Follow
Aswin Shanmugam Subramanian
Aswin Shanmugam Subramanian
Research Scientist, MERL
Verified email at merl.com - Homepage
Title
Cited by
Cited by
Year
CHiME-6 Challenge: Tackling multispeaker speech recognition for unsegmented recordings
S Watanabe, M Mandel, J Barker, E Vincent, ...
arXiv preprint arXiv:2004.09249, 2020
1442020
A Common Attribute based Unified HTS framework for Speech Synthesis in Indian Languages
B Ramani, SL Christina, GA Rachel, VS Solomi, MK Nandwana, ...
8th ISCA Workshop on Speech Synthesis, Barcelona, Spain, 311-316, 2013
662013
Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline
SJ Chen, AS Subramanian, H Xu, S Watanabe
arXiv preprint arXiv:1803.10109, 2018
552018
The Hitachi/JHU CHiME-5 system: Advances in speech recognition for everyday home environments using multiple microphone arrays
N Kanda, R Ikeshita, S Horiguchi, Y Fujita, K Nagamatsu, X Wang, ...
Proc. CHiME-5, 6-10, 2018
452018
A hybrid approach to segmentation of speech using group delay processing and HMM based embedded reestimation
SA Shanmugam, H Murthy
Fifteenth Annual Conference of the International Speech Communication …, 2014
302014
Speech Enhancement Using End-to-End Speech Recognition Objectives
AS Subramanian, X Wang, MK Baskar, S Watanabe, T Taniguchi, D Tran, ...
2019 IEEE Workshop on Applications of Signal Processing to Audio and …, 2019
282019
ESPnet-SE: End-to-end speech enhancement and separation toolkit designed for ASR integration
C Li, J Shi, W Zhang, AS Subramanian, X Chang, N Kamo, M Hira, ...
2021 IEEE Spoken Language Technology Workshop (SLT), 785-792, 2021
252021
The 2020 espnet update: new features, broadened applications, performance improvements, and future plans
S Watanabe, F Boyer, X Chang, P Guo, T Hayashi, Y Higuchi, T Hori, ...
2021 IEEE Data Science and Learning Workshop (DSLW), 1-6, 2021
212021
An Investigation of End-to-End Multichannel Speech Recognition for Reverberant and Mismatch Conditions
AS Subramanian, X Wang, S Watanabe, T Taniguchi, D Tran, Y Fujita
arXiv preprint arXiv:1904.09049, 2019
202019
Far-field location guided target speech extraction using end-to-end speech recognition objectives
AS Subramanian, C Weng, M Yu, SX Zhang, Y Xu, S Watanabe, D Yu
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
192020
End-to-end far-field speech recognition with unified dereverberation and beamforming
W Zhang, AS Subramanian, X Chang, S Watanabe, Y Qian
arXiv preprint arXiv:2005.10479, 2020
172020
A Syllable Based Statistical Text to Speech System
A Pradhan, SA Shanmugam, A Prakash, K Veezhinathan, H Murthy
EUSIPCO, 2013
162013
Group delay based phone segmentation for HTS
SA Shanmugam, HA Murthy
2014 Twentieth National Conference on Communications (NCC), 1-6, 2014
152014
Student-teacher learning for BLSTM mask-based speech enhancement
AS Subramanian, SJ Chen, S Watanabe
arXiv preprint arXiv:1803.10013, 2018
142018
Building speech synthesis systems for Indian languages
A Pradhan, A Prakash, SA Shanmugam, GR Kasthuri, R Krishnan, ...
2015 Twenty First National Conference on Communications (NCC), 1-6, 2015
132015
Attention-based asr with lightweight and dynamic convolutions
Y Fujita, AS Subramanian, M Omachi, S Watanabe
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
112020
Deep learning based multi-source localization with source splitting and its effectiveness in multi-talker speech recognition
AS Subramanian, C Weng, S Watanabe, M Yu, D Yu
Computer Speech & Language 75, 101360, 2022
102022
An exploration of self-supervised pretrained representations for end-to-end speech recognition
X Chang, T Maekaku, P Guo, J Shi, YJ Lu, AS Subramanian, T Wang, ...
arXiv preprint arXiv:2110.04590, 2021
102021
A Hybrid Approach to Segmentation of Speech using Signal Processing Cues and Hidden Markov Models
SA Shanmugam
Indian Institute of Technology Madras, 2016
92016
Significance of pseudo-syllables in building better acoustic models for indian english tts
SR Vignesh, SA Shanmugam, HA Murthy
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
82016
The system can't perform the operation now. Try again later.
Articles 1–20