M. Seltzer

发表

Recent advances in deep learning for speech research at Microsoft

Geoffrey Zweig, Kaisheng Yao, Yifan Gong, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

An introduction to computational networks and the computational network toolkit (invited talk)

Geoffrey Zweig, Kaisheng Yao, Dong Yu, 2014, INTERSPEECH.

Binary coding of speech spectrograms using a deep auto-encoder

Geoffrey E. Hinton, Dong Yu, Li Deng, 2010, INTERSPEECH.

Improved Bottleneck Features Using Pretrained Deep Neural Networks

Dong Yu, Michael L. Seltzer, Dong Yu, 2011, INTERSPEECH.

Feature Learning in Deep Neural Networks - Studies on Speech Recognition Tasks.

Jinyu Li, Dong Yu, Jui-Ting Huang, 2013, ICLR 2013.

An investigation of deep neural networks for noise robust speech recognition

Yongqiang Wang, Dong Yu, Michael L. Seltzer, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Toward Human Parity in Conversational Speech Recognition

Geoffrey Zweig, Andreas Stolcke, Dong Yu, 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Noise Adaptive Training for Robust Automatic Speech Recognition

Alex Acero, Jasha Droppo, Ozlem Kalinli, 2010, IEEE Transactions on Audio, Speech, and Language Processing.

Phone sequence modeling with recurrent neural networks

Dong Yu, Jasha Droppo, Nicolas Boulanger-Lewandowski, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving speech recognition in reverberation using a room-aware deep neural network and multi-task learning

Jasha Droppo, Ritwik Giri, Dong Yu, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multi-task learning in deep neural networks for improved phoneme recognition

Jasha Droppo, Michael L. Seltzer, J. Droppo, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Towards a non-parametric acoustic model: an acoustic decision tree for observation probability calculation

Alex Acero, Jasha Droppo, Yu-Hsiang Bosco Chiu, 2008, INTERSPEECH.

Robust bandwidth extension of noise-corrupted narrowband speech

Alex Acero, Jasha Droppo, Michael L. Seltzer, 2005, INTERSPEECH.

Single-channel mixed speech recognition using deep neural networks

Dong Yu, Chao Weng, Jasha Droppo, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Robust design of wideband loudspeaker arrays

Alex Acero, Jasha Droppo, Ivan Tashev, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

A summary of the 2012 JHU CLSP workshop on zero resource speech technologies and models of early language acquisition

Kenneth Ward Church, Florian Metze, Aren Jansen, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Reconstruction of missing features for robust speech recognition

Richard M. Stern, Bhiksha Raj, Michael L. Seltzer, 2004, Speech Commun..

Speech recognizer-based microphone array processing for robust hands-free speech recognition

Richard M. Stern, Bhiksha Raj, Michael L. Seltzer, 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Speech Processing for Digital Home Assistants

Heiga Zen, Shinji Watanabe, Tomohiro Nakatani, 2019 .

Detection of Corrupted Speech Features for Robust Speech Recognition

Michael L. Seltzer, Mike Seltzer, M. Seltzer, 2000 .

Robust speech recognition using cepstral minimum-mean-square-error noise suppressor

Yifan Gong, Dong Yu, Alex Acero, 2008 .

ReLU, Sigmoid, Tanh, Log, Cos, Dropout, Negate, Softmax, LogSoftmax, SumElements, RowSlice, RowStack, Scale, Times, DiagTimes, Plus, Minus, ElementTimes, KhatriRaoProd- uct, Reshape traInIng crIterIa SquareError, CrossEntropyWithSoftmax, ClassificationError, ClassBasedCrossEntropyWith- SoftMax, GMML

Clément Farabet, Koray Kavukcuoglu, Ronan Collobert, 2015 .

Robust speech recognition using missing features

Richard M. Stern, Bhiksha Raj, Michael L. Seltzer, 2003 .

On the Role of Nonlinear Transformations in Deep Neural Network Acoustic Models

Tasha Nagamine, Nima Mesgarani, Michael L. Seltzer, 2016, INTERSPEECH.

Achieving Human Parity in Conversational Speech Recognition pdf

Geoffrey Zweig, Andreas Stolcke, Dong Yu, 2016, ArXiv.

End-to-end Contextual Speech Recognition Using Class Language Models and a Token Passing Decoder

Yongqiang Wang, Zhehuai Chen, Christian Fuegen, 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

The data deluge: Challenges and opportunities of unlimited data in statistical signal processing

Lei Zhang, Michael L. Seltzer, Lei Zhang, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

A study on data augmentation of reverberant speech for robust speech recognition

Sanjeev Khudanpur, Daniel Povey, Tom Ko, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

AUTOMATIC DETECTION OF CORRUPT SPECTROGRAPHIC FEATURES FOR ROBUST SPEECH RECOGNITION

Michael L. Seltzer, M. Seltzer, 2000 .

Singular value decomposition based low-footprint speaker adaptation and personalization for deep neural network

Yifan Gong, Jinyu Li, Jian Xue, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Bayesian classifier for spectrographic mask estimation for missing feature speech recognition

Richard M. Stern, Bhiksha Raj, Michael L. Seltzer, 2004, Speech Commun..

Likelihood-maximizing beamforming for robust hands-free speech recognition

Richard M. Stern, Bhiksha Raj, Michael L. Seltzer, 2004, IEEE Transactions on Speech and Audio Processing.

Exploring how deep neural networks form phonemic categories

Tasha Nagamine, Nima Mesgarani, Michael L. Seltzer, 2015, INTERSPEECH.

Data Driven Beamformer Design for Binaural Headset

Ivan Tashev, Michael L. Seltzer, M. Seltzer, 2008 .

Microphone Array Post-Filter using Incremental Bayes Learning to Track the Spatial Distributions of Speech and Noise

Alex Acero, Ivan Tashev, Michael L. Seltzer, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Commute UX: Voice Enabled In-car Infotainment System

Alex Acero, Ye-Yi Wang, Ivan Tashev, 2009 .

Towards Language-Universal End-to-End Speech Recognition

Suyoun Kim, Michael L. Seltzer, M. Seltzer, 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Deep neural network features and semi-supervised training for low resource speech recognition

Kenneth Ward Church, Hynek Hermansky, Samuel Thomas, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

CROWDMOS: An approach for crowdsourcing mean opinion score studies

Cha Zhang, Dinei A. F. Florêncio, Michael L. Seltzer, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

On Lattice-Free Boosted MMI Training of HMM and CTC-Based Full-Context ASR Models pdf

Frank Zhang, Julian Chan, Fuchun Peng, 2021, 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition

Geoffrey Zweig, Xiaohui Zhang, Weiyi Zheng, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Emformer: Efficient Memory Transformer Based Acoustic Model for Low Latency Streaming Speech Recognition

M. Seltzer, Duc Le, Ching-feng Yeh, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Joint Grapheme and Phoneme Embeddings for Contextual End-to-End ASR

Yongqiang Wang, Zhehuai Chen, Christian Fuegen, 2019, INTERSPEECH.

Transformer-Transducer: End-to-End Speech Recognition with Self-Attention pdf

Kjell Schubert, Kaustubh Kalgaonkar, Yongqiang Wang, 2019, ArXiv.

Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities

M. Seltzer, Ozlem Kalinli, Andros Tjandra, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion

M. Seltzer, Ozlem Kalinli, Yatharth Saraf, 2021, Interspeech.

Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer pdf

Jay Mahadeokar, Christian Fuegen, Suyoun Kim, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Transformer-Based Acoustic Modeling for Hybrid Speech Recognition

M. Seltzer, G. Zweig, Xiaohui Zhang, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR

M. Seltzer, Duc Le, Christian Fuegen, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Large-Scale Domain Adaptation via Teacher-Student Learning pdf

Yifan Gong, Jinyu Li, Xi Wang, 2017, INTERSPEECH.

Alignment Restricted Streaming Recurrent Neural Network Transducer pdf

Hang Su, Gil Keren, Jay Mahadeokar, 2020, 2021 IEEE Spoken Language Technology Workshop (SLT).

Deep Shallow Fusion for RNN-T Personalization pdf

Gil Keren, Jay Mahadeokar, Christian Fuegen, 2020, 2021 IEEE Spoken Language Technology Workshop (SLT).

Collaborative Training of Acoustic Encoders for Speech Recognition pdf

Vikas Chandra, Ozlem Kalinli, Ganesh Venkatesh, 2021, Interspeech.

Streaming parallel transducer beam search with fast-slow cascaded encoders

M. Seltzer, V. Chandra, Ozlem Kalinli, 2022, INTERSPEECH.

Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency pdf

Julian Chan, Ching-Feng Yeh, Rohit Prabhavalkar, 2021, Interspeech.

Dissecting User-Perceived Latency of On-Device E2E Speech Recognition pdf

Rohit Prabhavalkar, Ozlem Kalinli, Duc Le, 2021, Interspeech.

Streaming Transformer Transducer based Speech Recognition Using Non-Causal Convolution pdf

Dilin Wang, Ozlem Kalinli, Jay Mahadeokar, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Memory-Efficient Speech Recognition on Smart Devices

M. Seltzer, Ganesh Venkatesh, V. Chandra, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Deliberation Model for On-Device Spoken Language Understanding

M. Seltzer, Ozlem Kalinli, Paden Tomasello, 2022, INTERSPEECH.

Speech Processing for Digital Home Assistants: Combining signal processing with deep-learning techniques

Heiga Zen, Shinji Watanabe, Tomohiro Nakatani, 2019, IEEE Signal Processing Magazine.

Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding pdf

Ching-Feng Yeh, Ozlem Kalinli, Duc Le, 2021, Interspeech.

Improving fast-slow Encoder based Transducer with Streaming Deliberation

M. Seltzer, Ozlem Kalinli, Ke Li, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

RNN-T For Latency Controlled ASR With Improved Beam Search

M. Seltzer, Anuroop Sriram, Jay Mahadeokar, 2019, ArXiv.

Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios pdf

Ozlem Kalinli, Duc Le, Chunyang Wu, 2021, Interspeech.

Efficient Integration of Fixed Beamformers and Speech Separation Networks for Multi-Channel Far-Field Speech Separation

Xiong Xiao, Yifan Gong, Takuya Yoshioka, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improved training for online end-to-end speech recognition systems pdf

Jinyu Li, Rui Zhao, Suyoun Kim, 2017, INTERSPEECH.

The microsoft 2016 conversational speech recognition system

Geoffrey Zweig, Andreas Stolcke, Dong Yu, 2016, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Transferring Voice Knowledge for Acoustic Event Detection: An Empirical Study pdf

Edison Thomaz, Ozlem Kalinli, Yangyang Shi, 2021, ArXiv.

Speech Separation by Humans and Machines

Bhiksha Raj, Michael L. Seltzer, Manuel Reyes-Gomez, 2004 .

Weak-Attention Suppression For Transformer Based Speech Recognition

Yongqiang Wang, Chunyang Wu, Christian Fuegen, 2020, INTERSPEECH.

Dynamic Speech Endpoint Detection with Regression Targets

M. Seltzer, Hang Su, Edison Thomaz, 2022, IEEE International Conference on Acoustics, Speech, and Signal Processing.

Prompting Large Language Models with Speech Recognition Abilities

M. Seltzer, Ozlem Kalinli, J. Jia, 2023, ArXiv.

Aipnet: Generative Adversarial Pre-Training of Accent-Invariant Networks for End-To-End Speech Recognition

Ching-Feng Yeh, Zhaojun Yang, Michael L. Seltzer, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Feature Learning in Deep Neural Networks - A Study on Speech Recognition Tasks pdf

Dong Yu, Jui-Ting Huang, Frank Seide, 2013, ICLR.

Acoustic model adaptation via Linear Spline Interpolation for robust speech recognition

Alex Acero, Kaustubh Kalgaonkar, Michael L. Seltzer, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Microphone array processing for robust speech recognition

Richard M. Stern, Michael L. Seltzer, M. Seltzer, 2003 .

Deep beamforming networks for multi-channel speech recognition

Liang Lu, Xiong Xiao, Yu Zhang, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech in Noisy Environments: robust automatic segmentation, feature extraction, and hypothesis combination

Richard M. Stern, Bhiksha Raj, Rita Singh, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

End-to-End Speech Recognition Contextualization with Large Language Models

M. Seltzer, Ozlem Kalinli, Christian Fuegen, 2023, ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Maximum a posteriori ICA: Applying prior knowledge to the separation of acoustic sources

Alex Acero, Graham W. Taylor, Michael L. Seltzer, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

A Bayesian classifier for spectrographic mask estimation for missing feature speech recognition

M. Seltzer, B. Raj, R. Stern, 2004, Speech Commun..