventory for Telugu and Kannada, and another one for West Bengali and Odia. For other language pairs like Gujarati and Marathi, we copied over the inventory of one language to another, but made a few changes to reflect the differences in their phonemic inventories. For all languages in these experiments we retained a common underlying representation, mapping similar phonemes across different inventories, so that we could still use the data from one language in training the others.

In addition, we made sure our representation is driven by the phonology in use, rather than the orthography. For example, although there are distinct letters for long and short vowels in Marathi, they are not contrastive in a linguistic sense, so we used a single representation for them, increasing the robustness of our training data. Similarly, if two languages use one character that was historically related to the same Sanskrit letter to represent different sounds or different letters for a similar sound, our mapping reflected the phonological closeness rather than the historical or orthographic representation. Describing all the features of the unified phoneme inventory is outside the scope of this post, the details can be found in our recent paper.
Diagram illustrating our multilingual text-to-speech approach. The input text queries are processed by language-specific linguistic front-ends to generate pronunciations in a shared phonemic representation serving as input to the language-agnostic acoustic model. The model then generates audio for the respective queries.
Our experiments focused on Indian Bengali, Gujarati, Kannada, Malayalam, Marathi, Tamil, Telugu and Urdu. For most of these languages, apart from Bengali and Marathi, the recording data and the transcriptions were crowd-sourced. For each of these languages we constructed a multilingual acoustic model that used all the data available. In addition, the acoustic model included the previously crowd-sourced Nepali and Sinhala data, as well as Hindi and Bangladeshi Bengali.

The results were encouraging: for most of the languages, the multilingual voices outperformed the voices that were constructed using traditional monolingual approach. We performed a further experiment with the Odia language, for which we had no training data, by attempting to synthesize it using the South Asian multilingual model. Subjective listening tests revealed that the native speakers of Odia judged the resulting audio to be acceptable and intelligible. The resulting voices for Marathi, Tamil, Telugu and Malayalam built using our multilingual approach in collaboration with the Speech team were announced at the recent “Google for India” event and are now powering Google Translate as well as other Google products.

Using crowd-sourcing in data collections was interesting from a research point of view and rewarding in terms of establishing fruitful collaborations with the native speaker communities. Our experiments with the Malayo-Polynesian, Indo-Aryan and Dravidian language families have shown that in most instances carefully sharing the data across multiple languages in a single multilingual acoustic model using deep learning techniques alleviates some of the severe data scarcity issues plaguing the low-resource languages and results in good quality voices used in Google products.

This TTS research is a first step towards applying speech and language technology to more of the world’s many languages, and it is our hope is that others will join us in this effort. To contribute to the research community we have open sourced corpora for Nepali, Sinhala, Bengali, Khmer, Javanese and Sundanese as we return from SLTU and Interspeech conferences, where we have been discussing this work with other researchers. We are planning on continuing to release additional datasets for other languages in our projects in the future.

Source: Google AI Blog


Looking to Listen: Audio-Visual Speech Separation



People are remarkably good at focusing their attention on a particular person in a noisy environment, mentally “muting” all other voices and sounds. Known as the cocktail party effect, this capability comes natural to us humans. However, automatic speech separation — separating an audio signal into its individual speech sources — while a well-studied problem, remains a significant challenge for computers.

In “Looking to Listen at the Cocktail Party”, we present a deep learning audio-visual model for isolating a single speech signal from a mixture of sounds such as other voices and background noise. In this work, we are able to computationally produce videos in which speech of specific people is enhanced while all other sounds are suppressed. Our method works on ordinary videos with a single audio track, and all that is required from the user is to select the face of the person in the video they want to hear, or to have such a person be selected algorithmically based on context. We believe this capability can have a wide range of applications, from speech enhancement and recognition in videos, through video conferencing, to improved hearing aids, especially in situations where there are multiple people speaking.
A unique aspect of our technique is in combining both the auditory and visual signals of an input video to separate the speech. Intuitively, movements of a person’s mouth, for example, should correlate with the sounds produced as that person is speaking, which in turn can help identify which parts of the audio correspond to that person. The visual signal not only improves the speech separation quality significantly in cases of mixed speech (compared to speech separation using audio alone, as we demonstrate in our paper), but, importantly, it also associates the separated, clean speech tracks with the visible speakers in the video.
The input to our method is a video with one or more people speaking, where the speech of interest is interfered by other speakers and/or background noise. The output is a decomposition of the input audio track into clean speech tracks, one for each person detected in the video.
An Audio-Visual Speech Separation Model
To generate training examples, we started by gathering a large collection of 100,000 high-quality videos of lectures and talks from YouTube. From these videos, we extracted segments with a clean speech (e.g. no mixed music, audience sounds or other speakers) and with a single speaker visible in the video frames. This resulted in roughly 2000 hours of video clips, each of a single person visible to the camera and talking with no background interference. We then used this clean data to generate “synthetic cocktail parties” -- mixtures of face videos and their corresponding speech from separate video sources, along with non-speech background noise we obtained from AudioSet.

Using this data, we were able to train a multi-stream convolutional neural network-based model to split the synthetic cocktail mixture into separate audio streams for each speaker in the video. The input to the network are visual features extracted from the face thumbnails of detected speakers in each frame, and a spectrogram representation of the video’s soundtrack. During training, the network learns (separate) encodings for the visual and auditory signals, then it fuses them together to form a joint audio-visual representation. With that joint representation, the network learns to output a time-frequency mask for each speaker. The output masks are multiplied by the noisy input spectrogram and converted back to a time-domain waveform to obtain an isolated, clean speech signal for each speaker. For full details, see our paper.
Our multi-stream, neural network-based model architecture.
Here are some more speech separation and enhancement results by our method. Sound by others than the selected speakers can be entirely suppressed or suppressed to the desired level.
To highlight the utilization of visual information by our model, we took two different parts from the same video of Google’s CEO, Sundar Pichai, and placed them side by side. It is very difficult to perform speech separation in this scenario using only characteristic speech frequencies contained in the audio, however our audio-visual model manages to properly separate the speech even in this challenging case.
Application to Speech Recognition
Our method can also potentially be used as a pre-process for speech recognition and automatic video captioning. Handling overlapping speakers is a known challenge for automatic captioning systems, and separating the audio to the different sources could help in presenting more accurate and easy-to-read captions.
You can similarly see and compare the captions before and after speech separation in all the other videos in this post and on our website, by turning on closed captions in the YouTube player when playing the videos (“cc” button at the lower right corner of the player).

On our project web page you can find more results, as well as comparisons with state-of-the-art audio-only speech separation and with other recent audio-visual speech separation work.
We envision a wide range of applications for this technology. We are currently exploring opportunities for incorporating it into various Google products. Stay tuned!

Acknowledgements
The research described in this post was done by Ariel Ephrat (as an intern), Inbar Mosseri, Oran Lang, Tali Dekel, Kevin Wilson, Avinatan Hassidim, Bill Freeman and Michael Rubinstein. We would like to thank Yossi Matias and Google Research Israel for their support for the project, and John Hershey for his valuable feedback. We also thank Arkady Ziefman for his help with animations and figures, and Rachel Soh for helping us procure permissions for video content in our results.

Looking to Listen: Audio-Visual Speech Separation



People are remarkably good at focusing their attention on a particular person in a noisy environment, mentally “muting” all other voices and sounds. Known as the cocktail party effect, this capability comes natural to us humans. However, automatic speech separation — separating an audio signal into its individual speech sources — while a well-studied problem, remains a significant challenge for computers.

In “Looking to Listen at the Cocktail Party”, we present a deep learning audio-visual model for isolating a single speech signal from a mixture of sounds such as other voices and background noise. In this work, we are able to computationally produce videos in which speech of specific people is enhanced while all other sounds are suppressed. Our method works on ordinary videos with a single audio track, and all that is required from the user is to select the face of the person in the video they want to hear, or to have such a person be selected algorithmically based on context. We believe this capability can have a wide range of applications, from speech enhancement and recognition in videos, through video conferencing, to improved hearing aids, especially in situations where there are multiple people speaking.
A unique aspect of our technique is in combining both the auditory and visual signals of an input video to separate the speech. Intuitively, movements of a person’s mouth, for example, should correlate with the sounds produced as that person is speaking, which in turn can help identify which parts of the audio correspond to that person. The visual signal not only improves the speech separation quality significantly in cases of mixed speech (compared to speech separation using audio alone, as we demonstrate in our paper), but, importantly, it also associates the separated, clean speech tracks with the visible speakers in the video.
The input to our method is a video with one or more people speaking, where the speech of interest is interfered by other speakers and/or background noise. The output is a decomposition of the input audio track into clean speech tracks, one for each person detected in the video.
An Audio-Visual Speech Separation Model
To generate training examples, we started by gathering a large collection of 100,000 high-quality videos of lectures and talks from YouTube. From these videos, we extracted segments with a clean speech (e.g. no mixed music, audience sounds or other speakers) and with a single speaker visible in the video frames. This resulted in roughly 2000 hours of video clips, each of a single person visible to the camera and talking with no background interference. We then used this clean data to generate “synthetic cocktail parties” -- mixtures of face videos and their corresponding speech from separate video sources, along with non-speech background noise we obtained from AudioSet.

Using this data, we were able to train a multi-stream convolutional neural network-based model to split the synthetic cocktail mixture into separate audio streams for each speaker in the video. The input to the network are visual features extracted from the face thumbnails of detected speakers in each frame, and a spectrogram representation of the video’s soundtrack. During training, the network learns (separate) encodings for the visual and auditory signals, then it fuses them together to form a joint audio-visual representation. With that joint representation, the network learns to output a time-frequency mask for each speaker. The output masks are multiplied by the noisy input spectrogram and converted back to a time-domain waveform to obtain an isolated, clean speech signal for each speaker. For full details, see our paper.
Our multi-stream, neural network-based model architecture.
Here are some more speech separation and enhancement results by our method, playing first the input video with mixed or noisy speech, then our results. Sound by others than the selected speakers can be entirely suppressed or suppressed to the desired level.
Application to Speech Recognition
Our method can also potentially be used as a pre-process for speech recognition and automatic video captioning. Handling overlapping speakers is a known challenge for automatic captioning systems, and separating the audio to the different sources could help in presenting more accurate and easy-to-read captions.
You can similarly see and compare the captions before and after speech separation in all the other videos in this post and on our website, by turning on closed captions in the YouTube player when playing the videos (“cc” button at the lower right corner of the player).

On our project web page you can find more results, as well as comparisons with state-of-the-art audio-only speech separation and with other recent audio-visual speech separation work. Indeed, with recent advances in deep learning, there is a clear growing interest in the academic community in audio-visual analysis. For example, independently and concurrently to our work, this work from UC Berkeley explored a self-supervised approach for separating speech of on/off-screen speakers, and this work from MIT addressed the problem of separating the sound of multiple on-screen objects (e.g., musical instruments), while locating the image regions from which the sound originates.

We envision a wide range of applications for this technology. We are currently exploring opportunities for incorporating it into various Google products. Stay tuned!

Acknowledgements
The research described in this post was done by Ariel Ephrat (as an intern), Inbar Mosseri, Oran Lang, Tali Dekel, Kevin Wilson, Avinatan Hassidim, Bill Freeman and Michael Rubinstein. We would like to thank Yossi Matias and Google Research Israel for their support for the project, and John Hershey for his valuable feedback. We also thank Arkady Ziefman for his help with animations and figures, and Rachel Soh for helping us procure permissions for video content in our results.

Source: Google AI Blog


Fun new ways developers are experimenting with voice interaction

Posted by Amit Pitaru, Creative Lab

Voice interaction has the potential to simplify the way we use technology. And with Dialogflow, Actions on Google, and Speech Synthesis API, it's becoming easier for any developer to create voice-based experiences. That's why we've created Voice Experiments, a site to showcase how developers are exploring voice interaction in all kinds of exciting new ways.

The site includes a few experiments that show how voice interaction can be used to explore music, gaming, storytelling, and more. MixLab makes it easier for anyone to create music, using simple voice commands. Mystery Animal puts a new spin on a classic game. And Story Speakerlets you create interactive, spoken stories by just writing in a Google Doc – no coding required.

You can try the experiments through the Google Assistant on your phone and on voice-activated speakers like the Google Home. Or you can try them on the web using a browser like Chrome.

It's still early days for voice interaction, and we're excited to see what you will make. Visit g.co/VoiceExperiments to play with the experiments or submit your own.

Kaldi now offers TensorFlow integration

Posted by Raziel Alvarez, Staff Research Engineer at Google and Yishay Carmiel, Founder of IntelligentWire

Automatic speech recognition (ASR) has seen widespread adoption due to the recent proliferation of virtual personal assistants and advances in word recognition accuracy from the application of deep learning algorithms. Many speech recognition teams rely on Kaldi, a popular open-source speech recognition toolkit. We're announcing today that Kaldi now offers TensorFlow integration.

With this integration, speech recognition researchers and developers using Kaldi will be able to use TensorFlow to explore and deploy deep learning models in their Kaldi speech recognition pipelines. This will allow the Kaldi community to build even better and more powerful ASR systems as well as providing TensorFlow users with a path to explore ASR while drawing upon the experience of the large community of Kaldi developers.

Building an ASR system that can understand human speech in every language, accent, environment, and type of conversation is an extremely complex undertaking. A traditional ASR system can be seen as a processing pipeline with many separate modules, where each module operates on the output from the previous one. Raw audio data enters the pipeline at one end and a transcription of recognized speech emerges from the other. In the case of Kaldi, these ASR transcriptions are post processed in a variety of ways to support an increasing array of end-user applications.

Yishay Carmiel and Hainan Xu of Seattle-based IntelligentWire, who led the development of the integration between Kaldi and TensorFlow with support from the two teams, know this complexity first-hand. Their company has developed cloud software to bridge the gap between live phone conversations and business applications. Their goal is to let businesses analyze and act on the contents of the thousands of conversations their representatives have with customers in real-time and automatically handle tasks like data entry or responding to requests. IntelligentWire is currently focused on the contact center market, in which more than 22 million agents throughout the world spend 50 billion hours a year on the phone and about 25 billion hours interfacing with and operating various business applications.

For an ASR system to be useful in this context, it must not only deliver an accurate transcription but do so with very low latency in a way that can be scaled to support many thousands of concurrent conversations efficiently. In situations like this, recent advances in deep learning can help push technical limits, and TensorFlow can be very useful.

In the last few years, deep neural networks have been used to replace many existing ASR modules, resulting in significant gains in word recognition accuracy. These deep learning models typically require processing vast amounts of data at scale, which TensorFlow simplifies. However, several major challenges must still be overcome when developing production-grade ASR systems:

  • Algorithms - Deep learning algorithms give the best results when tailored to the task at hand, including the acoustic environment (e.g. noise), the specific language spoken, the range of vocabulary, etc. These algorithms are not always easy to adapt once deployed.
  • Data - Building an ASR system for different languages and different acoustic environments requires large quantities of multiple types of data. Such data may not always be available or may not be suitable for the use case.
  • Scale - ASR systems that can support massive amounts of usage and many languages typically consume large amounts of computational power.

One of the ASR system modules that exemplifies these challenges is the language model. Language models are a key part of most state-of-the-art ASR systems; they provide linguistic context that helps predict the proper sequence of words and distinguish between words that sound similar. With recent machine learning breakthroughs, speech recognition developers are now using language models based on deep learning, known as neural language models. In particular, recurrent neural language models have shown superior results over classic statistical approaches.

However, the training and deployment of neural language models is complicated and highly time-consuming. For IntelligentWire, the integration of TensorFlow into Kaldi has reduced the ASR development cycle by an order of magnitude. If a language model already exists in TensorFlow, then going from model to proof of concept can take days rather than weeks; for new models, the development time can be reduced from months to weeks. Deploying new TensorFlow models into production Kaldi pipelines is straightforward as well, providing big gains for anyone working directly with Kaldi as well as the promise of more intelligent ASR systems for everyone in the future.

Similarly, this integration provides TensorFlow developers with easy access to a robust ASR platform and the ability to incorporate existing speech processing pipelines, such as Kaldi's powerful acoustic model, into their machine learning applications. Kaldi modules that feed the training of a TensorFlow deep learning model can be swapped cleanly, facilitating exploration, and the same pipeline that is used in production can be reused to evaluate the quality of the model.

We hope this Kaldi-TensorFlow integration will bring these two vibrant open-source communities closer together and support a wide variety of new speech-based products and related research breakthroughs. To get started using Kaldi with TensorFlow, please check out the Kaldi repo and also take a look at an example for Kaldi setup running with TensorFlow.