Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Jay Mahadeokar

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


Apr 06, 2021
Jay Mahadeokar, Yangyang Shi, Yuan Shangguan, Chunyang Wu, Alex Xiao, Hang Su, Duc Le, Ozlem Kalinli, Christian Fuegen, Michael L. Seltzer

* Submitted to Interspeech 2021 (under review) 

  Access Paper or Ask Questions

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


Apr 06, 2021
Yuan Shangguan, Rohit Prabhavalkar, Hang Su, Jay Mahadeokar, Yangyang Shi, Jiatong Zhou, Chunyang Wu, Duc Le, Ozlem Kalinli, Christian Fuegen, Michael L. Seltzer

* Submitted to Interspeech 2021 

  Access Paper or Ask Questions

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


Apr 05, 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

* Submitted to INTERSPEECH 2021 

  Access Paper or Ask Questions

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


Apr 05, 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

* 5 pages, 2 figures, submitted Interspeech 2021 

  Access Paper or Ask Questions

Memory-efficient Speech Recognition on Smart Devices


Feb 23, 2021
Ganesh Venkatesh, Alagappan Valliappan, Jay Mahadeokar, Yuan Shangguan, Christian Fuegen, Michael L. Seltzer, Vikas Chandra

* ICASSP 2021 

  Access Paper or Ask Questions

Deep Shallow Fusion for RNN-T Personalization


Nov 16, 2020
Duc Le, Gil Keren, Julian Chan, Jay Mahadeokar, Christian Fuegen, Michael L. Seltzer

* To appear at SLT 2021 

  Access Paper or Ask Questions

Alignment Restricted Streaming Recurrent Neural Network Transducer


Nov 05, 2020
Jay Mahadeokar, Yuan Shangguan, Duc Le, Gil Keren, Hang Su, Thong Le, Ching-Feng Yeh, Christian Fuegen, Michael L. Seltzer

* Accepted for presentation at IEEE Spoken Language Technology Workshop (SLT) 2021 

  Access Paper or Ask Questions

Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer


Oct 26, 2020
Suyoun Kim, Yuan Shangguan, Jay Mahadeokar, Antoine Bruguier, Christian Fuegen, Michael L. Seltzer, Duc Le

* submitted to ICASSP 2021 

  Access Paper or Ask Questions

Contextual RNN-T For Open Domain ASR


Jun 04, 2020
Mahaveer Jain, Gil Keren, Jay Mahadeokar, Yatharth Saraf


  Access Paper or Ask Questions

RNN-T For Latency Controlled ASR With Improved Beam Search


Nov 05, 2019
Mahaveer Jain, Kjell Schubert, Jay Mahadeokar, Ching-Feng Yeh, Kaustubh Kalgaonkar, Anuroop Sriram, Christian Fuegen, Michael L. Seltzer


  Access Paper or Ask Questions

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


Oct 28, 2019
Ching-Feng Yeh, Jay Mahadeokar, Kaustubh Kalgaonkar, Yongqiang Wang, Duc Le, Mahaveer Jain, Kjell Schubert, Christian Fuegen, Michael L. Seltzer


  Access Paper or Ask Questions

Transformer-based Acoustic Modeling for Hybrid Speech Recognition


Oct 22, 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


  Access Paper or Ask Questions