Следене
Arun Narayanan
Arun Narayanan
Senior Staff Research Scientist at Google Inc.
Потвърден имейл адрес: google.com - Начална страница
Заглавие
Позовавания
Позовавания
Година
On Training Targets For Supervised Speech Separation
Y Wang, A Narayanan, DL Wang
11922014
Ideal Ratio Mask Estimation Using Deep Neural Networks for Robust Speech Recognition
A Narayanan, DL Wang
Acoustics, Speech and Signal Processing (ICASSP), 2013 IEEE International …, 2013
6372013
Multichannel signal processing with deep neural networks for automatic speech recognition
TN Sainath, RJ Weiss, KW Wilson, B Li, A Narayanan, E Variani, ...
IEEE/ACM Transactions on Audio, Speech, and Language Processing 25 (5), 965-979, 2017
2742017
Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home.
C Kim, A Misra, KK Chin, T Hughes, A Narayanan, TN Sainath, ...
Interspeech, 379-383, 2017
2702017
Processing multi-channel audio waveforms
TN Sainath, RJ Weiss, KW Wilson, AW Senior, A Narayanan, Y Hoshen, ...
US Patent 9,697,826, 2017
2502017
A streaming on-device end-to-end model surpassing server-side conventional model quality and latency
TN Sainath, Y He, B Li, A Narayanan, R Pang, A Bruguier, S Chang, W Li, ...
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
2262020
Acoustic Modeling for Google Home.
B Li, TN Sainath, A Narayanan, J Caroselli, M Bacchiani, A Misra, ...
Interspeech, 399-403, 2017
2052017
Sound source estimation using neural networks
C Kim, RC Nongpiur, A Narayanan
US Patent 10,063,965, 2018
1882018
From audio to semantics: Approaches to end-to-end spoken language understanding
P Haghani*, A Narayanan*, M Bacchiani, G Chuang, N Gaur, P Moreno, ...
2018 IEEE Spoken Language Technology Workshop (SLT), 720-726, 2018
1682018
Investigation of speech separation as a front-end for noise robust speech recognition
A Narayanan, DL Wang
IEEE, 2014
1562014
Recognizing long-form speech using streaming end-to-end models
A Narayanan, R Prabhavalkar, CC Chiu, D Rybach, TN Sainath, ...
2019 IEEE automatic speech recognition and understanding workshop (ASRU …, 2019
1352019
A better and faster end-to-end model for streaming asr
B Li, A Gulati, J Yu, TN Sainath, CC Chiu, A Narayanan, SY Chang, ...
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
1272021
Toward domain-invariant speech recognition via large scale training
A Narayanan, A Misra, KC Sim, G Pundak, A Tripathi, M Elfeky, P Haghani, ...
2018 IEEE Spoken Language Technology Workshop (SLT), 441-447, 2018
1182018
Joint noise adaptive training for robust automatic speech recognition
A Narayanan, DL Wang
International conference on acoustics, speech, and signal processing (ICASSP), 2014
1122014
Fastemit: Low-latency streaming asr with sequence-level emission regularization
J Yu, CC Chiu, B Li, S Chang, TN Sainath, Y He, A Narayanan, W Han, ...
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
952021
Speaker Location and Microphone Spacing Invariant Acoustic Modeling from Raw Multichannel Wwaveforms
TN Sainath, RJ Weiss, KW Wilson, A Narayanan, M Bacchiani, A Senior
942015
Factored spatial and spectral multichannel raw waveform CLDNNs
TN Sainath, RJ Weiss, KW Wilson, A Narayanan, M Bacchiani
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
902016
A comparison of end-to-end models for long-form speech recognition
CC Chiu, W Han, Y Zhang, R Pang, S Kishchenko, P Nguyen, ...
2019 IEEE automatic speech recognition and understanding workshop (ASRU …, 2019
832019
Cascaded encoders for unifying streaming and non-streaming ASR
A Narayanan, TN Sainath, R Pang, J Yu, CC Chiu, R Prabhavalkar, ...
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
822021
Improving robustness of deep neural network acoustic models via speech separation and joint adaptive training
A Narayanan, DL Wang
IEEE/ACM transactions on audio, speech, and language processing 23 (1), 92-101, 2014
822014
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20