Michael L. Seltzer

ORCID

Publication Activity (10 Years)

Years Active: 2000-2024
Publications (10 Years): 71

Top Venues

Publications

Egor Lakomkin, Chunyang Wu, Yassir Fathullah, Ozlem Kalinli, Michael L. Seltzer, Christian Fuegen
End-to-End Speech Recognition Contextualization with Large Language Models. ICASSP (2024)
Suyoun Kim, Akshat Shrivastava, Duc Le, Ju Lin, Ozlem Kalinli, Michael L. Seltzer
Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding. CoRR (2023)
Andros Tjandra, Nayan Singhal, David Zhang, Ozlem Kalinli, Abdelrahman Mohamed, Duc Le, Michael L. Seltzer
Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities. ICASSP (2023)
Suyoun Kim, Akshat Shrivastava, Duc Le, Ju Lin, Ozlem Kalinli, Michael L. Seltzer
Modality Confidence Aware Training for Robust End-to-End Spoken Language Understanding. INTERSPEECH (2023)
Egor Lakomkin, Chunyang Wu, Yassir Fathullah, Ozlem Kalinli, Michael L. Seltzer, Christian Fuegen
End-to-End Speech Recognition Contextualization with Large Language Models. CoRR (2023)
Ke Li, Jay Mahadeokar, Jinxi Guo, Yangyang Shi, Gil Keren, Ozlem Kalinli, Michael L. Seltzer, Duc Le
Improving fast-slow Encoder based Transducer with Streaming Deliberation. ICASSP (2023)
Duc Le, Frank Seide, Yuhao Wang, Yang Li, Kjell Schubert, Ozlem Kalinli, Michael L. Seltzer
Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers. ICASSP (2023)
Roshan Sharma, Suyoun Kim, Daniel Lazar, Trang Le, Akshat Shrivastava, Kwanghoon Ahn, Piyush Kansal, Leda Sari, Ozlem Kalinli, Michael L. Seltzer
Augmenting text for spoken language understanding with Large Language Models. CoRR (2023)
Suyoun Kim, Duc Le, Weiyi Zheng, Tarun Singh, Abhinav Arora, Xiaoyu Zhai, Christian Fuegen, Ozlem Kalinli, Michael L. Seltzer
Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric. INTERSPEECH (2022)
Duc Le, Frank Seide, Yuhao Wang, Yang Li, Kjell Schubert, Ozlem Kalinli, Michael L. Seltzer
Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers. CoRR (2022)
Antoine Bruguier, Duc Le, Rohit Prabhavalkar, Dangna Li, Zhe Liu, Bo Wang, Eun Chang, Fuchun Peng, Ozlem Kalinli, Michael L. Seltzer
Neural-FST Class Language Model for End-to-End Speech Recognition. CoRR (2022)
Antoine Bruguier, Duc Le, Rohit Prabhavalkar, Dangna Li, Zhe Liu, Bo Wang, Eun Chang, Fuchun Peng, Ozlem Kalinli, Michael L. Seltzer
Neural-FST Class Language Model for End-to-End Speech Recognition. ICASSP (2022)
Duc Le, Akshat Shrivastava, Paden Tomasello, Suyoun Kim, Aleksandr Livshits, Ozlem Kalinli, Michael L. Seltzer
Deliberation Model for On-Device Spoken Language Understanding. CoRR (2022)
Jay Mahadeokar, Yangyang Shi, Ke Li, Duc Le, Jiedan Zhu, Vikas Chandra, Ozlem Kalinli, Michael L. Seltzer
Streaming parallel transducer beam search with fast slow cascaded encoders. INTERSPEECH (2022)
Jay Mahadeokar, Yangyang Shi, Ke Li, Duc Le, Jiedan Zhu, Vikas Chandra, Ozlem Kalinli, Michael L. Seltzer
Streaming parallel transducer beam search with fast-slow cascaded encoders. CoRR (2022)
Duc Le, Akshat Shrivastava, Paden D. Tomasello, Suyoun Kim, Aleksandr Livshits, Ozlem Kalinli, Michael L. Seltzer
Deliberation Model for On-Device Spoken Language Understanding. INTERSPEECH (2022)
Andros Tjandra, Nayan Singhal, David Zhang, Ozlem Kalinli, Abdelrahman Mohamed, Duc Le, Michael L. Seltzer
Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization Capabilities. CoRR (2022)
Jay Mahadeokar, Yangyang Shi, Yuan Shangguan, Chunyang Wu, Alex Xiao, Hang Su, Duc Le, Ozlem Kalinli, Christian Fuegen, Michael L. Seltzer
Flexi-Transducer: Optimizing Latency, Accuracy and Compute for Multi-Domain On-Device Scenarios. Interspeech (2021)
Suyoun Kim, Duc Le, Weiyi Zheng, Tarun Singh, Abhinav Arora, Xiaoyu Zhai, Christian Fuegen, Ozlem Kalinli, Michael L. Seltzer
Evaluating User Perception of Speech Recognition System Quality with Semantic Distance Metric. CoRR (2021)
Suyoun Kim, Abhinav Arora, Duc Le, Ching-Feng Yeh, Christian Fuegen, Ozlem Kalinli, Michael L. Seltzer
Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding. Interspeech (2021)
Duc Le, Mahaveer Jain, Gil Keren, Suyoun Kim, Yangyang Shi, Jay Mahadeokar, Julian Chan, Yuan Shangguan, Christian Fuegen, Ozlem Kalinli, Yatharth Saraf, Michael L. Seltzer
Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion. Interspeech (2021)
Varun Nagaraja, Yangyang Shi, Ganesh Venkatesh, Ozlem Kalinli, Michael L. Seltzer, Vikas Chandra
Collaborative Training of Acoustic Encoders for Speech Recognition. CoRR (2021)
Varun Nagaraja, Yangyang Shi, Ganesh Venkatesh, Ozlem Kalinli, Michael L. Seltzer, Vikas Chandra
Collaborative Training of Acoustic Encoders for Speech Recognition. Interspeech (2021)
Ganesh Venkatesh, Alagappan Valliappan, Jay Mahadeokar, Yuan Shangguan, Christian Fuegen, Michael L. Seltzer, Vikas Chandra
Memory-efficient Speech Recognition on Smart Devices. CoRR (2021)
Suyoun Kim, Abhinav Arora, Duc Le, Ching-Feng Yeh, Christian Fuegen, Ozlem Kalinli, Michael L. Seltzer
Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding. CoRR (2021)
Duc Le, Mahaveer Jain, Gil Keren, Suyoun Kim, Yangyang Shi, Jay Mahadeokar, Julian Chan, Yuan Shangguan, Christian Fuegen, Ozlem Kalinli, Yatharth Saraf, Michael L. Seltzer
Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion. CoRR (2021)
Ching-Feng Yeh, Yongqiang Wang, Yangyang Shi, Chunyang Wu, Frank Zhang, Julian Chan, Michael L. Seltzer
Streaming Attention-Based Models with Augmented Memory for End-To-End Speech Recognition. SLT (2021)
Yangyang Shi, Varun Nagaraja, Chunyang Wu, Jay Mahadeokar, Duc Le, Rohit Prabhavalkar, Alex Xiao, Ching-Feng Yeh, Julian Chan, Christian Fuegen, Ozlem Kalinli, Michael L. Seltzer
Dynamic Encoder Transducer: A Flexible Solution for Trading Off Accuracy for Latency. Interspeech (2021)
Yuan Shangguan, Rohit Prabhavalkar, Hang Su, Jay Mahadeokar, Yangyang Shi, Jiatong Zhou, Chunyang Wu, Duc Le, Ozlem Kalinli, Christian Fuegen, Michael L. Seltzer
Dissecting User-Perceived Latency of On-Device E2E Speech Recognition. Interspeech (2021)
Jay Mahadeokar, Yangyang Shi, Yuan Shangguan, Chunyang Wu, Alex Xiao, Hang Su, Duc Le, Ozlem Kalinli, Christian Fuegen, Michael L. Seltzer
Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios. CoRR (2021)
Suyoun Kim, Yuan Shangguan, Jay Mahadeokar, Antoine Bruguier, Christian Fuegen, Michael L. Seltzer, Duc Le
Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer. ICASSP (2021)
Duc Le, Gil Keren, Julian Chan, Jay Mahadeokar, Christian Fuegen, Michael L. Seltzer
Deep Shallow Fusion for RNN-T Personalization. SLT (2021)
Ganesh Venkatesh, Alagappan Valliappan, Jay Mahadeokar, Yuan Shangguan, Christian Fuegen, Michael L. Seltzer, Vikas Chandra
Memory-Efficient Speech Recognition on Smart Devices. ICASSP (2021)
Jay Mahadeokar, Yuan Shangguan, Duc Le, Gil Keren, Hang Su, Thong Le, Ching-Feng Yeh, Christian Fuegen, Michael L. Seltzer
Alignment Restricted Streaming Recurrent Neural Network Transducer. SLT (2021)
Yuan Shangguan, Rohit Prabhavalkar, Hang Su, Jay Mahadeokar, Yangyang Shi, Jiatong Zhou, Chunyang Wu, Duc Le, Ozlem Kalinli, Christian Fuegen, Michael L. Seltzer
Dissecting User-Perceived Latency of On-Device E2E Speech Recognition. CoRR (2021)
Yangyang Shi, Varun Nagaraja, Chunyang Wu, Jay Mahadeokar, Duc Le, Rohit Prabhavalkar, Alex Xiao, Ching-Feng Yeh, Julian Chan, Christian Fuegen, Ozlem Kalinli, Michael L. Seltzer
Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency. CoRR (2021)
Duc Le, Thilo Köhler, Christian Fuegen, Michael L. Seltzer
G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR. ICASSP (2020)
Yi-Chen Chen, Zhaojun Yang, Ching-Feng Yeh, Mahaveer Jain, Michael L. Seltzer
Aipnet: Generative Adversarial Pre-Training of Accent-Invariant Networks for End-To-End Speech Recognition. ICASSP (2020)
Yangyang Shi, Yongqiang Wang, Chunyang Wu, Ching-Feng Yeh, Julian Chan, Frank Zhang, Duc Le, Michael L. Seltzer
Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition. CoRR (2020)
Yangyang Shi, Yongqiang Wang, Chunyang Wu, Christian Fuegen, Frank Zhang, Duc Le, Ching-Feng Yeh, Michael L. Seltzer
Weak-Attention Suppression for Transformer Based Speech Recognition. INTERSPEECH (2020)
Yangyang Shi, Yongqiang Wang, Chunyang Wu, Christian Fuegen, Frank Zhang, Duc Le, Ching-Feng Yeh, Michael L. Seltzer
Weak-Attention Suppression For Transformer Based Speech Recognition. CoRR (2020)
Ching-Feng Yeh, Yongqiang Wang, Yangyang Shi, Chunyang Wu, Frank Zhang, Julian Chan, Michael L. Seltzer
Streaming Attention-Based Models with Augmented Memory for End-to-End Speech Recognition. CoRR (2020)
Yongqiang Wang, Abdelrahman Mohamed, Duc Le, Chunxi Liu, Alex Xiao, Jay Mahadeokar, Hongzhao Huang, Andros Tjandra, Xiaohui Zhang, Frank Zhang, Christian Fuegen, Geoffrey Zweig, Michael L. Seltzer
Transformer-Based Acoustic Modeling for Hybrid Speech Recognition. ICASSP (2020)
Jay Mahadeokar, Yuan Shangguan, Duc Le, Gil Keren, Hang Su, Thong Le, Ching-Feng Yeh, Christian Fuegen, Michael L. Seltzer
Alignment Restricted Streaming Recurrent Neural Network Transducer. CoRR (2020)
Duc Le, Gil Keren, Julian Chan, Jay Mahadeokar, Christian Fuegen, Michael L. Seltzer
Deep Shallow Fusion for RNN-T Personalization. CoRR (2020)
Suyoun Kim, Yuan Shangguan, Jay Mahadeokar, Antoine Bruguier, Christian Fuegen, Michael L. Seltzer, Duc Le
Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer. CoRR (2020)
Mahaveer Jain, Kjell Schubert, Jay Mahadeokar, Ching-Feng Yeh, Kaustubh Kalgaonkar, Anuroop Sriram, Christian Fuegen, Michael L. Seltzer
RNN-T For Latency Controlled ASR With Improved Beam Search. CoRR (2019)
Duc Le, Xiaohui Zhang, Weiyi Zheng, Christian Fügen, Geoffrey Zweig, Michael L. Seltzer
From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition. ASRU (2019)
Zhehuai Chen, Mahaveer Jain, Yongqiang Wang, Michael L. Seltzer, Christian Fuegen
Joint Grapheme and Phoneme Embeddings for Contextual End-to-End ASR. INTERSPEECH (2019)
Reinhold Haeb-Umbach, Shinji Watanabe, Tomohiro Nakatani, Michiel Bacchiani, Björn Hoffmeister, Michael L. Seltzer, Heiga Zen, Mehrez Souden
Speech Processing for Digital Home Assistants: Combining signal processing with deep-learning techniques. IEEE Signal Process. Mag. 36 (6) (2019)
Duc Le, Thilo Köhler, Christian Fuegen, Michael L. Seltzer
G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR. CoRR (2019)
Yi-Chen Chen, Zhaojun Yang, Ching-Feng Yeh, Mahaveer Jain, Michael L. Seltzer
AIPNet: Generative Adversarial Pre-training of Accent-invariant Networks for End-to-end Speech Recognition. CoRR (2019)
Ching-Feng Yeh, Jay Mahadeokar, Kaustubh Kalgaonkar, Yongqiang Wang, Duc Le, Mahaveer Jain, Kjell Schubert, Christian Fuegen, Michael L. Seltzer
Transformer-Transducer: End-to-End Speech Recognition with Self-Attention. CoRR (2019)
Yongqiang Wang, Abdelrahman Mohamed, Duc Le, Chunxi Liu, Alex Xiao, Jay Mahadeokar, Hongzhao Huang, Andros Tjandra, Xiaohui Zhang, Frank Zhang, Christian Fuegen, Geoffrey Zweig, Michael L. Seltzer
Transformer-based Acoustic Modeling for Hybrid Speech Recognition. CoRR (2019)
Zhehuai Chen, Mahaveer Jain, Yongqiang Wang, Michael L. Seltzer, Christian Fuegen
End-to-end Contextual Speech Recognition Using Class Language Models and a Token Passing Decoder. ICASSP (2019)
Duc Le, Xiaohui Zhang, Weiyi Zheng, Christian Fügen, Geoffrey Zweig, Michael L. Seltzer
From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition. CoRR (2019)
Shinji Watanabe, Shoko Araki, Michiel Bacchiani, Reinhold Haeb-Umbach, Michael L. Seltzer
Introduction to the Issue on Far-Field Speech Processing in the Era of Deep Learning: Speech Enhancement, Separation, and Recognition. IEEE J. Sel. Top. Signal Process. 13 (4) (2019)
Zhehuai Chen, Mahaveer Jain, Yongqiang Wang, Michael L. Seltzer, Christian Fuegen
End-to-end contextual speech recognition using class language models and a token passing decoder. CoRR (2018)
Suyoun Kim, Michael L. Seltzer
Towards Language-Universal End-to-End Speech Recognition. ICASSP (2018)
Suyoun Kim, Michael L. Seltzer, Jinyu Li, Rui Zhao
Improved Training for Online End-to-end Speech Recognition Systems. INTERSPEECH (2018)
Zhuo Chen, Takuya Yoshioka, Xiong Xiao, Linyu Li, Michael L. Seltzer, Yifan Gong
Efficient Integration of Fixed Beamformers and Speech Separation Networks for Multi-Channel Far-Field Speech Separation. ICASSP (2018)
Baolin Peng, Michael L. Seltzer, Y. C. Ju, Geoffrey Zweig, Kam-Fai Wong
May I take your order? A Neural Model for Extracting Structured Information from Conversations. EACL (1) (2017)
Suyoun Kim, Michael L. Seltzer, Jinyu Li, Rui Zhao
Improved training for online end-to-end speech recognition systems. CoRR (2017)
Tom Ko, Vijayaditya Peddinti, Daniel Povey, Michael L. Seltzer, Sanjeev Khudanpur
A study on data augmentation of reverberant speech for robust speech recognition. ICASSP (2017)
Wayne Xiong, Jasha Droppo, Xuedong Huang, Frank Seide, Michael L. Seltzer, Andreas Stolcke, Dong Yu, Geoffrey Zweig
Toward Human Parity in Conversational Speech Recognition. IEEE ACM Trans. Audio Speech Lang. Process. 25 (12) (2017)
Jinyu Li, Michael L. Seltzer, Xi Wang, Rui Zhao, Yifan Gong
Large-Scale Domain Adaptation via Teacher-Student Learning. CoRR (2017)
Suyoun Kim, Michael L. Seltzer
Towards Language-Universal End-to-End Speech Recognition. CoRR (2017)
Jinyu Li, Michael L. Seltzer, Xi Wang, Rui Zhao, Yifan Gong
Large-Scale Domain Adaptation via Teacher-Student Learning. INTERSPEECH (2017)
Tasha Nagamine, Michael L. Seltzer, Nima Mesgarani
On the Role of Nonlinear Transformations in Deep Neural Network Acoustic Models. INTERSPEECH (2016)
Xiong Xiao, Shinji Watanabe, Hakan Erdogan, Liang Lu, John R. Hershey, Michael L. Seltzer, Guoguo Chen, Yu Zhang, Michael I. Mandel, Dong Yu
Deep beamforming networks for multi-channel speech recognition. ICASSP (2016)
Pegah Ghahremani, Jasha Droppo, Michael L. Seltzer
Linearly augmented deep neural network. ICASSP (2016)
Tasha Nagamine, Michael L. Seltzer, Nima Mesgarani
Exploring how deep neural networks form phonemic categories. INTERSPEECH (2015)
Yu Zhang, Dong Yu, Michael L. Seltzer, Jasha Droppo
Speech recognition with prediction-adaptation-correction recurrent neural networks. ICASSP (2015)
Ritwik Giri, Michael L. Seltzer, Jasha Droppo, Dong Yu
Improving speech recognition in reverberation using a room-aware deep neural network and multi-task learning. ICASSP (2015)
Chao Weng, Dong Yu, Michael L. Seltzer, Jasha Droppo
Deep Neural Networks for Single-Channel Multi-Talker Speech Recognition. IEEE ACM Trans. Audio Speech Lang. Process. 23 (10) (2015)
Yan Huang, Malcolm Slaney, Michael L. Seltzer, Yifan Gong
Towards better performance with heterogeneous training data in acoustic modeling using deep neural networks. INTERSPEECH (2014)
Hyunson Seo, Hong-Goo Kang, Michael L. Seltzer
Factored adaptation of speaker and environment using orthogonal subspace transforms. ICASSP (2014)
Dong Yu, Adam Eversole, Michael L. Seltzer, Kaisheng Yao, Brian Guenter, Oleksii Kuchaiev, Frank Seide, Huaming Wang, Jasha Droppo, Zhiheng Huang, Geoffrey Zweig, Christopher J. Rossbach, Jon Currey
An introduction to computational networks and the computational network toolkit (invited talk). INTERSPEECH (2014)
Malcolm Slaney, Michael L. Seltzer
The influence of pitch and noise on the discriminability of filterbank features. INTERSPEECH (2014)
Chao Weng, Dong Yu, Michael L. Seltzer, Jasha Droppo
Single-channel mixed speech recognition using deep neural networks. ICASSP (2014)
Dong Yu, Michael L. Seltzer, Jinyu Li, Jui-Ting Huang, Frank Seide
Feature Learning in Deep Neural Networks - A Study on Speech Recognition Tasks ICLR (2013)
Michael L. Seltzer, Dong Yu, Yongqiang Wang
An investigation of deep neural networks for noise robust speech recognition. ICASSP (2013)
Michael L. Seltzer, Jasha Droppo
Multi-task learning in deep neural networks for improved phoneme recognition. ICASSP (2013)
Samuel Thomas, Michael L. Seltzer, Kenneth Church, Hynek Hermansky
Deep neural network features and semi-supervised training for low resource speech recognition. ICASSP (2013)
Li Deng, Jinyu Li, Jui-Ting Huang, Kaisheng Yao, Dong Yu, Frank Seide, Michael L. Seltzer, Geoffrey Zweig, Xiaodong He, Jason D. Williams, Yifan Gong, Alex Acero
Recent advances in deep learning for speech research at Microsoft. ICASSP (2013)
Jinyu Li, Michael L. Seltzer, Yifan Gong
Improvements to VTS feature enhancement. ICASSP (2012)
Michael L. Seltzer, Alex Acero
Factored adaptation using a combination of feature-space and model-space transforms. INTERSPEECH (2012)
Jinyu Li, Michael L. Seltzer, Yifan Gong
Efficient VTS Adaptation Using Jacobian Approximation. INTERSPEECH (2012)
Flavio P. Ribeiro, Dinei A. F. Florêncio, Cha Zhang, Michael L. Seltzer
CROWDMOS: An approach for crowdsourcing mean opinion score studies. ICASSP (2011)
Dong Yu, Michael L. Seltzer
Improved Bottleneck Features Using Pretrained Deep Neural Networks. INTERSPEECH (2011)
Michael L. Seltzer, Alex Acero
Separating Speaker and Environmental Variability Using Factored Transforms. INTERSPEECH (2011)
Michael L. Seltzer, Alex Acero
Factored adaptation for separable compensation of speaker and environmental variability. ASRU (2011)
Michael L. Seltzer, Yun-Cheng Ju, Ivan Tashev, Ye-Yi Wang, Dong Yu
In-Car Media Search. IEEE Signal Process. Mag. 28 (4) (2011)
Xing Fan, Michael L. Seltzer, Jasha Droppo, Henrique S. Malvar, Alex Acero
Joint encoding of the waveform and speech recognition features using a transform codec. ICASSP (2011)
Michael L. Seltzer, Alex Acero
HMM adaptation using linear spline interpolation with integrated spline parameter training for robust speech recognition. INTERSPEECH (2010)
Ozlem Kalinli, Michael L. Seltzer, Jasha Droppo, Alex Acero
Noise Adaptive Training for Robust Automatic Speech Recognition. IEEE Trans. Speech Audio Process. 18 (8) (2010)
Michael L. Seltzer, Alex Acero, Kaustubh Kalgaonkar
Acoustic model adaptation via Linear Spline Interpolation for robust speech recognition. ICASSP (2010)
Li Deng, Michael L. Seltzer, Dong Yu, Alex Acero, Abdel-rahman Mohamed, Geoffrey E. Hinton
Binary coding of speech spectrograms using a deep auto-encoder. INTERSPEECH (2010)
Kaustubh Kalgaonkar, Michael L. Seltzer, Alex Acero
Noise robust model adaptation using linear spline interpolation. ASRU (2009)
Michael L. Seltzer, Lei Zhang
The data deluge: Challenges and opportunities of unlimited data in statistical signal processing. ICASSP (2009)

Michael L. Seltzer.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Michael L. Seltzer