Jay Mahadeokar

71 papers A* 1A 9C 2Misc 17Journal 37Unranked 5

Year	Rank	Type	Title / Venue / Authors
2025	Misc	`conf`	CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR. ICASSP Wei Zhou, Junteng Jia, Leda Sari, Jay Mahadeokar, Ozlem Kalinli
2025	J	`jnl`	Can Speech LLMs Think while Listening? CoRR Yi-Jen Shih, Desh Raj, Chunyang Wu, Wei Zhou, SK Bong, Yashesh Gaur, Jay Mahadeokar, Ozlem Kalinli, Mike Seltzer
2025	Misc	`conf`	Efficient Streaming LLM for Speech Recognition. ICASSP Junteng Jia, Gil Keren, Wei Zhou, Egor Lakomkin, Xiaohui Zhang, Chunyang Wu, Frank Seide, Jay Mahadeokar, Ozlem Kalinli
2025	Misc	`conf`	Faster Speech-LLaMA Inference with Multi-token Prediction. ICASSP Desh Raj, Gil Keren, Junteng Jia, Jay Mahadeokar, Ozlem Kalinli
2025	A	`conf`	Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech. INTERSPEECH Wonjune Kang, Junteng Jia, Chunyang Wu, Wei Zhou, Egor Lakomkin, Yashesh Gaur, Leda Sari, Suyoun Kim, Ke Li, Jay Mahadeokar, Ozlem Kalinli
2025	Misc	`conf`	M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses. ICASSP Yufeng Yang, Desh Raj, Ju Lin, Niko Moritz, Junteng Jia, Gil Keren, Egor Lakomkin, Yiteng Huang, Jacob Donley, Jay Mahadeokar, Ozlem Kalinli
2025	Misc	`conf`	Speech-N-LlaMA: Improving Speech LLMs with Multi-Pass Training. ICASSP Amit Kumar Singh Yadav, Gil Keren, Desh Raj, Wei Zhou, Junteng Jia, Ke Li, Ying Xu, Chunyang Wu, Jay Mahadeokar, Ozlem Kalinli
2024	—	`conf`	AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs. NAACL-HLT Yassir Fathullah, Chunyang Wu, Egor Lakomkin, Ke Li, Junteng Jia, Yuan Shangguan, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer
2024	J	`jnl`	CJST: CTC Compressor based Joint Speech and Text Training for Decoder-Only ASR. CoRR Wei Zhou, Junteng Jia, Leda Sari, Jay Mahadeokar, Ozlem Kalinli
2024	Misc	`conf`	Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of a Multilingual ASR Model. ICASSP Jiamin Xie, Ke Li, Jinxi Guo, Andros Tjandra, Yuan Shangguan, Leda Sari, Chunyang Wu, Junteng Jia, Jay Mahadeokar, Ozlem Kalinli
2024	Misc	`conf`	Effective Internal Language Model Training and Fusion for Factorized Transducer Model. ICASSP Jinxi Guo, Niko Moritz, Yingyi Ma, Frank Seide, Chunyang Wu, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer
2024	J	`jnl`	Effective internal language model training and fusion for factorized transducer model. CoRR Jinxi Guo, Niko Moritz, Yingyi Ma, Frank Seide, Chunyang Wu, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer
2024	J	`jnl`	Efficient Streaming LLM for Speech Recognition. CoRR Junteng Jia, Gil Keren, Wei Zhou, Egor Lakomkin, Xiaohui Zhang, Chunyang Wu, Frank Seide, Jay Mahadeokar, Ozlem Kalinli
2024	J	`jnl`	Faster Speech-LLaMA Inference with Multi-token Prediction. CoRR Desh Raj, Gil Keren, Junteng Jia, Jay Mahadeokar, Ozlem Kalinli
2024	J	`jnl`	Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech. CoRR Wonjune Kang, Junteng Jia, Chunyang Wu, Wei Zhou, Egor Lakomkin, Yashesh Gaur, Leda Sari, Suyoun Kim, Ke Li, Jay Mahadeokar, Ozlem Kalinli
2024	J	`jnl`	M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses. CoRR Yufeng Yang, Desh Raj, Ju Lin, Niko Moritz, Junteng Jia, Gil Keren, Egor Lakomkin, Yiteng Huang, Jacob Donley, Jay Mahadeokar, Ozlem Kalinli
2024	Misc	`conf`	Prompting Large Language Models with Speech Recognition Abilities. ICASSP Yassir Fathullah, Chunyang Wu, Egor Lakomkin, Junteng Jia, Yuan Shangguan, Ke Li, Jinxi Guo, Wenhan Xiong, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer
2024	Misc	`conf`	TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-Device ASR Models. ICASSP Yuan Shangguan, Haichuan Yang, Danni Li, Chunyang Wu, Yassir Fathullah, Dilin Wang, Ayushi Dalmia, Raghuraman Krishnamoorthi, Ozlem Kalinli, Junteng Jia, Jay Mahadeokar, Xin Lei, Mike Seltzer, Vikas Chandra
2024	J	`jnl`	Towards scalable efficient on-device ASR with transfer learning. CoRR Laxmi Pandey, Ke Li, Jinxi Guo, Debjyoti Paul, Arthur Guo, Jay Mahadeokar, Xuedong Zhang
2023	Misc	`conf`	Anchored Speech Recognition with Neural Transducers. ICASSP Desh Raj, Junteng Jia, Jay Mahadeokar, Chunyang Wu, Niko Moritz, Xiaohui Zhang, Ozlem Kalinli
2023	J	`jnl`	Dynamic ASR Pathways: An Adaptive Masking Approach Towards Efficient Pruning of A Multilingual ASR Model. CoRR Jiamin Xie, Ke Li, Jinxi Guo, Andros Tjandra, Yuan Shangguan, Leda Sari, Chunyang Wu, Junteng Jia, Jay Mahadeokar, Ozlem Kalinli
2023	Misc	`conf`	Dynamic Speech Endpoint Detection with Regression Targets. ICASSP Dawei Liang, Hang Su, Tarun Singh, Jay Mahadeokar, Shanil Puri, Jiedan Zhu, Edison Thomaz, Mike Seltzer
2023	Misc	`conf`	Improving fast-slow Encoder based Transducer with Streaming Deliberation. ICASSP Ke Li, Jay Mahadeokar, Jinxi Guo, Yangyang Shi, Gil Keren, Ozlem Kalinli, Michael L. Seltzer, Duc Le
2023	C	`conf`	Joint Federated Learning and Personalization for on-Device ASR. ASRU Junteng Jia, Ke Li, Mani Malek, Kshitiz Malik, Jay Mahadeokar, Ozlem Kalinli, Frank Seide
2023	A	`conf`	Multi-Head State Space Model for Speech Recognition. INTERSPEECH Yassir Fathullah, Chunyang Wu, Yuan Shangguan, Junteng Jia, Wenhan Xiong, Jay Mahadeokar, Chunxi Liu, Yangyang Shi, Ozlem Kalinli, Mike Seltzer, Mark J. F. Gales
2023	J	`jnl`	Multi-Head State Space Model for Speech Recognition. CoRR Yassir Fathullah, Chunyang Wu, Yuan Shangguan, Junteng Jia, Wenhan Xiong, Jay Mahadeokar, Chunxi Liu, Yangyang Shi, Ozlem Kalinli, Mike Seltzer, Mark J. F. Gales
2023	J	`jnl`	Prompting Large Language Models with Speech Recognition Abilities. CoRR Yassir Fathullah, Chunyang Wu, Egor Lakomkin, Junteng Jia, Yuan Shangguan, Ke Li, Jinxi Guo, Wenhan Xiong, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer
2023	J	`jnl`	TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models. CoRR Yuan Shangguan, Haichuan Yang, Danni Li, Chunyang Wu, Yassir Fathullah, Dilin Wang, Ayushi Dalmia, Raghuraman Krishnamoorthi, Ozlem Kalinli, Junteng Jia, Jay Mahadeokar, Xin Lei, Mike Seltzer, Vikas Chandra
2023	J	`jnl`	Towards General-Purpose Speech Abilities for Large Language Models Using Unpaired Data. CoRR Yassir Fathullah, Chunyang Wu, Egor Lakomkin, Junteng Jia, Yuan Shangguan, Jay Mahadeokar, Ozlem Kalinli, Christian Fuegen, Mike Seltzer
2023	J	`jnl`	Towards Selection of Text-to-speech Data to Augment ASR Training. CoRR Shuo Liu, Leda Sari, Chunyang Wu, Gil Keren, Yuan Shangguan, Jay Mahadeokar, Ozlem Kalinli
2023	A*	`conf`	Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale. NeurIPS Matthew Le, Apoorv Vyas, Bowen Shi, Brian Karrer, Leda Sari, Rashel Moritz, Mary Williamson, Vimal Manohar, Yossi Adi, Jay Mahadeokar, Wei-Ning Hsu
2023	J	`jnl`	Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale. CoRR Matthew Le, Apoorv Vyas, Bowen Shi, Brian Karrer, Leda Sari, Rashel Moritz, Mary Williamson, Vimal Manohar, Yossi Adi, Jay Mahadeokar, Wei-Ning Hsu
2022	—	`conf`	An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition. SLT Niko Moritz, Frank Seide, Duc Le, Jay Mahadeokar, Christian Fuegen
2022	J	`jnl`	An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition. CoRR Niko Moritz, Frank Seide, Duc Le, Jay Mahadeokar, Christian Fuegen
2022	J	`jnl`	Anchored Speech Recognition with Neural Transducers. CoRR Desh Raj, Junteng Jia, Jay Mahadeokar, Chunyang Wu, Niko Moritz, Xiaohui Zhang, Ozlem Kalinli
2022	J	`jnl`	Dynamic Speech Endpoint Detection with Regression Targets. CoRR Dawei Liang, Hang Su, Tarun Singh, Jay Mahadeokar, Shanil Puri, Jiedan Zhu, Edison Thomaz, Mike Seltzer
2022	A	`conf`	Federated Domain Adaptation for ASR with Full Self-Supervision. INTERSPEECH Junteng Jia, Jay Mahadeokar, Weiyi Zheng, Yuan Shangguan, Ozlem Kalinli, Frank Seide
2022	J	`jnl`	Federated Domain Adaptation for ASR with Full Self-Supervision. CoRR Junteng Jia, Jay Mahadeokar, Weiyi Zheng, Yuan Shangguan, Ozlem Kalinli, Frank Seide
2022	Misc	`conf`	Streaming Transformer Transducer based Speech Recognition Using Non-Causal Convolution. ICASSP Yangyang Shi, Chunyang Wu, Dilin Wang, Alex Xiao, Jay Mahadeokar, Xiaohui Zhang, Chunxi Liu, Ke Li, Yuan Shangguan, Varun Nagaraja, Ozlem Kalinli, Mike Seltzer
2022	A	`conf`	Streaming parallel transducer beam search with fast slow cascaded encoders. INTERSPEECH Jay Mahadeokar, Yangyang Shi, Ke Li, Duc Le, Jiedan Zhu, Vikas Chandra, Ozlem Kalinli, Michael L. Seltzer
2022	J	`jnl`	Streaming parallel transducer beam search with fast-slow cascaded encoders. CoRR Jay Mahadeokar, Yangyang Shi, Ke Li, Duc Le, Jiedan Zhu, Vikas Chandra, Ozlem Kalinli, Michael L. Seltzer
2021	—	`conf`	Alignment Restricted Streaming Recurrent Neural Network Transducer. SLT Jay Mahadeokar, Yuan Shangguan, Duc Le, Gil Keren, Hang Su, Thong Le, Ching-Feng Yeh, Christian Fuegen, Michael L. Seltzer
2021	A	`conf`	Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion. Interspeech 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
2021	J	`jnl`	Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion. CoRR 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
2021	—	`conf`	Deep Shallow Fusion for RNN-T Personalization. SLT Duc Le, Gil Keren, Julian Chan, Jay Mahadeokar, Christian Fuegen, Michael L. Seltzer
2021	A	`conf`	Dissecting User-Perceived Latency of On-Device E2E Speech Recognition. Interspeech Yuan Shangguan, Rohit Prabhavalkar, Hang Su, Jay Mahadeokar, Yangyang Shi, Jiatong Zhou, Chunyang Wu, Duc Le, Ozlem Kalinli, Christian Fuegen, Michael L. Seltzer
2021	J	`jnl`	Dissecting User-Perceived Latency of On-Device E2E Speech Recognition. CoRR Yuan Shangguan, Rohit Prabhavalkar, Hang Su, Jay Mahadeokar, Yangyang Shi, Jiatong Zhou, Chunyang Wu, Duc Le, Ozlem Kalinli, Christian Fuegen, Michael L. Seltzer
2021	J	`jnl`	Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency. CoRR 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
2021	A	`conf`	Dynamic Encoder Transducer: A Flexible Solution for Trading Off Accuracy for Latency. Interspeech 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
2021	A	`conf`	Flexi-Transducer: Optimizing Latency, Accuracy and Compute for Multi-Domain On-Device Scenarios. Interspeech Jay Mahadeokar, Yangyang Shi, Yuan Shangguan, Chunyang Wu, Alex Xiao, Hang Su, Duc Le, Ozlem Kalinli, Christian Fuegen, Michael L. Seltzer
2021	J	`jnl`	Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios. CoRR Jay Mahadeokar, Yangyang Shi, Yuan Shangguan, Chunyang Wu, Alex Xiao, Hang Su, Duc Le, Ozlem Kalinli, Christian Fuegen, Michael L. Seltzer
2021	Misc	`conf`	Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer. ICASSP Suyoun Kim, Yuan Shangguan, Jay Mahadeokar, Antoine Bruguier, Christian Fuegen, Michael L. Seltzer, Duc Le
2021	Misc	`conf`	Memory-Efficient Speech Recognition on Smart Devices. ICASSP Ganesh Venkatesh, Alagappan Valliappan, Jay Mahadeokar, Yuan Shangguan, Christian Fuegen, Michael L. Seltzer, Vikas Chandra
2021	J	`jnl`	Memory-efficient Speech Recognition on Smart Devices. CoRR Ganesh Venkatesh, Alagappan Valliappan, Jay Mahadeokar, Yuan Shangguan, Christian Fuegen, Michael L. Seltzer, Vikas Chandra
2021	J	`jnl`	Streaming Transformer Transducer Based Speech Recognition Using Non-Causal Convolution. CoRR Yangyang Shi, Chunyang Wu, Dilin Wang, Alex Xiao, Jay Mahadeokar, Xiaohui Zhang, Chunxi Liu, Ke Li, Yuan Shangguan, Varun Nagaraja, Ozlem Kalinli, Mike Seltzer
2021	J	`jnl`	TorchAudio: Building Blocks for Audio and Speech Processing. CoRR Yao-Yuan Yang, Moto Hira, Zhaoheng Ni, Anjali Chourdia, Artyom Astafurov, Caroline Chen, Ching-Feng Yeh, Christian Puhrsch, David Pollack, Dmitriy Genzel, Donny Greenberg, Edward Z. Yang, Jason Lian, Jay Mahadeokar, Jeff Hwang, Ji Chen, Peter Goldsborough, Prabhat Roy, Sean Narenthiran, Shinji Watanabe, Soumith Chintala, Vincent Quenneville-Bélair, Yangyang Shi
2020	J	`jnl`	Alignment Restricted Streaming Recurrent Neural Network Transducer. CoRR Jay Mahadeokar, Yuan Shangguan, Duc Le, Gil Keren, Hang Su, Thong Le, Ching-Feng Yeh, Christian Fuegen, Michael L. Seltzer
2020	J	`jnl`	Contextual RNN-T For Open Domain ASR. CoRR Mahaveer Jain, Gil Keren, Jay Mahadeokar, Yatharth Saraf
2020	A	`conf`	Contextual RNN-T for Open Domain ASR. INTERSPEECH Mahaveer Jain, Gil Keren, Jay Mahadeokar, Geoffrey Zweig, Florian Metze, Yatharth Saraf
2020	J	`jnl`	Deep Shallow Fusion for RNN-T Personalization. CoRR Duc Le, Gil Keren, Julian Chan, Jay Mahadeokar, Christian Fuegen, Michael L. Seltzer
2020	J	`jnl`	Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer. CoRR Suyoun Kim, Yuan Shangguan, Jay Mahadeokar, Antoine Bruguier, Christian Fuegen, Michael L. Seltzer, Duc Le
2020	Misc	`conf`	Spatial Attention for Far-Field Speech Recognition with Deep Beamforming Neural Networks. ICASSP Weipeng He, Lu Lu, Biqiao Zhang, Jay Mahadeokar, Kaustubh Kalgaonkar, Christian Fuegen
2020	Misc	`conf`	Transformer-Based Acoustic Modeling for Hybrid Speech Recognition. ICASSP 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
2019	J	`jnl`	RNN-T For Latency Controlled ASR With Improved Beam Search. CoRR Mahaveer Jain, Kjell Schubert, Jay Mahadeokar, Ching-Feng Yeh, Kaustubh Kalgaonkar, Anuroop Sriram, Christian Fuegen, Michael L. Seltzer
2019	J	`jnl`	Spatial Attention for Far-field Speech Recognition with Deep Beamforming Neural Networks. CoRR Weipeng He, Lu Lu, Biqiao Zhang, Jay Mahadeokar, Kaustubh Kalgaonkar, Christian Fuegen
2019	J	`jnl`	Transformer-Transducer: End-to-End Speech Recognition with Self-Attention. CoRR Ching-Feng Yeh, Jay Mahadeokar, Kaustubh Kalgaonkar, Yongqiang Wang, Duc Le, Mahaveer Jain, Kjell Schubert, Christian Fuegen, Michael L. Seltzer
2019	J	`jnl`	Transformer-based Acoustic Modeling for Hybrid Speech Recognition. CoRR 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
2014	J	`jnl`	Faster algorithm to find anti-risk path between two nodes of an undirected graph. J. Comb. Optim. Jay Mahadeokar, Sanjeev Saxena
2014	—	`conf`	Short-text representation using diffusion wavelets. WWW (Companion Volume) Vidit Jain, Jay Mahadeokar
2013	J	`jnl`	Faster replacement paths algorithms in case of edge or node failure for undirected, positive integer weighted graphs. J. Discrete Algorithms Jay Mahadeokar, Sanjeev Saxena
2012	C	`conf`	Faster Replacement Paths Algorithm for Undirected, Positive Integer Weighted Graphs with Small Diameter. IWOCA Jay Mahadeokar, Sanjeev Saxena