Patrick Cardinal
Directeur du département de génie logiciel et ti
Département
Département de génie logiciel et TI
Formation
B.Ing (ÉTS), M.Sc. (McGill), Ph.D. (ÉTS)
Bureau
A-4486
Courriel
Unité de recherche
Expertises
- Reconnaissance de la parole
- Identification de la langue
- Détection des émotions
- Traitement parallèle
Encadrements
- En codirection avec : Julien Gascon-Samson
Évaluation exhaustive des performances de courtiers MQTT dans divers environnements en périphérie, par Guillaume Simard
Hiver 2024 - En codirection avec : Alessandro Lameiras Koerich
Automatic Audio Anonymization, par Guillaume Baril
Automne 2021 - En codirection avec : Rafael Menelau Oliveira Cruz
Identification des dialectes arabes avec la sélection dynamique de classifieurs, par Pierre-Marc Thibault
Automne 2021 - En codirection avec : Laureano Moro-Velazquez
Predicting the Severity of Parkinson’s Disease Symptoms with Smartwatches during Daily Living, par Marie-Philippe Gill
Hiver 2021 - En codirection avec : Pierre Dumouchel
Utilisation des caractéristiques prosodiques pour optimiser un système de compréhension du langage naturel, par Simon Boutin
Hiver 2016 - En codirection avec : Jean-Marc Robert
SIPBIO - Biometrics SIP Extension, par Wilmar Perez
Été 2018 - En codirection avec : Éric Granger
An Investigation of Ensemble Methods in Emotion Recognition Using LSTM and SVR, par Seyedeh Rafooneh Jafarian Bahri
Été 2019 - Information Extraction from Audio Recordings, par Armita Mohammadi
Automne 2024 - En codirection avec : Elsa Vasseur
Applications of Deep Learning in Visual Recognition, par Mirmohammad Saadati
Hiver 2023 - En codirection avec : Alessandro Lameiras Koerich
Emotion Recognition Using Fusion of Audio And Video Features, par Juan David Silva Ortega
Hiver 2019 - En codirection avec : Marco Pedersoli
Deep audio and video emotion detection, par Masih Aminbeidokhti
Hiver 2020 - En codirection avec : Nawwaf Kharma
Improved Measures of Robustness and Evolvability for Evolutionary Systems, par Rémi Bédard-Couture
Automne 2023 - En codirection avec : Jérémie Voix
Classification of Nonverbal Human-Produced Audio Events, par Philippe Chabot
Hiver 2020 - En codirection avec : Olivier Landon-Cardinal
Apprentissage machine quantique, par Ana Catarina Castro da Silva
Automne 2024 - En codirection avec : Marco Pedersoli
Variational Autoencoders with Gaussian Mixture Prior for Recommender Systems, par Kristof Boucher Charbonneau
Hiver 2020 - En codirection avec : Maxime Dumas
Unsupervised Abstractive Summaries of Controllable Length, par Stéphane Gazaille
Été 2020 - En codirection avec : Olivier Landon-Cardinal
Robustesse des classificateurs quantiques face aux attaques adverses, par Félix Wilhelmy
Automne 2024 - Détection et suivi de joueurs dans le jeu de Blackjack, par Branavan Inthiranathan
Automne 2022
- En codirection avec : Pierrich Plusquellec
Introduction aux réseaux conceptuels appliqués à l'apprentissage automatique des machines, par Patrice Boucher
Automne 2023 - En codirection avec : Alessandro Lameiras Koerich
Towards Reliable Data-Driven Sound Recognition Models: Developing Attack and Defense Algorithms, par Mohammad Esmaeilpour
Hiver 2022 - En codirection avec : Alessandro Lameiras Koerich
End-to-End Deep Learning for Audio Classification: From Waveforms to a Security Perspective, par Sajjad Abdoli
Automne 2021 - En codirection avec : Éric Granger
Deep Regression Models for Spatio-temporal Expression Recognition in Videos, par Gnanapraveen Rajasekhar
Été 2023
- En codirection avec : Pierre Dumouchel
Implémentation de l'algorithme SOLA - modification de l'échelle de temps en codage de moyenne à bas debit, par Freud Abner Romero
Automne 2015
- Valorisation des données pour améliorer la reconnaissance de la parole en français québécois, par Amira Morsli
Hiver 2024
- Développement de composantes d'extraction de contenu sémantique à partir d'enregistrements audio, en vue de leur application à la lutte contre la désinformation, par Amira Morsli
Hiver 2024
- Conception d'une Application de Conseil Psychologique Basée sur les LLM, par Joseph Corbin
Été 2024
Publications
- R. Gnana Praveen, Patrick Cardinal, Eric Granger. 2023 « Audio-visual fusion for emotion recognition in the valence-arousal space using joint cross-attention ». IEEE Transactions on Biometrics, Behavior, and Identity Science vol. 5 , nº 3. p. 360-373
- Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich. 2022 « From environmental sound representation to robustness of 2D CNN models against adversarial attacks ». Applied Acoustics vol. 195
- Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich. 2022 « Multidiscriminator sobolev defense-GAN against adversarial attacks for end-to-end speech systems ». IEEE Transactions on Information Forensics and Security vol. 17. p. 2044-2058
- Mohammad Esmaeilpour, Nourhene Chaalia, Adel Abusitta, Franois-Xavier Devailly, Wissem Maazoun, Patrick Cardinal. 2022 « Bi-discriminator GAN for tabular data synthesis ». Pattern Recognition Letters vol. 159. p. 204-210
- Mohammad Esmaeilpour, Nourhene Chaalia, Patrick Cardinal. 2022 « RSD-GAN: Regularized sobolev defense GAN against speech-to-text adversarial attacks ». IEEE Signal Processing Letters vol. 29. p. 1998-2002
- Philippe Chabot, Rachel E. Bouserhal, Patrick Cardinal, Jérémie Voix. 2021 « Detection and classification of human-produced nonverbal audio events ». Applied Acoustics vol. 171
- Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich. 2021 « Cyclic defense GAN against speech adversarial attacks ». IEEE Signal Processing Letters vol. 28. p. 1769-1773
- Gnana Praveen Rajasekhar, Eric Granger, Patrick Cardinal. 2021 « Deep domain adaptation with ordinal regression for pain assessment using weakly-labeled videos ». Image and Vision Computing vol. 110
- Marie-Michèle Dufour, Marc J. Lanovaz, Patrick Cardinal. 2020 « Artificial intelligence for the measurement of vocal stereotypy ». Journal of the Experimental Analysis of Behavior vol. 114 , nº 3. p. 368-380
- Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich. 2020 « A robust approach for securing audio classification against adversarial attacks ». IEEE Transactions on Information Forensics and Security vol. 15 , nº 1. p. 2147-2159
- Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich. 2020 « Unsupervised feature learning for environmental sound classification using Weighted Cycle-Consistent Generative Adversarial Network ». Applied Soft Computing vol. 86
- Sajjad Abdoli, Patrick Cardinal, Alessandro Lameiras Koerich. 2019 « End-to-end environmental sound classification using a 1D convolutional neural network ». Expert Systems with Applications vol. 136. p. 252-263
- Marc J. Lanovaz, Patrick Cardinal, Mary Francis. 2019 « Using a visual structured criterion for the analysis of alternating-treatment designs ». Behavior Modification vol. 43 , nº 1. p. 115-131
- Marc J. Lanovaz, Stéphanie Turgeon, Patrick Cardinal, Tara L. Wheatley. 2019 « Using single-case designs in practical settings: Is within-subject replication always necessary? ». Perspectives on Behavior Science vol. 42 , nº 1. p. 153-162
- Patrick Cardinal, Pierre Dumouchel, Gilles Boulianne. 2013 « Large vocabulary speech recognition on parallel architectures ». IEEE Transactions on Audio, Speech, and Language Processing vol. 21 , nº 11. p. 2290-2300
- Vishwa Nath Gupta, Gilles Boulianne, Patrick Cardinal. 2012 « CRIM’s content-based audio copy detection system for TRECVID 2009 ». Multimedia Tools and Applications vol. 60 , nº 2. p. 371-387
- Vishwa Gupta, Gilles Boulianne, Patrick Cardinal. 2014-09-09 « Content based audio copy detection ». Brevet américain US 8,831,760.
- Mohammed Senoussaoui, Milton O. Saria-Paja, Patrick Cardinal, Tiago H. Falk, François Michaud. 2020 « State-of-the-art speaker recognition methods applied to speakers with dysarthria ». In Voice Technologies for Speech Reconstruction and Enhancement. p. 7-34. De Gruyter
- Gilles Boulianne, Jean-François Beaumont, Maryse Boisvert, Julie Brousseau, Patrick Cardinal, Claude Chapdelaine, Michel Comeau, Pierre Ouellet, Frédéric Osterrath, Pierre Dumouchel. 2010 « Shadow speaking for real-time closed-captioning of TV broadcasts in french ». In Listening to subtitles : subtitles for the deaf and hard of hearing . Peter Lang International Academic Professional Publishers
- Rachel Bouserhal, Milton Sarria-Paja, Patrick Cardinal, Jérémie Voix. 2019 « Classification of nonverbal human produced audio events: a pilot study ». Communication lors de la conférence : National Hearing Conservation Association Annual Conference 2019 (Grapevine, TX, USA, Feb. 07-09, 2019)
- Rachel Bouserhal, Milton Sarria-Paja, Patrick Cardinal, Jérémie Voix. 2018 « Classification of nonverbal human produced audio events: a pilot study ». Communication lors de la conférence : Workshop on machine hearing and learning (Montreal, QC, Canada, Sept. 21, 2018)
- R. Gnana Praveen, Eric Granger, Patrick Cardinal. 2023 « Recursive joint attention for audio-visual fusion in regression based emotion recognition ». IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (Rhodes Island, Greece, June 04-10, 2023) Institute of Electrical and Electronics Engineers Inc.
- Guillaume Simard, Cédric Melançon, Patrick Cardinal, Julien Gascon-Samson. 2023 « Performance characterization of MQTT brokers in a device-local edge deployment ». MiddleWEdge 2023 - Proceedings of the 2nd International Workshop on Middleware for the Edge (Bologna, Italia, Dec. 11, 2023) Association for Computing Machinery, Inc
- Guillaume Baril, Patrick Cardinal, Alessandro Lameiras Koerich. 2022 « Named entity recognition for audio de-identification ». International Joint Conference on Neural Networks (IJCNN) (Padua, Italy, July 18-23, 2022) Institute of Electrical and Electronics Engineers Inc.
- Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich. 2022 « Towards robust speech-to-text adversarial attack ». 47th IEEE International Conference on Acoustics, Speech, and Signal Processing (Singapore, Singapore, May 23-27, 2022) Institute of Electrical and Electronics Engineers Inc.
- R. G. Praveen, W. C. de Melo, N. Ullah, H. Aslam, O. Zeeshan, T. Denorme, M. Pedersoli, A. L. Koerich, S. Bacon, P. Cardinal, E. Granger. 2022 « A joint cross-attention model for audio-visual fusion in dimensional emotion recognition ». IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (New Orleans, LA, USA, June 19-20, 2022) IEEE
- Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich. 2021 « Class-conditional defense GaN against end-to-end speech attacks ». IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (Toronto, ON, Canada - En ligne, June 06-11,, 2021) Institute of Electrical and Electronics Engineers Inc.
- R. Gnana Praveen, Eric Granger, Patrick Cardinal. 2021 « Cross attentional audio-visual fusion for dimensional emotion recognition ». 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021) (Jodhpur, India, Dec. 15-18, 2021) Institute of Electrical and Electronics Engineers Inc.
- Mirmohammad Saadati, Marco Pedersoli, Patrick Cardinal, Peter Oliver. 2021 « RADARSAT-2 Synthetic-Aperture radar land cover segmentation using deep convolutional neural networks ». Pattern Recognition. ICPR International Workshops and Challenges, Virtual Event, January 10-15, 2021, Proceedings Part VIII (Milan, Italy, Jan. 10-15, 2021) Springer
- Gnana R. Praveen, Eric Granger, Patrick Cardinal. 2020 « Deep weakly supervised domain adaptation for pain localization in videos ». 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG) (Buenos Aires, Argentina, Nov. 16-20, 2020) IEE Computer Society
- Raymel Alfonso Sallo, Mohammad Esmaeilpour, Patrick Cardinal. 2020 « Adversarially training for audio classifiers ». 25th International Conference on Pattern Recognition (ICPR) (Milan, Italy, Jan. 10-15, 2021) IEEE
- Masih Aminbeidokhti, Marco Pedersoli, Patrick Cardinal, Eric Granger. 2019 « Emotion recognition with spatial attention and temporal softmax pooling ». Image Analysis and Recognition : 16th International Conference, ICIAR : Proceedings (Waterloo, ON, Canada, Aug. 27-29, 2019) Springer International Publishing
- Juan D. S. Ortega, Patrick Cardinal, Alessandro L. Koerich. 2019 « Emotion recognition using fusion of audio and video features ». IEEE International Conference on Systems, Man and Cybernetics (SMC) (Bari, Italy, Oct. 06-09, 2019) Institute of Electrical and Electronics Engineers Inc.
- Rachel E. Bouserhal, Philippe Chabot, Milton Sarria-Paja, Patrick Cardinal, Jérémie Voix. 2018 « Classification of nonverbal human produced audio events: A pilot study ». 19th Annual Conference of the International Speech Communication (INTERSPEECH 2018) (Hyderabad, India, Sept. 02-06, 2018) International Speech Communication Association
- I. Verduyckt, P. Cardinal, A. Loubnani, A. Alpan. 2017 « MyOrtho – A vocal coach application with visual feed-back for monitoring and storing of patient progress in a home environment ». 10th International Workshop Models and Analysis of Vocal Emissions for Biomedical Applications (Firenze, Italy, Dec. 13-15, 2017) Firenze University Press
- Ahmed Ali, Najim Dehak, Patrick Cardinal, Sameer Khurana, Sree Harsha Yella, James Glass, Peter Bell, Steve Renals. 2016 « Automatic dialect detection in Arabic broadcast speech ». 17th Annual Conference of the International Speech Communication Association, (INTERSPEECH) (San Francisco, CA, USA, Sept. 08-16, 2016) International Speech and Communication Association
- Patrice Boucher, Pierre Dufour, Pierrich Plusquellec, Najim Dehak, Pierre Dumouchel, Patrick Cardinal. 2016 « PHYSIOSTRESS: A multimodal corpus of data on acute stress and physiological activation ». Workshop on Multimodal Corpora : Computer vision and language processing (MMC 2016) (Portoroz, Slovenia, May 23-28, 2016) European Language Resources Association (ELRA)
- Mohammed Senoussaoui, Patrick Cardinal, Najim Dehak, Alessandro L. Koerich. 2016 « Native language detection using the i-vector framework ». 17th Annual Conference of the International Speech Communication Association (INTERSPEECH) (San Francisco, CA, USA, Sept. 08-16, 2016) International Speech and Communication Association
- Simon Boutin, Réal Tremblay, Patrick Cardinal, Doug Peters, Pierre Dumouchel. 2015 « Audio quotation marks for natural language understanding ». INTERSPEECH 2015. 16th Annual Conference of the International Speech Communication Association (Dresden, Germany, Sept. 6-10, 2015) International Speech Communication Association
- Patrick Cardinal, Najim Dehak, Alessandro Koerich Lameiras, Jahangir Alam, Patrice Boucher. 2015 « ETS System for AV+EC 2015 Challenge ». Proceedings of the 5th International Workshop on Audio/Visual Emotion Challenge (Brisbane, Australia, Oct. 26-30, 2015) ACM
- Patrick Cardinal, Najim Dehak, Yu Zhang, James Glass. 2015 « Speaker adaptation using the I-vector technique for bottleneck features ». INTERSPEECH 2015. 16th Annual Conference of the International Speech Communication Association (Dresden, Germany, Sept. 6-10, 2015) International Speech Communication Association
- Ahmed Ali, Yifan Zhang, Patrick Cardinal, Najim Dehak, Stephan Vogel, James Glass. 2014 « A complete KALDI recipe for building Arabic speech recognition systems ». 2014 IEEE Spoken Language Technology Workshop (STL) (South Lake Tahoe, NV, USA, Dec. 7-10, 2014) IEEE
- Patrick Cardinal, Ahmed Ali, Najim Dehak, Yu Zhang, Tuka Al Hanai, Yifan Zhang, James R. Glass, Stephan Vogel. 2014 « Recent advances in ASR applied to an Arabic transcription system for Al-Jazeera ». INTERSPEECH 2014. 15th Annual Conference of the International Speech Communication Association (Singapore, Singapore, Sept. 14-18, 2014) International Speech Communication Association
- Patrick Cardinal, Gilles Boulianne, Pierre Dumouchel. 2012 « The A* speech recognition system on parallel architectures ». 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA) (Montreal, QC, Canada, July 2-5, 2012) IEEE Computer Society
- Patrick Cardinal, Gilles Boulianne, Pierre Dumouchel. 2012 « Using A* for the parallelization of speech recognition systems ». 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (Kyoto, Japan, Mar. 25-30, 2012) Institute of Electrical and Electronics Engineers Inc.
- Patrick Cardinal, Vishwa Gupta, Gilles Boulianne. 2010 « Content-based advertisement detection ». INTERSPEECH 2010. 11th Annual Conference of the International Speech Communication Association (Chiba, Makuhari, Japan, Sept. 26-30, 2010) International Speech Communication Association
- Vishwa Gupta, Gilles Boulianne, Patrick Cardinal. 2010 « CRIM's content-based audio copy detection system for TRECVID 2009 ». 2010 International Workshop on Content-Based Multimedia Indexing (CBMI) (Grenoble, France, June 23-25, 2010) IEEE
- Vishwa Gupta, Gilles Boulianne, Patrick Cardinal. 2010 « Content-based audio copy detection using nearest-neighbor mapping ». 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) (Dallas, TX, USA, Mar. 14-19, 2010) IEEE
- Patrick Cardinal, Gilles Boulianne. 2009 « Real-time correction of closed-captions ». INTERSPEECH 2009 - 10th Annual Conference of the International Speech Communication Association (Brighton, UK, Sept. 6-10, 2009) International Speech and Communication Association
- Patrick Cardinal, Pierre Dumouchel, Gilles Boulianne. 2009 « Using parallel architectures in speech recognition ». INTERSPEECH 2009 - 10th Annual Conference of the International Speech Communication Association (Brighton, UK, Sept. 6-10, 2009) International Speech and Communication Association
- Maguelonne Héritier, Vishwa Gupta, Langis Gagnon, Gilles Boulianne, Samuel Foucher, Patrick Cardinal. 2009 « CRIM's content-based copy detection system for TRECVID ». 2009 TREC Video Retrieval Evaluation Notebook Papers (Gaithesburg, MD, USA, Nov. 16, 2009) National Institute of Standards and Technology
- Patrick Cardinal, Pierre Dumouchel, Gilles Boulianne, Michel Comeau. 2008 « GPU accelerated acoustics likelihood computations ». 9th Annual Conference of the International Speech Communication Association (INTERSPEECH) (Brisbane, Australia, Sept. 22-26, 2008) International Speech Communication Association
- P. Cardinal, G. Boulianne, M. Comeau, M. Boisvert. 2007 « Real-time correction of closed captions ». Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics (Prague, Czech Republic, June 24-29, 2007) Association for Computational Linguistics (ACL)
- G. Boulianne, J.-F. Beaumont, M. Boisvert, J. Brousseau, P. Cardinal, C. Chapdelaine, M. Comeau, P. Ouellet, F. Osterrath. 2006 « Computer-assisted closed-captioning of live TV broadcasts in French ». INTERSPEECH 2006 : ICSLP ; Proceedings of the Ninth International Conference on Spoken Language Processing (Pittsburgh, PA, USA, Sept. 17-21, 2006) International Speech and Communication Association
- Patrick Cardinal, Gilles Boulianne, Michel Comeau. 2005 « Segmentation of recordings based on partial transcriptions ». Proceedings of the 9th European Conference on Speech Communication and Technology (Interspeech'2005-Eurospeech) (Lisbon, Portugal, Sept. 4-8, 2005) International Speech and Communication Association
- Gilles Boulianne, Jean-François Beaumont, Patrick Cardinal, Michel Comeau, Pierre Ouellet, Pierre Dumouchel. 2003 « Automatic segmentation of film dialogues into phonemes and graphemes ». Proceedings of the 8th European Conference on Speech Communication and Technology (Eurospeech 2003) (Geneva, Switzerland, Sept. 1-4, 2003) International Speech and Communication Association
- Julie Brousseau, Jean-François Beaumont, Gilles Boulianne, Patrick Cardinal, Claude Chapdelaine, Michel Comeau, Frédéric Osterrath, Pierre Ouellet. 2003 « Automated closed-captioning of live TV broadcast news in French ». Proceedings of the 8th European Conference on Speech Communication and Technology (Eurospeech 2003) (Geneva, Switzerland, Sept. 1-4, 2003) International Speech and Communication Association
- N. Smaili, P. Cardinal, G. Boulianne, P. Dumouchel. 2002 « Disambiguation of finite-state transducers ». Proceedings of the 19th International Conference on Computational Linguistics (COLING2002) (Taipei, Taiwan, Aug. 26-30, 2002) Association for Computational Linguistics (ACL)
- Patrick Cardinal. 2013 « Speech recognition on multi-core processors and GPUs ». 145 p.Thèse de doctorat. Montréal, (Québec), École de technologie supérieure.
- Patrick Cardinal. 2003 « Finite-state transducers and speech recognition ». Mémoire de maîtrise. McGill University.
- Patrick Cardinal. 2006 « E-Inclusion core speech forward-backward algorithm ». Centre de recherche informatique de Montréal. 6 p.