| 2025 | Interspeech | Evaluating Speech Foundation Models for Automatic Speech Recognition in the Low-Resource Kanyen'kha Language. | Mengzhe Geng, Patrick Littell, Aidan Pine, Robbie Jimerson, Gilles Boulianne, Vishwa Gupta, Rolando Coto-Solano, Anna Kazantseva, Marc Tessier, Delaney Lothian, Akwiratkha' Martin, Eric Joanis, Samuel Larkin, Roland Kuhn |
| 2022 | LREC | Progress in Multilingual Speech Recognition for Low Resource Languages Kurmanji Kurdish, Cree and Inuktut. | Vishwa Gupta, Gilles Boulianne |
| 2020 | COLING | The Indigenous Languages Technology project at NRC Canada: An empowerment-oriented approach to developing language software. | Roland Kuhn, Fineen Davis, Alain Dsilets, Eric Joanis, Anna Kazantseva, Rebecca Knowles, Patrick Littell, Delaney Lothian, Aidan Pine, Caroline Running Wolf, Eddie Antonio Santos, Darlene A. Stewart, Gilles Boulianne, Vishwa Gupta, Brian Maracle Owennatkha, Akwiratkha' Martin, Christopher Cox, Marie-Odile Junker, Olivia Sammons, Delasie Torkornoo, Nathan Thanyehtnhas Brinklow, Sara Child, Benoit Farley, David Huggins-Daines, Daisy Rosenblum, Heather Souter |
| 2020 | LREC | Automatic Transcription Challenges for Inuktitut, a Low-Resource Polysynthetic Language. | Vishwa Gupta, Gilles Boulianne |
| 2019 | Interspeech | CRIM's Speech Transcription and Call Sign Detection System for the ATC Airbus Challenge Task. | Vishwa Gupta, Lise Rebout, Gilles Boulianne, Pierre Andr Mnard, Jahangir Alam |
| 2018 | Interspeech | Deeply Fused Speaker Embeddings for Text-Independent Speaker Verification. | Gautam Bhattacharya, Jahangir Alam, Vishwa Gupta, Patrick Kenny |
| 2018 | Interspeech | CRIM's System for the MGB-3 English Multi-Genre Broadcast Media Transcription. | Vishwa Gupta, Gilles Boulianne |
| 2017 | ICASSP | Robust video fingerprints using positions of salient regions. | Chahid Ouali, Pierre Dumouchel, Vishwa Gupta |
| 2016 | Interspeech | Tandem Features for Text-Dependent Speaker Verification on the RedDots Corpus. | Md. Jahangir Alam, Patrick Kenny, Vishwa Gupta |
| 2015 | ASRU | CRIM and LIUM approaches for multi-genre broadcast media transcription. | Vishwa Gupta, Paul Delglise, Gilles Boulianne, Yannick Estve, Sylvain Meignier, Anthony Rousseau |
| 2015 | CBMI | GPU implementation of an audio fingerprints similarity search algorithm. | Chahid Ouali, Pierre Dumouchel, Vishwa Gupta |
| 2015 | ICASSP | Speaker change point detection using deep neural nets. | Vishwa Gupta |
| 2015 | ICASSP | Efficient spectrogram-based binary image feature for audio copy detection. | Chahid Ouali, Pierre Dumouchel, Vishwa Gupta |
| 2015 | ISM | Content-Based Multimedia Copy Detection. | Chahid Ouali, Pierre Dumouchel, Vishwa Gupta |
| 2014 | CBMI | A robust audio fingerprinting method for content-based copy detection. | Chahid Ouali, Pierre Dumouchel, Vishwa Gupta |
| 2014 | ICASSP | I-vector-based speaker adaptation of deep neural networks for French broadcast audio transcription. | Vishwa Gupta, Patrick Kenny, Pierre Ouellet, Themos Stafylakis |
| 2014 | Interspeech | Robust features for content-based audio copy detection. | Chahid Ouali, Pierre Dumouchel, Vishwa Gupta |
| 2013 | ICASSP | Compensation for inter-frame correlations in speaker diarization and recognition. | Themos Stafylakis, Patrick Kenny, Vishwa Gupta, Pierre Dumouchel |
| 2013 | Interspeech | Comparing computation in Gaussian mixture and neural network based large-vocabulary speech recognition. | Vishwa Gupta, Gilles Boulianne |
| 2010 | CBMI | Crim's content-based audio copy detection system for TRECVID 2009. | Vishwa Gupta, Gilles Boulianne, Patrick Cardinal |
| 2010 | CVPR | A computer-vision-assisted system for Videodescription scripting. | Langis Gagnon, Claude Chapdelaine, David Byrns, Samuel Foucher, Maguelonne Hritier, Vishwa Gupta |
| 2010 | ICASSP | Content-based audio copy detection using nearest-neighbor mapping. | Vishwa Gupta, Gilles Boulianne, Patrick Cardinal |
| 2010 | ICASSP | Subword-based spoken term detection in audio course lectures. | Richard C. Rose, Atta Norouzian, Aarthi M. Reddy, Andr Coy, Vishwa Gupta, Martin Karafit |
| 2010 | Interspeech | Content-based advertisement detection. | Patrick Cardinal, Vishwa Gupta, Gilles Boulianne |
| 2008 | ICASSP | Speaker diarization of French broadcast news. | Vishwa Gupta, Gilles Boulianne, Patrick Kenny, Pierre Ouellet, Pierre Dumouchel |
| 2008 | Interspeech | Advertisement detection in French broadcast news using acoustic repetition and Gaussian mixture models. | Vishwa Gupta, Gilles Boulianne, Patrick Kenny, Pierre Dumouchel |
| 2008 | Interspeech | Development of the primary CRIM system for the NIST 2008 speaker recognition evaluation. | Patrick Kenny, Najim Dehak, Pierre Ouellet, Vishwa Gupta, Pierre Dumouchel |
| 2007 | ASRU | Multiple feature combination to improve speaker diarization of telephone conversations. | Vishwa Gupta, Patrick Kenny, Pierre Ouellet, Gilles Boulianne, Pierre Dumouchel |
| 2006 | Interspeech | Feature normalization using smoothed mixture transformations. | Patrick Kenny, Vishwa Gupta, Gilles Boulianne, Pierre Ouellet, Pierre Dumouchel |
| 1999 | ICASSP | Application of simultaneous decoding algorithms to automatic transcription of known and unknown words. | Jian-Xiong Wu, Vishwa Gupta |
| 1996 | ICASSP | Compensated mel frequency cepstrum coefficients. | Rivarol Vergin, Douglas D. O'Shaughnessy, Vishwa Gupta |
| 1992 | ICASSP | Hybrid segmental-LVQ/HMM for large vocabulary speech recognition. | Yan Ming Cheng, Douglas D. O'Shaughnessy, Vishwa Gupta, Patrick Kenny, Matthew Lennig, Paul Mermelstein, Sarangarajan Parthasarathy |
| 1992 | Interspeech | Flexible vocabulary recognition of speech. | Matthew Lennig, Douglas Sharp, Patrick Kenny, Vishwa Gupta, Kristin Precoda |
| 1991 | ICASSP | Using phoneme duration and energy contour information to improve large vocabulary isolated-word recognition. | Vishwa Gupta, Matthew Lennig, Paul Mermelstein, Patrick Kenny, Franz Seitz, Douglas D. O'Shaughnessy |
| 1991 | ICASSP | A*-admissible heuristics for rapid lexical access. | Patrick Kenny, Rene Hollan, Vishwa Gupta, Matthew Lennig, Paul Mermelstein, Douglas D. O'Shaughnessy |
| 1991 | Interspeech | Energy, duration and Markov models. | Patrick Kenny, Sarangarajan Parthasarathy, Vishwa Gupta, Matthew Lennig, Paul Mermelstein, Douglas D. O'Shaughnessy |
| 1990 | ICASSP | Acoustic recognition component of an 86000-word speech recognizer. | Li Deng, Vishwa Gupta, Matthew Lennig, Patrick Kenny, Paul Mermelstein |
| 1990 | NAACL | An 86, 000-Word Recognizer Based on Phonemic Models. | Matthew Lennig, Vishwa Gupta, Patrick Kenny, Paul Mermelstein, Douglas D. O'Shaughnessy |
| 1989 | ICASSP | A locus model of coarticulation in an HMM speech recognizer. | Li Deng, Patrick Kenny, Matthew Lennig, Vishwa Gupta, Paul Mermelstein |
| 1988 | ICASSP | Modeling acoustic-phonetic detail in an HMM-based large vocabulary speech recognizer. | Li Deng, Matthew Lennig, Vishwa Gupta, Paul Mermelstein |
| 1988 | ICASSP | Three probabilistic language models for a large-vocabulary speech recognizer. | Pierre Dumouchel, Vishwa Gupta, Matthew Lennig, Paul Mermelstein |
| 1987 | ICASSP | Integration of acoustic information in a large vocabulary word recognizer. | Vishwa Gupta, Matthew Lennig, Paul Mermelstein |
| 1984 | ICASSP | Decision rules for speaker-independent isolated word recognition. | Vishwa Gupta, Matthew Lennig, Paul Mermelstein |
| 1978 | ICASSP | Speaker-independent vowel indetification in continuous speech. | Vishwa Gupta, J. Kent Bryan, John N. Gowdy |