Jay Mahadeokar
Jay Mahadeokar
Facebook AI
Verified email at fb.com
Title
Cited by
Cited by
Year
Transformer-based acoustic modeling for hybrid speech recognition
Y Wang, A Mohamed, D Le, C Liu, A Xiao, J Mahadeokar, H Huang, ...
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
742020
Transformer-transducer: End-to-end speech recognition with self-attention
CF Yeh, J Mahadeokar, K Kalgaonkar, Y Wang, D Le, M Jain, K Schubert, ...
arXiv preprint arXiv:1910.12977, 2019
472019
RNN-T for latency controlled ASR with improved beam search
M Jain, K Schubert, J Mahadeokar, CF Yeh, K Kalgaonkar, A Sriram, ...
arXiv preprint arXiv:1911.01629, 2019
162019
Alignment restricted streaming recurrent neural network transducer
J Mahadeokar, Y Shangguan, D Le, G Keren, H Su, T Le, CF Yeh, ...
2021 IEEE Spoken Language Technology Workshop (SLT), 52-59, 2021
72021
Contextual rnn-t for open domain asr
M Jain, G Keren, J Mahadeokar, G Zweig, F Metze, Y Saraf
arXiv preprint arXiv:2006.03411, 2020
62020
Faster algorithm to find anti-risk path between two nodes of an undirected graph
J Mahadeokar, S Saxena
Journal of Combinatorial Optimization 27 (4), 798-807, 2014
52014
Improved neural language model fusion for streaming recurrent neural network transducer
S Kim, Y Shangguan, J Mahadeokar, A Bruguier, C Fuegen, ML Seltzer, ...
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
42021
Deep Shallow Fusion for RNN-T Personalization
D Le, G Keren, J Chan, J Mahadeokar, C Fuegen, ML Seltzer
2021 IEEE Spoken Language Technology Workshop (SLT), 251-257, 2021
32021
Short-text representation using diffusion wavelets
V Jain, J Mahadeokar
Proceedings of the 23rd International Conference on World Wide Web, 301-302, 2014
32014
Faster replacement paths algorithms in case of edge or node failure for undirected, positive integer weighted graphs
J Mahadeokar, S Saxena
Journal of Discrete Algorithms 23, 54-62, 2013
32013
Spatial attention for far-field speech recognition with deep beamforming neural networks
W He, L Lu, B Zhang, J Mahadeokar, K Kalgaonkar, C Fuegen
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
22020
Faster Replacement Paths Algorithm for Undirected, Positive Integer Weighted Graphs with Small Diameter
J Mahadeokar, S Saxena
International Workshop on Combinatorial Algorithms, 81-85, 2012
12012
Memory-Efficient Speech Recognition on Smart Devices
G Venkatesh, A Valliappan, J Mahadeokar, Y Shangguan, C Fuegen, ...
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
2021
Dissecting User-Perceived Latency of On-Device E2E Speech Recognition
Y Shangguan, R Prabhavalkar, H Su, J Mahadeokar, Y Shi, J Zhou, C Wu, ...
arXiv preprint arXiv:2104.02207, 2021
2021
Flexi-Transducer: Optimizing Latency, Accuracy and Compute forMulti-Domain On-Device Scenarios
J Mahadeokar, Y Shi, Y Shangguan, C Wu, A Xiao, H Su, D Le, O Kalinli, ...
arXiv preprint arXiv:2104.02232, 2021
2021
Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency
Y Shi, V Nagaraja, C Wu, J Mahadeokar, D Le, R Prabhavalkar, A Xiao, ...
arXiv preprint arXiv:2104.02176, 2021
2021
Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion
D Le, M Jain, G Keren, S Kim, Y Shi, J Mahadeokar, J Chan, ...
arXiv preprint arXiv:2104.02194, 2021
2021
The system can't perform the operation now. Try again later.
Articles 1–17