Arnab Ghoshal

43 papers A* 2A 5C 3Misc 15Journal 11Unranked 7
YearRankTypeTitle / Venue / Authors
2023 Misc conf
Variable Attention Masking for Configurable Transformer Transducer Speech Recognition.
ICASSP
Pawel Swietojanski, Stefan Braun, Dogan Can, Thiago Fraga Da Silva, Arnab Ghoshal, Takaaki Hori, Roger Hsiao, Henry Mason, Erik McDermott, Honza Silovsky, Ruchir Travadi, Xiaodan Zhuang
2022 Misc conf
Bilingual End-to-End ASR with Byte-Level Subwords.
ICASSP
Liuhui Deng, Roger Hsiao, Arnab Ghoshal
2022 J jnl
Bilingual End-to-End ASR with Byte-Level Subwords.
CoRR
Liuhui Deng, Roger Hsiao, Arnab Ghoshal
2022 J jnl
Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation.
CoRR
Thien Nguyen, Nathalie Tran, Liuhui Deng, Thiago Fraga Da Silva, Matthew Radzihovsky, Roger Hsiao, Henry Mason, Stefan Braun, Erik McDermott, Dogan Can, Pawel Swietojanski, Lyan Verwimp, Sibel Oyman, Tresi Arvizo, Honza Silovsky, Arnab Ghoshal, Mathieu Martel, Bharat Ram Ambati, Mohamed Ali
2022 J jnl
Variable Attention Masking for Configurable Transformer Transducer Speech Recognition.
CoRR
Pawel Swietojanski, Stefan Braun, Dogan Can, Thiago Fraga Da Silva, Arnab Ghoshal, Takaaki Hori, Roger Hsiao, Henry Mason, Erik McDermott, Honza Silovsky, Ruchir Travadi, Xiaodan Zhuang
2020 Misc conf
Improving Language Identification for Multilingual Speakers.
ICASSP
Andrew Titus, Jan Silovský, Nanxin Chen, Roger Hsiao, Mary Young, Arnab Ghoshal
2020 J jnl
Improving Language Identification for Multilingual Speakers.
CoRR
Andrew Titus, Jan Silovský, Nanxin Chen, Roger Hsiao, Mary Young, Arnab Ghoshal
2020 J jnl
Online Automatic Speech Recognition With Listen, Attend and Spell Model.
IEEE Signal Process. Lett.
Roger Hsiao, Dogan Can, Tim Ng, Ruchir Travadi, Arnab Ghoshal
2020 J jnl
Online Automatic Speech Recognition with Listen, Attend and Spell Model.
CoRR
Roger Hsiao, Dogan Can, Tim Ng, Ruchir Travadi, Arnab Ghoshal
2017 A conf
Improving DNN Bluetooth Narrowband Acoustic Models by Cross-Bandwidth and Cross-Lingual Initialization.
INTERSPEECH
Xiaodan Zhuang, Arnab Ghoshal, Antti-Veikko Rosti, Matthias Paulik, Daben Liu
2014 A conf
A flexible front-end for HTS.
INTERSPEECH
Matthew P. Aylett, Rasmus Dall, Arnab Ghoshal, Gustav Eje Henter, Thomas Merritt
2014 J jnl
Convolutional Neural Networks for Distant Speech Recognition.
IEEE Signal Process. Lett.
Pawel Swietojanski, Arnab Ghoshal, Steve Renals
2014 J jnl
Cross-Lingual Subspace Gaussian Mixture Models for Low-Resource Speech Recognition.
IEEE ACM Trans. Audio Speech Lang. Process.
Liang Lu, Arnab Ghoshal, Steve Renals
2013 C conf
Acoustic data-driven pronunciation lexicon for large vocabulary speech recognition.
ASRU
Liang Lu, Arnab Ghoshal, Steve Renals
2013 C conf
Hybrid acoustic models for distant and multichannel large vocabulary speech recognition.
ASRU
Pawel Swietojanski, Arnab Ghoshal, Steve Renals
2013 J jnl
Joint Uncertainty Decoding for Noise Robust Subspace Gaussian Mixture Models.
IEEE Trans. Speech Audio Process.
Liang Lu, K. K. Chin, Arnab Ghoshal, Stephen Renals
2013 Misc conf
Multilingual training of deep neural networks.
ICASSP
Arnab Ghoshal, Pawel Swietojanski, Steve Renals
2013 A conf
Noise adaptive training for subspace Gaussian mixture models.
INTERSPEECH
Liang Lu, Arnab Ghoshal, Steve Renals
2013 Misc conf
Revisiting hybrid and GMM-HMM system combination techniques.
ICASSP
Pawel Swietojanski, Arnab Ghoshal, Steve Renals
2013 A conf
Sequence-discriminative training of deep neural networks.
INTERSPEECH
Karel Veselý, Arnab Ghoshal, Lukás Burget, Daniel Povey
2012 Misc conf
Generating exact lattices in the WFST framework.
ICASSP
Daniel Povey, Mirko Hannemann, Gilles Boulianne, Lukás Burget, Arnab Ghoshal, Milos Janda, Martin Karafiát, Stefan Kombrink, Petr Motlícek, Yanmin Qian, Korbinian Riedhammer, Karel Veselý, Ngoc Thang Vu
2012 — conf
Joint uncertainty decoding with unscented transform for noise robust subspace Gaussian mixture models.
SAPA@INTERSPEECH
Liang Lu, Arnab Ghoshal, Steve Renals
2012 Misc conf
Maximum a posteriori adaptation of subspace Gaussian mixture models for cross-lingual speech recognition.
ICASSP
Liang Lu, Arnab Ghoshal, Steve Renals
2012 A conf
Noise Compensation for Subspace Gaussian Mixture Models.
INTERSPEECH
Liang Lu, K. K. Chin, Arnab Ghoshal, Steve Renals
2012 Misc conf
Revisiting semi-continuous hidden Markov models.
ICASSP
Korbinian Riedhammer, Tobias Bocklet, Arnab Ghoshal, Daniel Povey
2012 — conf
The UEDIN systems for the IWSLT 2012 evaluation.
IWSLT
Eva Hasler, Peter Bell, Arnab Ghoshal, Barry Haddow, Philipp Koehn, Fergus McInnes, Steve Renals, Pawel Swietojanski
2012 — conf
Unsupervised cross-lingual knowledge transfer in DNN-based LVCSR.
SLT
Pawel Swietojanski, Arnab Ghoshal, Steve Renals
2011 Misc conf
A symmetrization of the Subspace Gaussian Mixture Model.
ICASSP
Daniel Povey, Martin Karafiát, Arnab Ghoshal, Petr Schwarz
2011 J jnl
Regularized Subspace Gaussian Mixture Models for Speech Recognition.
IEEE Signal Process. Lett.
Liang Lu, Arnab Ghoshal, Steve Renals
2011 C conf
Regularized subspace Gaussian mixture models for cross-lingual speech recognition.
ASRU
Liang Lu, Arnab Ghoshal, Steve Renals
2011 J jnl
The subspace Gaussian mixture model - A structured model for speech recognition.
Comput. Speech Lang.
Daniel Povey, Lukás Burget, Mohit Agarwal, Pinar Akyazi, Kai Feng, Arnab Ghoshal, Ondrej Glembek, Nagendra K. Goel, Martin Karafiát, Ariya Rastrow, Richard C. Rose, Petr Schwarz, Samuel Thomas
2010 Misc conf
A novel estimation of feature-space MLLR for full-covariance models.
ICASSP
Arnab Ghoshal, Daniel Povey, Mohit Agarwal, Pinar Akyazi, Lukás Burget, Kai Feng, Ondrej Glembek, Nagendra Goel, Martin Karafiát, Ariya Rastrow, Richard C. Rose, Petr Schwarz, Samuel Thomas
2010 Misc conf
Approaches to automatic lexicon learning with limited training examples.
ICASSP
Nagendra Goel, Samuel Thomas, Mohit Agarwal, Pinar Akyazi, Lukás Burget, Kai Feng, Arnab Ghoshal, Ondrej Glembek, Martin Karafiát, Daniel Povey, Ariya Rastrow, Richard C. Rose, Petr Schwarz
2010 — conf
Maximum negentropy beamforming with superdirectivity.
EUSIPCO
Ken'ichi Kumatani, Liang Lu, John W. McDonough, Arnab Ghoshal, Dietrich Klakow
2010 Misc conf
Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models.
ICASSP
Lukás Burget, Petr Schwarz, Mohit Agarwal, Pinar Akyazi, Kai Feng, Arnab Ghoshal, Ondrej Glembek, Nagendra K. Goel, Martin Karafiát, Daniel Povey, Ariya Rastrow, Richard C. Rose, Samuel Thomas
2010 Misc conf
Subspace Gaussian Mixture Models for speech recognition.
ICASSP
Daniel Povey, Lukás Burget, Mohit Agarwal, Pinar Akyazi, Kai Feng, Arnab Ghoshal, Ondrej Glembek, Nagendra K. Goel, Martin Karafiát, Ariya Rastrow, Richard C. Rose, Petr Schwarz, Samuel Thomas
2009 Misc conf
Impact of novel sources on content-based image and video retrieval.
ICASSP
Arnab Ghoshal, Sanjeev Khudanpur, Dietrich Klakow
2009 Misc conf
WEB-derived pronunciations.
ICASSP
Arnab Ghoshal, Martin Jansche, Sanjeev Khudanpur, Michael Riley, Morgan Ulinski
2009 A* conf
Web derived pronunciations for spoken term detection.
SIGIR
Dogan Can, Erica Cooper, Arnab Ghoshal, Martin Jansche, Sanjeev Khudanpur, Bhuvana Ramabhadran, Michael Riley, Murat Saraclar, Abhinav Sethy, Morgan Ulinski, Christopher M. White
2006 — conf
Imperial College and Johns Hopkins University at TRECVID.
TRECVID
Arnab Ghoshal, Sanjeev Khudanpur, João Magalhães, Simon E. Overell, Stefan M. Rüger, Alexei Yavlinsky
2006 — conf
Source Adaptation for Improved Content-Based Video Retrieval.
ICASSP (2)
Arnab Ghoshal, Sanjeev Khudanpur
2005 A* conf
Hidden Markov models for automatic annotation and content-based retrieval of images and video.
SIGIR
Arnab Ghoshal, Pavel Ircing, Sanjeev Khudanpur
2005 — conf
TRECVID 2005 Experiment at Johns Hopkins University: Using Hidden Markov Models for Video Retrieval.
TRECVID
Brock Pytlik, Arnab Ghoshal, Damianos G. Karakos, Sanjeev Khudanpur