Arnab Ghoshal

According to our database, Arnab Ghoshal authored at least 39 papers between 2005 and 2023.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2023

Variable Attention Masking for Configurable Transformer Transducer Speech Recognition.

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

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation.

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

CoRR, 2022

Bilingual End-to-End ASR with Byte-Level Subwords.

Liuhui Deng, Roger Hsiao, Arnab Ghoshal

Proceedings of the IEEE International Conference on Acoustics, 2022

2020

Online Automatic Speech Recognition With Listen, Attend and Spell Model.

Roger Hsiao, Dogan Can, Tim Ng, Ruchir Travadi, Arnab Ghoshal

IEEE Signal Process. Lett., 2020

Improving Language Identification for Multilingual Speakers.

Andrew Titus, Jan Silovský, Nanxin Chen, Roger Hsiao, Mary Young, Arnab Ghoshal

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

2017

Improving DNN Bluetooth Narrowband Acoustic Models by Cross-Bandwidth and Cross-Lingual Initialization.

Xiaodan Zhuang, Arnab Ghoshal, Antti-Veikko Rosti, Matthias Paulik, Daben Liu

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

2014

Cross-Lingual Subspace Gaussian Mixture Models for Low-Resource Speech Recognition.

Liang Lu, Arnab Ghoshal, Steve Renals

IEEE ACM Trans. Audio Speech Lang. Process., 2014

Convolutional Neural Networks for Distant Speech Recognition.

Pawel Swietojanski, Arnab Ghoshal, Steve Renals

IEEE Signal Process. Lett., 2014

A flexible front-end for HTS.

Matthew P. Aylett, Rasmus Dall, Arnab Ghoshal, Gustav Eje Henter, Thomas Merritt

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

2013

Joint Uncertainty Decoding for Noise Robust Subspace Gaussian Mixture Models.

Liang Lu, K. K. Chin, Arnab Ghoshal, Stephen Renals

IEEE Trans. Speech Audio Process., 2013

Sequence-discriminative training of deep neural networks.

Karel Veselý, Arnab Ghoshal, Lukás Burget, Daniel Povey

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Noise adaptive training for subspace Gaussian mixture models.

Liang Lu, Arnab Ghoshal, Steve Renals

Proceedings of the 14th Annual Conference of the International Speech Communication Association, 2013

Revisiting hybrid and GMM-HMM system combination techniques.

Pawel Swietojanski, Arnab Ghoshal, Steve Renals

Proceedings of the IEEE International Conference on Acoustics, 2013

Multilingual training of deep neural networks.

Arnab Ghoshal, Pawel Swietojanski, Steve Renals

Proceedings of the IEEE International Conference on Acoustics, 2013

Hybrid acoustic models for distant and multichannel large vocabulary speech recognition.

Pawel Swietojanski, Arnab Ghoshal, Steve Renals

Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 2013

Acoustic data-driven pronunciation lexicon for large vocabulary speech recognition.

Liang Lu, Arnab Ghoshal, Steve Renals

Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, 2013

2012

Unsupervised cross-lingual knowledge transfer in DNN-based LVCSR.

Pawel Swietojanski, Arnab Ghoshal, Steve Renals

Proceedings of the 2012 IEEE Spoken Language Technology Workshop (SLT), 2012

The UEDIN systems for the IWSLT 2012 evaluation.

Eva Hasler, Peter Bell, Arnab Ghoshal, Barry Haddow, Philipp Koehn, Fergus McInnes, Steve Renals, Pawel Swietojanski

Proceedings of the 2012 International Workshop on Spoken Language Translation, 2012

Joint uncertainty decoding with unscented transform for noise robust subspace Gaussian mixture models.

Liang Lu, Arnab Ghoshal, Steve Renals

Proceedings of the ISCA Workshop on Statistical And Perceptual Audition, 2012

Noise Compensation for Subspace Gaussian Mixture Models.

Liang Lu, K. K. Chin, Arnab Ghoshal, Steve Renals

Proceedings of the 13th Annual Conference of the International Speech Communication Association, 2012

Revisiting semi-continuous hidden Markov models.

Korbinian Riedhammer, Tobias Bocklet, Arnab Ghoshal, Daniel Povey

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Generating exact lattices in the WFST framework.

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

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

Maximum a posteriori adaptation of subspace Gaussian mixture models for cross-lingual speech recognition.

Liang Lu, Arnab Ghoshal, Steve Renals

Proceedings of the 2012 IEEE International Conference on Acoustics, 2012

2011

Regularized Subspace Gaussian Mixture Models for Speech Recognition.

Liang Lu, Arnab Ghoshal, Steve Renals

IEEE Signal Process. Lett., 2011

The subspace Gaussian mixture model - A structured model for speech recognition.

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

Comput. Speech Lang., 2011

A symmetrization of the Subspace Gaussian Mixture Model.

Daniel Povey, Martin Karafiát, Arnab Ghoshal, Petr Schwarz

Proceedings of the IEEE International Conference on Acoustics, 2011

Regularized subspace Gaussian mixture models for cross-lingual speech recognition.

Liang Lu, Arnab Ghoshal, Steve Renals

Proceedings of the 2011 IEEE Workshop on Automatic Speech Recognition & Understanding, 2011

2010

Subspace Gaussian Mixture Models for speech recognition.

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

Proceedings of the IEEE International Conference on Acoustics, 2010

Approaches to automatic lexicon learning with limited training examples.

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

Proceedings of the IEEE International Conference on Acoustics, 2010

A novel estimation of feature-space MLLR for full-covariance models.

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

Proceedings of the IEEE International Conference on Acoustics, 2010

Multilingual acoustic modeling for speech recognition based on subspace Gaussian Mixture Models.

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

Proceedings of the IEEE International Conference on Acoustics, 2010

Maximum negentropy beamforming with superdirectivity.

Ken'ichi Kumatani, Liang Lu, John W. McDonough, Arnab Ghoshal, Dietrich Klakow

Proceedings of the 18th European Signal Processing Conference, 2010

2009

Web derived pronunciations for spoken term detection.

Dogan Can, Erica Cooper, Arnab Ghoshal, Martin Jansche, Sanjeev Khudanpur, Bhuvana Ramabhadran, Michael Riley, Murat Saraclar, Abhinav Sethy, Morgan Ulinski, Christopher M. White

Proceedings of the 32nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2009

Impact of novel sources on content-based image and video retrieval.

Arnab Ghoshal, Sanjeev Khudanpur, Dietrich Klakow

Proceedings of the IEEE International Conference on Acoustics, 2009

WEB-derived pronunciations.

Arnab Ghoshal, Martin Jansche, Sanjeev Khudanpur, Michael Riley, Morgan Ulinski

Proceedings of the IEEE International Conference on Acoustics, 2009

2006

Imperial College and Johns Hopkins University at TRECVID.

Arnab Ghoshal, Sanjeev Khudanpur, João Magalhães, Simon E. Overell, Stefan M. Rüger, Alexei Yavlinsky

Proceedings of the 2006 TREC Video Retrieval Evaluation, 2006

Source Adaptation for Improved Content-Based Video Retrieval.

Arnab Ghoshal, Sanjeev Khudanpur

Proceedings of the 2006 IEEE International Conference on Acoustics Speech and Signal Processing, 2006

2005

TRECVID 2005 Experiment at Johns Hopkins University: Using Hidden Markov Models for Video Retrieval.

Brock Pytlik, Arnab Ghoshal, Damianos G. Karakos, Sanjeev Khudanpur

Proceedings of the 2005 TREC Video Retrieval Evaluation, 2005

Hidden Markov models for automatic annotation and content-based retrieval of images and video.

Arnab Ghoshal, Pavel Ircing, Sanjeev Khudanpur

Proceedings of the SIGIR 2005: Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 2005