Models, code, and papers for "Ron J. Weiss":

A spelling correction model for end-to-end speech recognition

Feb 19, 2019
Jinxi Guo, Tara N. Sainath, Ron J. Weiss

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language model component of the end-to-end model is only trained on transcribed audio-text pairs, which leads to performance degradation especially on rare words. While there have been a variety of work that look at incorporating an external LM trained on text-only data into the end-to-end framework, none of them have taken into account the characteristic error distribution made by the model. In this paper, we propose a novel approach to utilizing text-only data, by training a spelling correction (SC) model to explicitly correct those errors. On the LibriSpeech dataset, we demonstrate that the proposed model results in an 18.6% relative improvement in WER over the baseline model when directly correcting top ASR hypothesis, and a 29.0% relative improvement when further rescoring an expanded n-best list using an external LM.

* Accepted to ICASSP 2019 

  Click for Model/Code and Paper
On Using Backpropagation for Speech Texture Generation and Voice Conversion

Mar 08, 2018
Jan Chorowski, Ron J. Weiss, Rif A. Saurous, Samy Bengio

Inspired by recent work on neural network image generation which rely on backpropagation towards the network inputs, we present a proof-of-concept system for speech texture synthesis and voice conversion based on two mechanisms: approximate inversion of the representation learned by a speech recognition neural network, and on matching statistics of neuron activations between different source and target utterances. Similar to image texture synthesis and neural style transfer, the system works by optimizing a cost function with respect to the input waveform samples. To this end we use a differentiable mel-filterbank feature extraction pipeline and train a convolutional CTC speech recognition network. Our system is able to extract speaker characteristics from very limited amounts of target speaker data, as little as a few seconds, and can be used to generate realistic speech babble or reconstruct an utterance in a different voice.

* Accepted to ICASSP 2018 

  Click for Model/Code and Paper
Unsupervised speech representation learning using WaveNet autoencoders

Jan 25, 2019
Jan Chorowski, Ron J. Weiss, Samy Bengio, Aäron van den Oord

We consider the task of unsupervised extraction of meaningful latent representations of speech by applying autoencoding neural networks to speech waveforms. The goal is to learn a representation able to capture high level semantic content from the signal, e.g. phoneme identities, while being invariant to confounding low level details in the signal such as the underlying pitch contour or background noise. The behavior of autoencoder models depends on the kind of constraint that is applied to the latent representation. We compare three variants: a simple dimensionality reduction bottleneck, a Gaussian Variational Autoencoder (VAE), and a discrete Vector Quantized VAE (VQ-VAE). We analyze the quality of learned representations in terms of speaker independence, the ability to predict phonetic content, and the ability to accurately reconstruct individual spectrogram frames. Moreover, for discrete encodings extracted using the VQ-VAE, we measure the ease of mapping them to phonemes. We introduce a regularization scheme that forces the representations to focus on the phonetic content of the utterance and report performance comparable with the top entries in the ZeroSpeech 2017 unsupervised acoustic unit discovery task.

  Click for Model/Code and Paper
Sequence-to-Sequence Models Can Directly Translate Foreign Speech

Jun 12, 2017
Ron J. Weiss, Jan Chorowski, Navdeep Jaitly, Yonghui Wu, Zhifeng Chen

We present a recurrent encoder-decoder deep neural network architecture that directly translates speech in one language into text in another. The model does not explicitly transcribe the speech into text in the source language, nor does it require supervision from the ground truth source language transcription during training. We apply a slightly modified sequence-to-sequence with attention architecture that has previously been used for speech recognition and show that it can be repurposed for this more complex task, illustrating the power of attention-based models. A single model trained end-to-end obtains state-of-the-art performance on the Fisher Callhome Spanish-English speech translation task, outperforming a cascade of independently trained sequence-to-sequence speech recognition and machine translation models by 1.8 BLEU points on the Fisher test set. In addition, we find that making use of the training data in both languages by multi-task training sequence-to-sequence speech translation and recognition models with a shared encoder network can improve performance by a further 1.4 BLEU points.

* 5 pages, 1 figure. Interspeech 2017 

  Click for Model/Code and Paper
Online and Linear-Time Attention by Enforcing Monotonic Alignments

Jun 29, 2017
Colin Raffel, Minh-Thang Luong, Peter J. Liu, Ron J. Weiss, Douglas Eck

Recurrent neural network models with an attention mechanism have proven to be extremely effective on a wide variety of sequence-to-sequence problems. However, the fact that soft attention mechanisms perform a pass over the entire input sequence when producing each element in the output sequence precludes their use in online settings and results in a quadratic time complexity. Based on the insight that the alignment between input and output sequence elements is monotonic in many problems of interest, we propose an end-to-end differentiable method for learning monotonic alignments which, at test time, enables computing attention online and in linear time. We validate our approach on sentence summarization, machine translation, and online speech recognition problems and achieve results competitive with existing sequence-to-sequence models.

* ICML camera-ready version; 10 pages + 9 page appendix 

  Click for Model/Code and Paper
Direct speech-to-speech translation with a sequence-to-sequence model

Apr 12, 2019
Ye Jia, Ron J. Weiss, Fadi Biadsy, Wolfgang Macherey, Melvin Johnson, Zhifeng Chen, Yonghui Wu

We present an attention-based sequence-to-sequence neural network which can directly translate speech from one language into speech in another language, without relying on an intermediate text representation. The network is trained end-to-end, learning to map speech spectrograms into target spectrograms in another language, corresponding to the translated content (in a different canonical voice). We further demonstrate the ability to synthesize translated speech using the voice of the source speaker. We conduct experiments on two Spanish-to-English speech translation datasets, and find that the proposed model slightly underperforms a baseline cascade of a direct speech-to-text translation model and a text-to-speech synthesis model, demonstrating the feasibility of the approach on this very challenging task.

* Submitted to Interspeech 2019 

  Click for Model/Code and Paper
Multilingual Speech Recognition With A Single End-To-End Model

Feb 15, 2018
Shubham Toshniwal, Tara N. Sainath, Ron J. Weiss, Bo Li, Pedro Moreno, Eugene Weinstein, Kanishka Rao

Training a conventional automatic speech recognition (ASR) system to support multiple languages is challenging because the sub-word unit, lexicon and word inventories are typically language specific. In contrast, sequence-to-sequence models are well suited for multilingual ASR because they encapsulate an acoustic, pronunciation and language model jointly in a single network. In this work we present a single sequence-to-sequence ASR model trained on 9 different Indian languages, which have very little overlap in their scripts. Specifically, we take a union of language-specific grapheme sets and train a grapheme-based sequence-to-sequence model jointly on data from all languages. We find that this model, which is not explicitly given any information about language identity, improves recognition performance by 21% relative compared to analogous sequence-to-sequence models trained on each language individually. By modifying the model to accept a language identifier as an additional input feature, we further improve performance by an additional 7% relative and eliminate confusion between different languages.

* Accepted in ICASSP 2018 

  Click for Model/Code and Paper
Learning to Speak Fluently in a Foreign Language: Multilingual Speech Synthesis and Cross-Language Voice Cloning

Jul 24, 2019
Yu Zhang, Ron J. Weiss, Heiga Zen, Yonghui Wu, Zhifeng Chen, RJ Skerry-Ryan, Ye Jia, Andrew Rosenberg, Bhuvana Ramabhadran

We present a multispeaker, multilingual text-to-speech (TTS) synthesis model based on Tacotron that is able to produce high quality speech in multiple languages. Moreover, the model is able to transfer voices across languages, e.g. synthesize fluent Spanish speech using an English speaker's voice, without training on any bilingual or parallel examples. Such transfer works across distantly related languages, e.g. English and Mandarin. Critical to achieving this result are: 1. using a phonemic input representation to encourage sharing of model capacity across languages, and 2. incorporating an adversarial loss term to encourage the model to disentangle its representation of speaker identity (which is perfectly correlated with language in the training data) from the speech content. Further scaling up the model by training on multiple speakers of each language, and incorporating an autoencoding input to help stabilize attention during training, results in a model which can be used to consistently synthesize intelligible speech for training speakers in all languages seen during training, and in native or foreign accents.

* 5 pages, submitted to Interspeech 2019 

  Click for Model/Code and Paper
Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation

Nov 05, 2018
Ye Jia, Melvin Johnson, Wolfgang Macherey, Ron J. Weiss, Yuan Cao, Chung-Cheng Chiu, Naveen Ari, Stella Laurenzo, Yonghui Wu

End-to-end Speech Translation (ST) models have many potential advantages when compared to the cascade of Automatic Speech Recognition (ASR) and text Machine Translation (MT) models, including lowered inference latency and the avoidance of error compounding. However, the quality of end-to-end ST is often limited by a paucity of training data, since it is difficult to collect large parallel corpora of speech and translated transcript pairs. Previous studies have proposed the use of pre-trained components and multi-task learning in order to benefit from weakly supervised training data, such as speech-to-transcript or text-to-foreign-text pairs. In this paper, we demonstrate that using pre-trained MT or text-to-speech (TTS) synthesis models to convert weakly supervised data into speech-to-translation pairs for ST training can be more effective than multi-task learning. Furthermore, we demonstrate that a high quality end-to-end ST model can be trained using only weakly supervised datasets, and that synthetic data sourced from unlabeled monolingual text or speech can be used to improve performance. Finally, we discuss methods for avoiding overfitting to synthetic speech with a quantitative ablation study.

  Click for Model/Code and Paper
Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron

Mar 24, 2018
RJ Skerry-Ryan, Eric Battenberg, Ying Xiao, Yuxuan Wang, Daisy Stanton, Joel Shor, Ron J. Weiss, Rob Clark, Rif A. Saurous

We present an extension to the Tacotron speech synthesis architecture that learns a latent embedding space of prosody, derived from a reference acoustic representation containing the desired prosody. We show that conditioning Tacotron on this learned embedding space results in synthesized audio that matches the prosody of the reference signal with fine time detail even when the reference and synthesis speakers are different. Additionally, we show that a reference prosody embedding can be used to synthesize text that is different from that of the reference utterance. We define several quantitative and subjective metrics for evaluating prosody transfer, and report results with accompanying audio samples from single-speaker and 44-speaker Tacotron models on a prosody transfer task.

  Click for Model/Code and Paper
VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking

Oct 27, 2018
Quan Wang, Hannah Muckenhirn, Kevin Wilson, Prashant Sridhar, Zelin Wu, John Hershey, Rif A. Saurous, Ron J. Weiss, Ye Jia, Ignacio Lopez Moreno

In this paper, we present a novel system that separates the voice of a target speaker from multi-speaker signals, by making use of a reference signal from the target speaker. We achieve this by training two separate neural networks: (1) A speaker recognition network that produces speaker-discriminative embeddings; (2) A spectrogram masking network that takes both noisy spectrogram and speaker embedding as input, and produces a mask. Our system significantly reduces the speech recognition WER on multi-speaker signals, with minimal WER degradation on single-speaker signals.

* To be submitted to ICASSP 2019 

  Click for Model/Code and Paper
Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis

Nov 05, 2018
Ye Jia, Yu Zhang, Ron J. Weiss, Quan Wang, Jonathan Shen, Fei Ren, Zhifeng Chen, Patrick Nguyen, Ruoming Pang, Ignacio Lopez Moreno, Yonghui Wu

We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently trained components: (1) a speaker encoder network, trained on a speaker verification task using an independent dataset of noisy speech from thousands of speakers without transcripts, to generate a fixed-dimensional embedding vector from seconds of reference speech from a target speaker; (2) a sequence-to-sequence synthesis network based on Tacotron 2, which generates a mel spectrogram from text, conditioned on the speaker embedding; (3) an auto-regressive WaveNet-based vocoder that converts the mel spectrogram into a sequence of time domain waveform samples. We demonstrate that the proposed model is able to transfer the knowledge of speaker variability learned by the discriminatively-trained speaker encoder to the new task, and is able to synthesize natural speech from speakers that were not seen during training. We quantify the importance of training the speaker encoder on a large and diverse speaker set in order to obtain the best generalization performance. Finally, we show that randomly sampled speaker embeddings can be used to synthesize speech in the voice of novel speakers dissimilar from those used in training, indicating that the model has learned a high quality speaker representation.

* NIPS 2018 

  Click for Model/Code and Paper
Hierarchical Generative Modeling for Controllable Speech Synthesis

Oct 16, 2018
Wei-Ning Hsu, Yu Zhang, Ron J. Weiss, Heiga Zen, Yonghui Wu, Yuxuan Wang, Yuan Cao, Ye Jia, Zhifeng Chen, Jonathan Shen, Patrick Nguyen, Ruoming Pang

This paper proposes a neural end-to-end text-to-speech (TTS) model which can control latent attributes in the generated speech that are rarely annotated in the training data, such as speaking style, accent, background noise, and recording conditions. The model is formulated as a conditional generative model with two levels of hierarchical latent variables. The first level is a categorical variable, which represents attribute groups (e.g. clean/noisy) and provides interpretability. The second level, conditioned on the first, is a multivariate Gaussian variable, which characterizes specific attribute configurations (e.g. noise level, speaking rate) and enables disentangled fine-grained control over these attributes. This amounts to using a Gaussian mixture model (GMM) for the latent distribution. Extensive evaluation demonstrates its ability to control the aforementioned attributes. In particular, it is capable of consistently synthesizing high-quality clean speech regardless of the quality of the training data for the target speaker.

  Click for Model/Code and Paper
Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions

Feb 16, 2018
Jonathan Shen, Ruoming Pang, Ron J. Weiss, Mike Schuster, Navdeep Jaitly, Zongheng Yang, Zhifeng Chen, Yu Zhang, Yuxuan Wang, RJ Skerry-Ryan, Rif A. Saurous, Yannis Agiomyrgiannakis, Yonghui Wu

This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spectrograms, followed by a modified WaveNet model acting as a vocoder to synthesize timedomain waveforms from those spectrograms. Our model achieves a mean opinion score (MOS) of $4.53$ comparable to a MOS of $4.58$ for professionally recorded speech. To validate our design choices, we present ablation studies of key components of our system and evaluate the impact of using mel spectrograms as the input to WaveNet instead of linguistic, duration, and $F_0$ features. We further demonstrate that using a compact acoustic intermediate representation enables significant simplification of the WaveNet architecture.

* Accepted to ICASSP 2018 

  Click for Model/Code and Paper
Tacotron: Towards End-to-End Speech Synthesis

Apr 06, 2017
Yuxuan Wang, RJ Skerry-Ryan, Daisy Stanton, Yonghui Wu, Ron J. Weiss, Navdeep Jaitly, Zongheng Yang, Ying Xiao, Zhifeng Chen, Samy Bengio, Quoc Le, Yannis Agiomyrgiannakis, Rob Clark, Rif A. Saurous

A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module. Building these components often requires extensive domain expertise and may contain brittle design choices. In this paper, we present Tacotron, an end-to-end generative text-to-speech model that synthesizes speech directly from characters. Given <text, audio> pairs, the model can be trained completely from scratch with random initialization. We present several key techniques to make the sequence-to-sequence framework perform well for this challenging task. Tacotron achieves a 3.82 subjective 5-scale mean opinion score on US English, outperforming a production parametric system in terms of naturalness. In addition, since Tacotron generates speech at the frame level, it's substantially faster than sample-level autoregressive methods.

* Submitted to Interspeech 2017. v2 changed paper title to be consistent with our conference submission (no content change other than typo fixes) 

  Click for Model/Code and Paper
State-of-the-art Speech Recognition With Sequence-to-Sequence Models

Feb 23, 2018
Chung-Cheng Chiu, Tara N. Sainath, Yonghui Wu, Rohit Prabhavalkar, Patrick Nguyen, Zhifeng Chen, Anjuli Kannan, Ron J. Weiss, Kanishka Rao, Ekaterina Gonina, Navdeep Jaitly, Bo Li, Jan Chorowski, Michiel Bacchiani

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural network. In previous work, we have shown that such architectures are comparable to state-of-theart ASR systems on dictation tasks, but it was not clear if such architectures would be practical for more challenging tasks such as voice search. In this work, we explore a variety of structural and optimization improvements to our LAS model which significantly improve performance. On the structural side, we show that word piece models can be used instead of graphemes. We also introduce a multi-head attention architecture, which offers improvements over the commonly-used single-head attention. On the optimization side, we explore synchronous training, scheduled sampling, label smoothing, and minimum word error rate optimization, which are all shown to improve accuracy. We present results with a unidirectional LSTM encoder for streaming recognition. On a 12, 500 hour voice search task, we find that the proposed changes improve the WER from 9.2% to 5.6%, while the best conventional system achieves 6.7%; on a dictation task our model achieves a WER of 4.1% compared to 5% for the conventional system.

* ICASSP camera-ready version 

  Click for Model/Code and Paper
CNN Architectures for Large-Scale Audio Classification

Jan 10, 2017
Shawn Hershey, Sourish Chaudhuri, Daniel P. W. Ellis, Jort F. Gemmeke, Aren Jansen, R. Channing Moore, Manoj Plakal, Devin Platt, Rif A. Saurous, Bryan Seybold, Malcolm Slaney, Ron J. Weiss, Kevin Wilson

Convolutional Neural Networks (CNNs) have proven very effective in image classification and show promise for audio. We use various CNN architectures to classify the soundtracks of a dataset of 70M training videos (5.24 million hours) with 30,871 video-level labels. We examine fully connected Deep Neural Networks (DNNs), AlexNet [1], VGG [2], Inception [3], and ResNet [4]. We investigate varying the size of both training set and label vocabulary, finding that analogs of the CNNs used in image classification do well on our audio classification task, and larger training and label sets help up to a point. A model using embeddings from these classifiers does much better than raw features on the Audio Set [5] Acoustic Event Detection (AED) classification task.

* Accepted for publication at ICASSP 2017 Changes: Added definitions of mAP, AUC, and d-prime. Updated mAP/AUC/d-prime numbers for Audio Set based on changes of latest Audio Set revision. Changed wording to fit 4 page limit with new additions 

  Click for Model/Code and Paper
Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling

Feb 21, 2019
Jonathan Shen, Patrick Nguyen, Yonghui Wu, Zhifeng Chen, Mia X. Chen, Ye Jia, Anjuli Kannan, Tara Sainath, Yuan Cao, Chung-Cheng Chiu, Yanzhang He, Jan Chorowski, Smit Hinsu, Stella Laurenzo, James Qin, Orhan Firat, Wolfgang Macherey, Suyog Gupta, Ankur Bapna, Shuyuan Zhang, Ruoming Pang, Ron J. Weiss, Rohit Prabhavalkar, Qiao Liang, Benoit Jacob, Bowen Liang, HyoukJoong Lee, Ciprian Chelba, Sébastien Jean, Bo Li, Melvin Johnson, Rohan Anil, Rajat Tibrewal, Xiaobing Liu, Akiko Eriguchi, Navdeep Jaitly, Naveen Ari, Colin Cherry, Parisa Haghani, Otavio Good, Youlong Cheng, Raziel Alvarez, Isaac Caswell, Wei-Ning Hsu, Zongheng Yang, Kuan-Chieh Wang, Ekaterina Gonina, Katrin Tomanek, Ben Vanik, Zelin Wu, Llion Jones, Mike Schuster, Yanping Huang, Dehao Chen, Kazuki Irie, George Foster, John Richardson, Klaus Macherey, Antoine Bruguier, Heiga Zen, Colin Raffel, Shankar Kumar, Kanishka Rao, David Rybach, Matthew Murray, Vijayaditya Peddinti, Maxim Krikun, Michiel A. U. Bacchiani, Thomas B. Jablin, Rob Suderman, Ian Williams, Benjamin Lee, Deepti Bhatia, Justin Carlson, Semih Yavuz, Yu Zhang, Ian McGraw, Max Galkin, Qi Ge, Golan Pundak, Chad Whipkey, Todd Wang, Uri Alon, Dmitry Lepikhin, Ye Tian, Sara Sabour, William Chan, Shubham Toshniwal, Baohua Liao, Michael Nirschl, Pat Rondon

Lingvo is a Tensorflow framework offering a complete solution for collaborative deep learning research, with a particular focus towards sequence-to-sequence models. Lingvo models are composed of modular building blocks that are flexible and easily extensible, and experiment configurations are centralized and highly customizable. Distributed training and quantized inference are supported directly within the framework, and it contains existing implementations of a large number of utilities, helper functions, and the newest research ideas. Lingvo has been used in collaboration by dozens of researchers in more than 20 papers over the last two years. This document outlines the underlying design of Lingvo and serves as an introduction to the various pieces of the framework, while also offering examples of advanced features that showcase the capabilities of the framework.

  Click for Model/Code and Paper
Autonomy Infused Teleoperation with Application to BCI Manipulation

Jun 07, 2015
Katharina Muelling, Arun Venkatraman, Jean-Sebastien Valois, John Downey, Jeffrey Weiss, Shervin Javdani, Martial Hebert, Andrew B. Schwartz, Jennifer L. Collinger, J. Andrew Bagnell

Robot teleoperation systems face a common set of challenges including latency, low-dimensional user commands, and asymmetric control inputs. User control with Brain-Computer Interfaces (BCIs) exacerbates these problems through especially noisy and erratic low-dimensional motion commands due to the difficulty in decoding neural activity. We introduce a general framework to address these challenges through a combination of computer vision, user intent inference, and arbitration between the human input and autonomous control schemes. Adjustable levels of assistance allow the system to balance the operator's capabilities and feelings of comfort and control while compensating for a task's difficulty. We present experimental results demonstrating significant performance improvement using the shared-control assistance framework on adapted rehabilitation benchmarks with two subjects implanted with intracortical brain-computer interfaces controlling a seven degree-of-freedom robotic manipulator as a prosthetic. Our results further indicate that shared assistance mitigates perceived user difficulty and even enables successful performance on previously infeasible tasks. We showcase the extensibility of our architecture with applications to quality-of-life tasks such as opening a door, pouring liquids from containers, and manipulation with novel objects in densely cluttered environments.

  Click for Model/Code and Paper