Publications

Publications HAL de Sunit Sivasankaran

2021

Conference papers

titre
Explaining deep learning models for speech enhancement
auteur
Sunit Sivasankaran, Emmanuel Vincent, Dominique Fohr
article
INTERSPEECH 2021, Aug 2021, Brno, Czech Republic. ⟨10.21437/Interspeech.2021-1764⟩
typdoc
Conference papers
DOI
DOI : 10.21437/Interspeech.2021-1764
Accès au texte intégral et bibtex
https://inria.hal.science/hal-03257450/file/dnn_explain_revised.pdf BibTex
titre
Analyzing the impact of speaker localization errors on speech separation for automatic speech recognition
auteur
Sunit Sivasankaran, Emmanuel Vincent, Dominique Fohr
article
EUSIPCO 2020 – 28th European Signal Processing Conference, Jan 2021, Amsterdam / Virtual, Netherlands. ⟨10.23919/Eusipco47968.2020.9287541⟩
typdoc
Conference papers
DOI
DOI : 10.23919/Eusipco47968.2020.9287541
Accès au texte intégral et bibtex
https://inria.hal.science/hal-02355669/file/sunits_eusipco_2020.pdf BibTex

2020

Conference papers

titre
Asteroid: the PyTorch-based audio source separation toolkit for researchers
auteur
Manuel Pariente, Samuele Cornell, Joris Cosentino, Sunit Sivasankaran, Efthymios Tzinis, Jens Heitkaemper, Michel Olvera, Fabian-Robert Stöter, Mathieu Hu, Juan M. Martín-Doñas, David Ditter, Ariel Frank, Antoine Deleforge, Emmanuel Vincent
article
Interspeech 2020, Oct 2020, Shanghai, China
typdoc
Conference papers
Accès au texte intégral et bibtex
https://inria.hal.science/hal-02962964/file/old_main.pdf BibTex
titre
SLOGD: Speaker Location Guided Deflation Approach to Speech Separation
auteur
Sunit Sivasankaran, Emmanuel Vincent, Dominique Fohr
article
ICASSP 2020 – 45th International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelona, Spain
typdoc
Conference papers
Accès au texte intégral et bibtex
https://inria.hal.science/hal-02355613/file/sivasankaran.pdf BibTex

Software

titre
voiceHome-2 corpus – automatic speech recognition baseline – scripts
auteur
Sunit Sivasankaran, Irina Illina, Emmanuel Vincent
article
2020, ⟨swh:1:dir:e61ed9084af0d3e8542cd4ab3a990d24314a6724;origin=https://hal.archives-ouvertes.fr/hal-02963802;visit=swh:1:snp:b958e3aa64f6b1663929789c8cf28d019f55f57d;anchor=swh:1:rev:6b9bf3964385d0c16d262796d9e4a3a30a52dafd;path=/⟩
typdoc
Software
Accès au texte intégral et bibtex
https://inria.hal.science/hal-02963802/file/baseline_recognition_scripts.tar.gz BibTex

Theses

titre
Localization guided speech separation
auteur
Sunit Sivasankaran
article
Machine Learning [cs.LG]. Université de Lorraine, 2020. English. ⟨NNT : 2020LORR0078⟩
typdoc
Theses
Accès au texte intégral et bibtex
https://hal.univ-lorraine.fr/tel-02961882/file/DDOC_T_2020_0078_SIVASANKARAN.pdf BibTex

2019

Journal articles

titre
VoiceHome-2, an extended corpus for multichannel speech processing in real homes
auteur
Nancy Bertin, Ewen Camberlein, Romain Lebarbenchon, Emmanuel Vincent, Sunit Sivasankaran, Irina Illina, Frédéric Bimbot
article
Speech Communication, 2019, 106, pp.68-78. ⟨10.1016/j.specom.2018.11.002⟩
typdoc
Journal articles
DOI
DOI : 10.1016/j.specom.2018.11.002
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01923108/file/bertin_SpeechCom18.pdf BibTex

Preprints, Working Papers, …

titre
The Speed Submission to DIHARD II: Contributions & Lessons Learned
auteur
Md Sahidullah, Jose Patino, Samuele Cornell, Ruiqing Yin, Sunit Sivasankaran, Hervé Bredin, Pavel Korshunov, Alessio Brutti, Romain Serizel, Emmanuel Vincent, Nicholas Evans, Sébastien Marcel, Stefano Squartini, Claude Barras
article
2019
typdoc
Preprints, Working Papers, …
Accès au texte intégral et bibtex
https://inria.hal.science/hal-02352840/file/Speed_DIHARDII_Manuscript.pdf BibTex

2018

Conference papers

titre
Keyword-based speaker localization: Localizing a target speaker in a multi-speaker environment
auteur
Sunit Sivasankaran, Emmanuel Vincent, Dominique Fohr
article
Interspeech 2018 – 19th Annual Conference of the International Speech Communication Association, Sep 2018, Hyderabad, India
typdoc
Conference papers
Accès au texte intégral et bibtex
https://hal.science/hal-01817519/file/single-speaker-localization.pdf BibTex
titre
Phone Merging for Code-switched Speech Recognition
auteur
Sunit Sivasankaran, Brij Mohan Lal Srivastava, Sunayana Sitaram, Kalika Bali, Monojit Choudhury
article
Third Workshop on Computational Approaches to Linguistic Code-switching, collocated with ACL 2018 Jul 2018, Melbourne, Australia
typdoc
Conference papers
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01800466/file/phone-merging-acl.pdf BibTex

2017

Journal articles

titre
A combined evaluation of established and new approaches for speech recognition in varied reverberation conditions
auteur
Sunit Sivasankaran, Emmanuel Vincent, Irina Illina
article
Computer Speech and Language, 2017, 46, pp.444-460. ⟨10.1016/j.csl.2017.02.003⟩
typdoc
Journal articles
DOI
DOI : 10.1016/j.csl.2017.02.003
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01461382/file/sivasankaran_CSL17.pdf BibTex

Conference papers

titre
Discriminative importance weighting of augmented training data for acoustic model training
auteur
Sunit Sivasankaran, Emmanuel Vincent, Irina Illina
article
42th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2017), Mar 2017, New Orleans, United States
typdoc
Conference papers
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01415759/file/sivasankaran_ICASSP17.pdf BibTex
titre
An extended experimental investigation of DNN uncertainty propagation for noise robust ASR
auteur
Karan Nathwani, Juan A Morales-Cordovilla, Sunit Sivasankaran, Irina Illina, Emmanuel Vincent
article
5th Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA 2017), Mar 2017, San Francisco, United States
typdoc
Conference papers
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01446441/file/nathwani_HSCMA17.pdf BibTex

2016

Conference papers

titre
A French corpus for distant-microphone speech processing in real homes
auteur
Nancy Bertin, Ewen Camberlein, Emmanuel Vincent, Romain Lebarbenchon, Stéphane Peillon, Éric Lamandé, Sunit Sivasankaran, Frédéric Bimbot, Irina Illina, Ariane Tom, Sylvain Fleury, Eric Jamet
article
Interspeech 2016, Sep 2016, San Francisco, United States
typdoc
Conference papers
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01343060/file/bertin_IS16.pdf BibTex

2015

Conference papers

titre
Robust ASR using neural network based speech enhancement and feature simulation
auteur
Sunit Sivasankaran, Aditya A Nugraha, Emmanuel Vincent, Juan Andrés Morales Cordovilla, Siddharth Dalmia, Irina Illina, Antoine Liutkus
article
ASRU, Dec 2015, Arizona, United States
typdoc
Conference papers
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01204553/file/INRIA.pdf BibTex

2013

Conference papers

titre
Statistics Based Features for Unvoiced Sound Classification
auteur
Sunit Sivasankaran, Kmm Prabhu
article
MLSP 2013 – IEEE International Workshop on Machine Learning for Signal Processing, Sep 2013, Southampton, United Kingdom. ⟨10.1109/MLSP.2013.6661986⟩
typdoc
Conference papers
DOI
DOI : 10.1109/MLSP.2013.6661986
Accès au bibtex
BibTex
titre
Robust features for environmental sound classification
auteur
Sunit Sivasankaran, K.M.M Prabhu
article
2013 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), Jan 2013, Bangalore, India. pp.1 – 6, ⟨10.1109/CONECCT.2013.6469297⟩
typdoc
Conference papers
DOI
DOI : 10.1109/CONECCT.2013.6469297
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01456201/file/toConf.pdf BibTex