Seguir
Sunit Sivasankaran
Sunit Sivasankaran
Dirección de correo verificada de microsoft.com
Título
Citado por
Citado por
Año
Asteroid: the PyTorch-based audio source separation toolkit for researchers
M Pariente, S Cornell, J Cosentino, S Sivasankaran, E Tzinis, ...
arXiv preprint arXiv:2005.04132, 2020
1432020
Robust ASR using neural network based speech enhancement and feature simulation
S Sivasankaran, AA Nugraha, E Vincent, JA Morales-Cordovilla, S Dalmia, ...
2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU …, 2015
512015
Phone merging for code-switched speech recognition
S Sivasankaran, BML Srivastava, S Sitaram, K Bali, M Choudhury
Third Workshop on Computational Approaches to Linguistic Code-switching, 2018
342018
Keyword-based speaker localization: Localizing a target speaker in a multi-speaker environment
S Sivasankaran, E Vincent, D Fohr
Interspeech 2018-19th Annual Conference of the International Speech …, 2018
302018
VoiceHome-2, an extended corpus for multichannel speech processing in real homes
N Bertin, E Camberlein, R Lebarbenchon, E Vincent, S Sivasankaran, ...
Speech Communication 106, 68-78, 2019
272019
A French corpus for distant-microphone speech processing in real homes
N Bertin, E Camberlein, E Vincent, R Lebarbenchon, S Peillon, ...
Interspeech 2016, 2016
272016
Robust features for environmental sound classification
S Sivasankaran, KMM Prabhu
2013 IEEE International Conference on Electronics, Computing and …, 2013
212013
A combined evaluation of established and new approaches for speech recognition in varied reverberation conditions
S Sivasankaran, E Vincent, I Illina
Computer Speech & Language 46, 444-460, 2017
202017
Discriminative importance weighting of augmented training data for acoustic model training
S Sivasankaran, E Vincent, I Illina
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
172017
The speed submission to DIHARD II: Contributions & lessons learned
M Sahidullah, J Patino, S Cornell, R Yin, S Sivasankaran, H Bredin, ...
arXiv preprint arXiv:1911.02388, 2019
132019
An extended experimental investigation of DNN uncertainty propagation for noise robust ASR
K Nathwani, JA Morales-Cordovilla, S Sivasankaran, I Illina, E Vincent
2017 Hands-free Speech Communications and Microphone Arrays (HSCMA), 26-30, 2017
122017
Speech separation with large-scale self-supervised learning
Z Chen, N Kanda, J Wu, Y Wu, X Wang, T Yoshioka, J Li, S Sivasankaran, ...
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
92023
Analyzing the impact of speaker localization errors on speech separation for automatic speech recognition
S Sivasankaran, E Vincent, D Fohr
2020 28th European Signal Processing Conference (EUSIPCO), 346-350, 2021
92021
Explaining deep learning models for speech enhancement
S Sivasankaran, E Vincent, D Fohr
INTERSPEECH 2021, 2021
72021
Simulating realistic speech overlaps improves multi-talker asr
M Yang, N Kanda, X Wang, J Wu, S Sivasankaran, Z Chen, J Li, ...
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
52023
Cosmic: Data efficient instruction-tuning for speech in-context learning
J Pan, J Wu, Y Gaur, S Sivasankaran, Z Chen, S Liu, J Li
arXiv preprint arXiv:2311.02248, 2023
42023
Analysis of hemispherical Dielectric lens antennas for wireless applications
S Ravishankar, TS Rukmini, HV Kumaraswamy, S Sunit, Y Karthik, ...
2007 Asia-Pacific Conference on Applied Electromagnetics, 1-6, 2007
32007
Localization guided speech separation
S Sivasankaran
Université de Lorraine, 2020
22020
SLOGD: Speaker location guided deflation approach to speech separation
S Sivasankaran, E Vincent, D Fohr
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
22020
Statistics based features for unvoiced sound classification
S Sivasankaran, KMM Prabhu
2013 IEEE International Workshop on Machine Learning for Signal Processing …, 2013
22013
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–20