Tara N. Sainath

发表

Learning filter banks within a deep neural network framework

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Auto-encoder bottleneck features using deep belief networks

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving the efficiency of forward-backward algorithm using batched computation in TensorFlow

Tara N. Sainath, Arun Narayanan, Khe Chai Sim, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Neural Network Adaptive Beamforming for Robust Multichannel Speech Recognition

Tara N. Sainath, Michiel Bacchiani, Ron J. Weiss, 2016, INTERSPEECH.

Minimum Word Error Rate Training for Attention-Based Sequence-to-Sequence Models

Tara N. Sainath, Patrick Nguyen, Yonghui Wu, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improved pre-training of Deep Belief Networks using Sparse Encoding Symmetric Machines

Tara N. Sainath, Bhuvana Ramabhadran, David Nahamoo, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Deep Context: End-to-end Contextual Speech Recognition

Tara N. Sainath, Ding Zhao, Rohit Prabhavalkar, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Acoustic Modeling for Google Home

Mitch Weintraub, Tara N. Sainath, Arun Narayanan, 2017, INTERSPEECH.

Cascaded Encoders for Unifying Streaming and Non-Streaming ASR pdf

Tara N. Sainath, Arun Narayanan, Rohit Prabhavalkar, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The Use of isometric transformations and bayesian estimation in compressive sensing for fMRI classification

Tara N. Sainath, Bhuvana Ramabhadran, Pini Gurfil, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Convolutional neural networks for small-footprint keyword spotting

Tara N. Sainath, Carolina Parada, Carolina Parada, 2015, INTERSPEECH.

Joint training of convolutional and non-convolutional neural networks

Tara N. Sainath, George Saon, Hagen Soltau, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Learning compact recurrent neural networks

Tara N. Sainath, Vikas Sindhwani, Zhiyun Lu, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Spectral Distortion Model for Training Phase-Sensitive Deep-Neural Networks for Far-Field Speech Recognition

Tara N. Sainath, Arun Narayanan, Michiel Bacchiani, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Reducing the Computational Complexity of Two-Dimensional LSTMs

Tara N. Sainath, Bo Li, 2017, INTERSPEECH.

Temporal Modeling Using Dilated Convolution and Gating for Voice-Activity-Detection

Tara N. Sainath, Oriol Vinyals, Aäron van den Oord, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Unsupervised Audio Segmentation using Extended Baum-Welch Transformations

Tara N. Sainath, Giridharan Iyengar, Dimitri Kanevsky, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Query-by-example keyword spotting using long short-term memory networks

Tara N. Sainath, Carolina Parada, Guoguo Chen, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Low-rank matrix factorization for Deep Neural Network training with high-dimensional output targets

Ebru Arisoy, Tara N. Sainath, Brian Kingsbury, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Improving Performance of End-to-End ASR on Numeric Sequences

Tara N. Sainath, Hao Zhang, Cal Peyser, 2019, INTERSPEECH.

Speaker location and microphone spacing invariant acoustic modeling from raw multichannel waveforms

Tara N. Sainath, Arun Narayanan, Michiel Bacchiani, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Gradient steepness metrics using extended Baum-Welch transformations for universal pattern recognition tasks

Tara N. Sainath, Bhuvana Ramabhadran, Dimitri Kanevsky, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Highway-LSTM and Recurrent Highway Networks for Speech Recognition

Tara N. Sainath, Golan Pundak, G. Pundak, 2017, INTERSPEECH.

Emitting Word Timings with End-to-End Models

Tara N. Sainath, David Rybach, Ruoming Pang, 2020, INTERSPEECH.

Feature Learning with Raw-Waveform CLDNNs for Voice Activity Detection

Tara N. Sainath, Carolina Parada, Gabor Simko, 2016, INTERSPEECH.

Improving Proper Noun Recognition in End-To-End Asr by Customization of the Mwer Loss Criterion

Tara N. Sainath, Golan Pundak, Cal Peyser, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Parallel Deep Neural Network Training for Big Data on Blue Gene/Q

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2017, IEEE Trans. Parallel Distributed Syst..

Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models

Tara N. Sainath, Ke Hu, Rohit Prabhavalkar, 2019, INTERSPEECH.

A Comparison of Techniques for Language Model Integration in Encoder-Decoder Speech Recognition

Tara N. Sainath, Yonghui Wu, Karen Livescu, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Multitask Training with Text Data for End-to-End Speech Recognition pdf

Tara N. Sainath, Ron J. Weiss, Peidong Wang, 2020, ArXiv.

Endpoint Detection Using Grid Long Short-Term Memory Networks for Streaming Speech Recognition

Tara N. Sainath, Bo Li, Carolina Parada, 2017, INTERSPEECH.

Audio classification using extended baum-welch transformations

Tara N. Sainath, Victor Zue, Dimitri Kanevsky, 2007, INTERSPEECH.

Towards Fast and Accurate Streaming End-To-End ASR

Tara N. Sainath, Bo Li, Yonghui Wu, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Compression of End-to-End Models

Tara N. Sainath, Yonghui Wu, Rohit Prabhavalkar, 2018, INTERSPEECH.

A comparison of broad phonetic and acoustic units for noise robust segment-based phonetic recognition

Tara N. Sainath, Victor Zue, V. Zue, 2008, INTERSPEECH.

Developing speech recognition systems for corpus indexing under the IARPA Babel program

Xiaodong Cui, Tara N. Sainath, Brian Kingsbury, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

An exploration of large vocabulary tools for small vocabulary phonetic recognition

Tara N. Sainath, Bhuvana Ramabhadran, Michael Picheny, 2009, 2009 IEEE Workshop on Automatic Speech Recognition & Understanding.

RNN-T Models Fail to Generalize to Out-of-Domain Audio: Causes and Solutions pdf

Tara N. Sainath, Arun Narayanan, Navdeep Jaitly, 2020, 2021 IEEE Spoken Language Technology Workshop (SLT).

A generalized family of parameter estimation techniques

Tara N. Sainath, Bhuvana Ramabhadran, Dimitri Kanevsky, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Broad phonetic class recognition in a Hidden Markov model framework using extended Baum-Welch transformations

Tara N. Sainath, Bhuvana Ramabhadran, Dimitri Kanevsky, 2007, 2007 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU).

Multistate Encoding with End-To-End Speech RNN Transducer Network

Tara N. Sainath, Bo Li, Yu Zhang, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The shared views of four research groups )

Tara N. Sainath, Brian Kingsbury, Geoffrey E. Hinton, 2012 .

Streaming End-to-end Speech Recognition for Mobile Devices

Tara N. Sainath, Ding Zhao, Ian McGraw, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Bayesian compressive sensing for phonetic classification

Tara N. Sainath, Bhuvana Ramabhadran, Dimitri Kanevsky, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Applications of broad class knowledge for noise robust speech recognition

Tara N. Sainath, 2009 .

Universal ASR: Unify and Improve Streaming ASR with Full-context Modeling pdf

Tara N. Sainath, Bo Li, Jiahui Yu, 2020, ArXiv.

Large vocabulary automatic speech recognition for children

Tara N. Sainath, Olivier Siohan, Hank Liao, 2015, INTERSPEECH.

Kalman filtering for compressed sensing

Tara N. Sainath, Bhuvana Ramabhadran, Pini Gurfil, 2010, 2010 13th International Conference on Information Fusion.

Protecting data a network entity, while maintaining network properties

Tara N. Sainath, Dimitri Kanevsky, Clifford A. Pickover, 2012 .

Learning the speech front-end with raw waveform CLDNNs

Tara N. Sainath, Oriol Vinyals, Ron J. Weiss, 2015, INTERSPEECH.

Reducing Impediments to Collaboration in a Virtual Design World

Tara N. Sainath, Amar Gupta, Satwik Seshasai, 2002 .

Improving the Performance of Online Neural Transducer Models

Tara N. Sainath, Patrick Nguyen, Yonghui Wu, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An Attention-Based Joint Acoustic and Text on-Device End-To-End Model

Tara N. Sainath, Chung-Cheng Chiu, Ruoming Pang, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Bytes Are All You Need: End-to-end Multilingual Speech Recognition and Synthesis with Bytes

Tara N. Sainath, Yu Zhang, William Chan, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An Analysis of "Attention" in Sequence-to-Sequence Models

Tara N. Sainath, Navdeep Jaitly, Rohit Prabhavalkar, 2017, INTERSPEECH.

An evaluation of posterior modeling techniques for phonetic recognition

Tara N. Sainath, Bhuvana Ramabhadran, Dimitri Kanevsky, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Improving training time of Hessian-free optimization for deep neural networks using preconditioning and sampling pdf

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2013, ArXiv.

Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling pdf

Tara N. Sainath, Ankur Bapna, Navdeep Jaitly, 2019, ArXiv.

Generalization of extended baum-welch parameter estimation for discriminative training and decoding

Tara N. Sainath, Bhuvana Ramabhadran, Dimitri Kanevsky, 2008, INTERSPEECH.

Application specific loss minimization using gradient boosting

Tara N. Sainath, Bhuvana Ramabhadran, Abhinav Sethy, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

FUNDAMENTAL TECHNOLOGIES IN MODERN SPEECH RECOGNITION Digital Object Identifier 10.1109/MSP.2012.2205597

Tara N. Sainath, Brian Kingsbury, Geoffrey E. Hinton, 2012 .

No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models

Tara N. Sainath, Shankar Kumar, Patrick Nguyen, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Making Deep Belief Networks effective for large vocabulary continuous speech recognition

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

Reducing Computational Complexities of Exemplar-Based Sparse Representations with Applications to Large Vocabulary Speech Recognition

Tara N. Sainath, Bhuvana Ramabhadran, Dimitri Kanevsky, 2011, INTERSPEECH.

Improvements to filterbank and delta learning within a deep neural network framework

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multilingual Speech Recognition with a Single End-to-End Model

Tara N. Sainath, Ron J. Weiss, Bo Li, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Contextual Speech Recognition with Difficult Negative Training Examples

Tara N. Sainath, Uri Alon, Golan Pundak, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Data selection for language modeling using sparse representations

Tara N. Sainath, Bhuvana Ramabhadran, Dimitri Kanevsky, 2010, INTERSPEECH.

Raw Multichannel Processing Using Deep Neural Networks

Tara N. Sainath, Arun Narayanan, Izhak Shafran, 2017, New Era for Robust Speech Recognition, Exploiting Deep Learning.

Annealed f-Smoothing as a Mechanism to Speed up Neural Network Training

Tara N. Sainath, Arun Narayanan, Olivier Siohan, 2017, INTERSPEECH.

An analysis of sparseness and regularization in exemplar-based methods for speech classification

Tara N. Sainath, Bhuvana Ramabhadran, Dimitri Kanevsky, 2010, INTERSPEECH.

State-of-the-Art Speech Recognition with Sequence-to-Sequence Models

Tara N. Sainath, Navdeep Jaitly, Yonghui Wu, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Deep Belief Networks using discriminative features for phone recognition

Tara N. Sainath, Bhuvana Ramabhadran, Michael Picheny, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Lower Frame Rate Neural Network Acoustic Models

Tara N. Sainath, Golan Pundak, G. Pundak, 2016, INTERSPEECH.

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

Tara N. Sainath, Bhuvana Ramabhadran, Arindrima Datta, 2019, INTERSPEECH.

Island-driven search using broad phonetic classes

Tara N. Sainath, 2009, 2009 IEEE Workshop on Automatic Speech Recognition & Understanding.

Accelerating Hessian-free optimization for Deep Neural Networks by implicit preconditioning and sampling

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Performance of Mask Based Statistical Beamforming in a Smart Home Scenario

Tara N. Sainath, Michiel Bacchiani, Jahn Heymann, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Exemplar-Based Processing for Speech Recognition: An Overview

Tara N. Sainath, Bhuvana Ramabhadran, Jerome R. Bellegarda, 2012, IEEE Signal Processing Magazine.

Recognizing Long-Form Speech Using Streaming End-to-End Models

Tara N. Sainath, Arun Narayanan, Rohit Prabhavalkar, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Domain Adaptation Using Factorized Hidden Layer for Robust Automatic Speech Recognition

Tara N. Sainath, Arun Narayanan, Khe Chai Sim, 2018, INTERSPEECH.

Enhancing Exemplar-Based Posteriors for Speech Recognition Tasks

Tara N. Sainath, Bhuvana Ramabhadran, Dimitri Kanevsky, 2012, INTERSPEECH.

Improvements to Deep Convolutional Neural Networks for LVCSR

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2013, 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.

Multi-Dialect Speech Recognition with a Single Sequence-to-Sequence Model

Tara N. Sainath, Patrick Nguyen, Zhifeng Chen, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A voice-commandable robotic forklift working alongside humans in minimally-prepared outdoor environments

Tara N. Sainath, Luke Fletcher, Jonathan P. How, 2010, 2010 IEEE International Conference on Robotics and Automation.

Parallel Deep Neural Network Training for Big Data on Blue Gene/Q

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2017, IEEE Transactions on Parallel and Distributed Systems.

Optimization Techniques to Improve Training Speed of Deep Neural Networks for Large Speech Tasks

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2013, IEEE Transactions on Audio, Speech, and Language Processing.

A Spelling Correction Model for End-to-end Speech Recognition

Tara N. Sainath, Ron J. Weiss, Jinxi Guo, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Comparison of Sequence-to-Sequence Models for Speech Recognition

Tara N. Sainath, Navdeep Jaitly, Rohit Prabhavalkar, 2017, INTERSPEECH.

Contextual Speech Recognition in End-to-end Neural Network Systems Using Beam Search

Tara N. Sainath, Ian Williams, David Rybach, 2018, INTERSPEECH.

Reducing the Computational Complexity of Multimicrophone Acoustic Models with Integrated Feature Extraction

Tara N. Sainath, Arun Narayanan, Izhak Shafran, 2016, INTERSPEECH.

Modeling Time-Frequency Patterns with LSTM vs. Convolutional Architectures for LVCSR Tasks

Tara N. Sainath, Bo Li, Bo Li, 2016, INTERSPEECH.

Convergence of Line Search A-Function Methods

Tara N. Sainath, Bhuvana Ramabhadran, Dimitri Kanevsky, 2011, INTERSPEECH.

A convex hull approach to sparse representations for exemplar-based speech recognition

Tara N. Sainath, Bhuvana Ramabhadran, Dimitri Kanevsky, 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

Sparse Representations for Speech Recognition

Tara N. Sainath, Bhuvana Ramabhadran, Stephen J. Wright, 2014 .

Kernel methods match Deep Neural Networks on TIMIT

Tara N. Sainath, Bhuvana Ramabhadran, Po-Sen Huang, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

FastEmit: Low-latency Streaming ASR with Sequence-level Emission Regularization pdf

Tara N. Sainath, Arun Narayanan, Jiahui Yu, 2020, ArXiv.

Acoustic modelling with CD-CTC-SMBR LSTM RNNS

Tara N. Sainath, Andrew W. Senior, Hasim Sak, 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

Deep convolutional neural networks for LVCSR

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Complex Linear Projection (CLP): A Discriminative Approach to Joint Feature Extraction and Acoustic Modeling

Tara N. Sainath, Izhak Shafran, Michiel Bacchiani, 2016, INTERSPEECH.

A Better and Faster end-to-end Model for Streaming ASR pdf

Tara N. Sainath, Arun Narayanan, Bo Li, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Parallel deep neural network training for LVCSR tasks using blue gene/Q

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2014, INTERSPEECH.

Exemplar-based Sparse Representation phone identification features

Tara N. Sainath, Bhuvana Ramabhadran, Vaibhava Goel, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Sparse representations for text categorization

Tara N. Sainath, Bhuvana Ramabhadran, Julia Hirschberg, 2010, INTERSPEECH.

A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality and Latency

Tara N. Sainath, Anjuli Kannan, Arun Narayanan, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Deep scattering spectra with deep neural networks for LVCSR tasks

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2014, INTERSPEECH.

A-Functions: A generalization of Extended Baum-Welch transformations to convex optimization

Tara N. Sainath, Bhuvana Ramabhadran, Peder A. Olsen, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home

Tara N. Sainath, Arun Narayanan, Michiel Bacchiani, 2017, INTERSPEECH.

Techniques for Improving Training Time of Deep Neural Networks with Applications to Speech Recognition

Tara N. Sainath, T. Sainath, 2014 .

Automatic gain control and multi-style training for robust small-footprint keyword spotting with deep neural networks

Tara N. Sainath, Rohit Prabhavalkar, Preetum Nakkiran, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An Analysis of Incorporating an External Language Model into a Sequence-to-Sequence Model

Tara N. Sainath, Patrick Nguyen, Yonghui Wu, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Incorporating sparse representation phone identification features in automatic speech recognition using exponential families

Tara N. Sainath, Bhuvana Ramabhadran, Vaibhava Goel, 2010, INTERSPEECH.

Deliberation Model Based Two-Pass End-To-End Speech Recognition

Tara N. Sainath, Ke Hu, Rohit Prabhavalkar, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Scalable Minimum Bayes Risk Training of Deep Neural Network Acoustic Models Using Distributed Hessian-free Optimization

Tara N. Sainath, Brian Kingsbury, Hagen Soltau, 2012, INTERSPEECH.

Shallow-Fusion End-to-End Contextual Biasing

Tara N. Sainath, Ding Zhao, Bo Li, 2019, INTERSPEECH.

Less is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging pdf

Tara N. Sainath, Arun Narayanan, Rohit Prabhavalkar, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Factored spatial and spectral multichannel raw waveform CLDNNs

Tara N. Sainath, Arun Narayanan, Michiel Bacchiani, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Automated Design Data and Rationale Capture

Tara N. Sainath, Amar Gupta, Satwik Seshasai, 2002 .

Deep Scattering Spectrum with deep neural networks

Tara N. Sainath, Bhuvana Ramabhadran, Vaibhava Goel, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks

Tara N. Sainath, Oriol Vinyals, Andrew W. Senior, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving deep neural networks for LVCSR using rectified linear units and dropout

Tara N. Sainath, Geoffrey E. Hinton, George E. Dahl, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Improving Tail Performance of a Deliberation E2E ASR Model Using a Large Text Corpus

Tara N. Sainath, Ruoming Pang, James Apfel, 2020, INTERSPEECH.

Deep Convolutional Neural Networks for Large-scale Speech Tasks

Tara N. Sainath, Brian Kingsbury, Bhuvana Ramabhadran, 2015, Neural Networks.

A Sinusoidal Model Approach to Acoustic Landmark Detection and Segmentation for Robust Segment-Based Speech Recognition

Tara N. Sainath, Timothy J. Hazen, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Multichannel Signal Processing With Deep Neural Networks for Automatic Speech Recognition

Tara N. Sainath, Arun Narayanan, Izhak Shafran, 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Low Latency Speech Recognition Using End-to-End Prefetching

Tara N. Sainath, Wei Li, Bo Li, 2020, INTERSPEECH.

Structured Transforms for Small-Footprint Deep Learning

Tara N. Sainath, Sanjiv Kumar, Vikas Sindhwani, 2015, NIPS.

Locally-connected and convolutional neural networks for small footprint speaker recognition

Tara N. Sainath, Mirkó Visontai, Ignacio Lopez-Moreno, 2015, INTERSPEECH.

Sparse representation features for speech recognition

Tara N. Sainath, Bhuvana Ramabhadran, Dimitri Kanevsky, 2010, INTERSPEECH.

N-best entropy based data selection for acoustic modeling

Tara N. Sainath, Bhuvana Ramabhadran, Jie Zhou, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Two-Pass End-to-End Speech Recognition pdf

Tara N. Sainath, Rohit Prabhavalkar, Wei Li, 2019, INTERSPEECH.

Tied & Reduced RNN-T Decoder pdf

Tara N. Sainath, Rami Botros, Wei Li, 2021, Interspeech.

Lookup-Table Recurrent Language Models for Long Tail Speech Recognition pdf

Tara N. Sainath, David Rybach, Trevor Strohman, 2021, Interspeech 2021.

Improving the Fusion of Acoustic and Text Representations in RNN-T

Tara N. Sainath, Shuo-yiin Chang, Bo Li, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multitask Training with Text Data for End-to-End Speech Recognition pdf

Tara N. Sainath, Ron J. Weiss, Peidong Wang, 2020, Interspeech.

BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition pdf

Tara N. Sainath, Bhuvana Ramabhadran, Aren Jansen, 2021, ArXiv.

A Deliberation-Based Joint Acoustic and Text Decoder

Tara N. Sainath, Sepand Mavandadi, Kevin Hu, 2021, Interspeech.

Scaling End-to-End Models for Large-Scale Multilingual ASR pdf

Tara N. Sainath, Ruoming Pang, Anmol Gulati, 2021, 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

FastEmit: Low-Latency Streaming ASR with Sequence-Level Emission Regularization

Tara N. Sainath, Arun Narayanan, Jiahui Yu, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Joint Unsupervised and Supervised Training for Multilingual ASR pdf

Tara N. Sainath, Ankur Bapna, Khe Chai Sim, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Better and Faster end-to-end Model for Streaming ASR

Tara N. Sainath, Arun Narayanan, Yu Zhang, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Learning Word-Level Confidence for Subword End-To-End ASR

Tara N. Sainath, Ian McGraw, Liangliang Cao, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Language Agnostic Multilingual Streaming On-Device ASR System

Tara N. Sainath, Bo Li, Trevor Strohman, 2022, INTERSPEECH.

BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition

Tara N. Sainath, Quoc V. Le, Yonghui Wu, 2021, IEEE Journal of Selected Topics in Signal Processing.

Streaming Intended Query Detection using E2E Modeling for Continued Conversation

Tara N. Sainath, Bo Li, Manaal Faruqui, 2022, INTERSPEECH.

Self-supervised Representation Learning for Speech Processing

Tara N. Sainath, Abdel-rahman Mohamed, Karen Livescu, 2022, NAACL.

Self-Supervised Speech Representation Learning: A Review

Tara N. Sainath, Jakob Drachmann Havtorn, Abdel-rahman Mohamed, 2022, IEEE Journal of Selected Topics in Signal Processing.

Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification

Tara N. Sainath, Bo Li, Trevor Strohman, 2022, INTERSPEECH.

A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition

Tara N. Sainath, S. M. Siniscalchi, Bo Li, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

End-to-End Speech Recognition: A Survey

Tara N. Sainath, Rohit Prabhavalkar, Takaaki Hori, 2023, ArXiv.

Deep Neural Networks for Acoustic Modeling in Speech Recognition

Tara N. Sainath, Brian Kingsbury, Geoffrey E. Hinton, 2012 .

Deep Learning for Audio Signal Processing

Tara N. Sainath, Bo Li, Hendrik Purwins, 2019, IEEE Journal of Selected Topics in Signal Processing.

Acoustic landmark detection and segmentation using the McAulay-Quatieri Sinusoidal Model

Tara N. Sainath, Tara N Sainath, 2005 .

Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages

Tara N. Sainath, Yonghui Wu, H. Soltau, 2023, ArXiv.

UML: A Universal Monolingual Output Layer for Multilingual ASR

Tara N. Sainath, Bo Li, Trevor Strohman, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Truly Multilingual First Pass and Monolingual Second Pass Streaming on-Device ASR System

Tara N. Sainath, Bo Li, Trevor Strohman, 2023, 2022 IEEE Spoken Language Technology Workshop (SLT).

A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale

Tara N. Sainath, Kyunghyun Cho, M. Picheny, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

JOIST: A Joint Speech and Text Streaming Model for ASR

Tara N. Sainath, Rohit Prabhavalkar, Bo Li, 2022, 2022 IEEE Spoken Language Technology Workshop (SLT).

Sentence-Select: Large-Scale Language Model Data Selection for Rare-Word Speech Recognition

Tara N. Sainath, T. Sainath, Trevor Strohman, 2022, INTERSPEECH.

Lookup-Table Recurrent Language Models for Long Tail Speech Recognition

Tara N. Sainath, David Rybach, Trevor Strohman, 2021, Interspeech.

Semi-supervised Training for End-to-end Models via Weak Distillation

Tara N. Sainath, Bo Li, Ruoming Pang, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling

Tara N. Sainath, Chung-Cheng Chiu, Ruoming Pang, 2020, ICLR.

A Comparison of End-to-End Models for Long-Form Speech Recognition

Tara N. Sainath, Arun Narayanan, Yonghui Wu, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition

Tara N. Sainath, Rohit Prabhavalkar, Bo Li, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Phoebe: Pronunciation-aware Contextualization for End-to-end Speech Recognition

Tara N. Sainath, Rohit Prabhavalkar, Golan Pundak, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Streaming On-Device End-To-End Model Surpassing Server-Side Conventional Model Quality and Latency

Tara N. Sainath, Z. Chen, Yonghui Wu, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Massively Multilingual ASR: A Lifelong Learning Solution

Tara N. Sainath, Trevor Strohman, Ruoming Pang, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Efficient Domain Adaptation for Speech Foundation Models

Tara N. Sainath, Zhouyuan Huo, F. Beaufays, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Turn-Taking Prediction for Natural Conversational Speech

Tara N. Sainath, Bo Li, Trevor Strohman, 2022, INTERSPEECH.

An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling

Tara N. Sainath, T. Sainath, C. Chiu, 2021, Interspeech.

Joint Endpointing and Decoding with End-to-end Models

Tara N. Sainath, Rohit Prabhavalkar, Tara N. Sainath, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Transducer-Based Streaming Deliberation for Cascaded Encoders

Tara N. Sainath, Trevor Strohman, Ruoming Pang, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Deliberation of Streaming RNN-Transducer by Non-Autoregressive Decoding pdf

Tara N. Sainath, Ke Hu, Tara Sainath, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Transformer Based Deliberation for Two-Pass Speech Recognition

Tara N. Sainath, Ke Hu, Ruoming Pang, 2021, 2021 IEEE Spoken Language Technology Workshop (SLT).

E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model

Tara N. Sainath, Rohit Prabhavalkar, David Rybach, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems

Tara N. Sainath, Bo Li, Yanzhang He, 2022, 2022 IEEE Spoken Language Technology Workshop (SLT).

E2E Segmenter: Joint Segmenting and Decoding for Long-Form ASR

Tara N. Sainath, Rohit Prabhavalkar, David Rybach, 2022, INTERSPEECH.

Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models

Tara N. Sainath, Steven M. Hernandez, Rohit Prabhavalkar, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Resource-Efficient Transfer Learning From Speech Foundation Model Using Hierarchical Feature Fusion

Tara N. Sainath, Bo Li, Zhouyuan Huo, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving The Latency And Quality Of Cascaded Encoders

Tara N. Sainath, Yonghui Wu, K. Choromanski, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Dual Learning for Large Vocabulary On-Device ASR

Tara N. Sainath, Rohit Prabhavalkar, W. R. Huang, 2023, 2022 IEEE Spoken Language Technology Workshop (SLT).

Scaling Up Deliberation For Multilingual ASR

Tara N. Sainath, Bo Li, Ke Hu, 2022, 2022 IEEE Spoken Language Technology Workshop (SLT).

Improving Rare Word Recognition with LM-aware MWER Training

Tara N. Sainath, B. Ramabhadran, Rohit Prabhavalkar, 2022, INTERSPEECH.

Improving Deliberation by Text-Only and Semi-Supervised Training

Tara N. Sainath, Rohit Prabhavalkar, Trevor Strohman, 2022, INTERSPEECH.

Context-Aware end-to-end ASR Using Self-Attentive Embedding and Tensor Fusion

Tara N. Sainath, Trevor Strohman, Shuo-yiin Chang, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Unified Cascaded Encoder ASR Model for Dynamic Model Sizes

Tara N. Sainath, Rohit Prabhavalkar, R. Panigrahy, 2022, INTERSPEECH.

Echo State Speech Recognition

Tara N. Sainath, Yu Zhang, Harsh Shrivastava, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Deep Neural Network Language Models

Tara N. Sainath, T. Sainath, Brian Kingsbury, 2012, WLM@NAACL-HLT.

Sparse representation features for speech recognition

Tara N. Sainath, D. Nahamoo, D. Kanevsky, 2010, INTERSPEECH.

Semantic Segmentation with Bidirectional Language Models Improves Long-form ASR

Tara N. Sainath, Hao Zhang, Shuo-yiin Chang, 2023, INTERSPEECH 2023.

AudioPaLM: A Large Language Model That Can Speak and Listen

Tara N. Sainath, Dalia El Badawy, Paul K. Rubenstein, 2023, ArXiv.

Deep convolutional neural networks for LVCSR

Tara N. Sainath, Abdel-rahman Mohamed, Brian Kingsbury, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Exemplar-Based Sparse Representation Features: From TIMIT to LVCSR

Tara N. Sainath, D. Nahamoo, T. N. Sainath, 2011, IEEE Transactions on Audio, Speech, and Language Processing.

Contextual Speech Recognition with Difficult Negative Training Examples

Tara N. Sainath, G. Pundak, Uri Alon, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Modular Domain Adaptation for Conformer-Based Streaming ASR

Tara N. Sainath, Tara N. Sainath, Bo Li, 2023, INTERSPEECH 2023.

Text Injection for Capitalization and Turn-Taking Prediction in Speech Models

Tara N. Sainath, Hao Zhang, Shuo-yiin Chang, 2023, INTERSPEECH 2023.

Multi-Output RNN-T Joint Networks for Multi-Task Learning of ASR and Auxiliary Tasks

Tara N. Sainath, David Rybach, Ian McGraw, 2023, IEEE International Conference on Acoustics, Speech, and Signal Processing.

JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition

Tara N. Sainath, B. Ramabhadran, Rohit Prabhavalkar, 2023, IEEE International Conference on Acoustics, Speech, and Signal Processing.

Top Downloads in IEEE Xplore [Reader's Choice]

Tara N. Sainath, Geoffrey E. Hinton, George E. Dahl, 2017, IEEE Signal Processing Magazine.

Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages

Tara N. Sainath, Yonghui Wu, H. Soltau, 2023, ArXiv.

Self-Supervised Speech Representation Learning: A Review

Tara N. Sainath, Jakob Drachmann Havtorn, Abdel-rahman Mohamed, 2022, IEEE Journal of Selected Topics in Signal Processing.

Gemini: A Family of Highly Capable Multimodal Models

Tara N. Sainath, Dalia El Badawy, Reinald Kim Amplayo, 2023, ArXiv.

How to Estimate Model Transferability of Pre-Trained Speech Models?

Tara N. Sainath, Rohit Prabhavalkar, Bo Li, 2023, INTERSPEECH 2023.