P
Patrick Cardinal
Researcher at École de technologie supérieure
Publications - 79
Citations - 1287
Patrick Cardinal is an academic researcher from École de technologie supérieure. The author has contributed to research in topics: Computer science & Audio signal. The author has an hindex of 17, co-authored 71 publications receiving 945 citations. Previous affiliations of Patrick Cardinal include Université du Québec & Massachusetts Institute of Technology.
Papers
More filters
Journal ArticleDOI
End-to-End Environmental Sound Classification using a 1D Convolutional Neural Network
TL;DR: An end-to-end approach for environmental sound classification based on a 1D Convolution Neural Network that learns a representation directly from the audio signal that outperforms most of the state-of-the-art approaches that use handcrafted features or 2D representations as input.
Proceedings ArticleDOI
A complete KALDI recipe for building Arabic speech recognition systems
TL;DR: A prototype broadcast news system using 200 hours GALE data that is publicly available through LDC and the first effort to share reproducible sizable training and testing results on MSA system is shared.
Proceedings ArticleDOI
Automatic Dialect Detection in Arabic Broadcast Speech
Ahmed Ali,Najim Dehak,Najim Dehak,Patrick Cardinal,Sameer Khurana,Sree Harsha Yella,James Glass,Peter Bell,Steve Renals +8 more
TL;DR: This work investigates different approaches for dialect identification in Arabic broadcast speech, using phonetic, lexical features obtained from a speech recognition system, and acoustic features using the i-vector framework, and combined these features using a multi-class Support Vector Machine (SVM).
Posted Content
Automatic Dialect Detection in Arabic Broadcast Speech
Ahmed Ali,Najim Dehak,Najim Dehak,Patrick Cardinal,Sameer Khurana,Sree Harsha Yella,James Glass,Peter Bell,Steve Renals +8 more
TL;DR: In this paper, the authors investigated different approaches for dialect identification in Arabic broadcast speech, using phonetic, lexical features obtained from a speech recognition system, and acoustic features using the i-vector framework.
Journal ArticleDOI
A Robust Approach for Securing Audio Classification Against Adversarial Attacks
TL;DR: A novel approach based on pre-processed DWT representation of audio signals and SVM to secure audio systems against adversarial attacks and shows competitive performance compared to the deep neural networks both in terms of accuracy and robustness against strong adversarial attack.