Idiap at ICASSP 2021
Idiap's speech group will be presenting six papers at ICASSP 2021. Our papers address a variety of research problems in pathological and physiological speech processing, automatic speech recognition, and machine learning.
Accepted papers:
- Lattice-free MMI adaptation of self-supervised pretrained acoustic models from Apoorv Vyas, Srikanth Madikeri, and Hervé Bourlard
- On the relationship between speech-based breathing signal prediction evaluation measures and breathing parameters estimation from Zohreh Mostaani, Venkata Srikanth Nallanthighal, Aki Härmä, Helmer Strik, and Mathew Magimai-Doss
- Automatic and perceptual discrimination between dysarthria, apraxia of speech, and neurotypical speech from Ina Kodrasi, Michaela Pernon, Marina Laganaro, and Hervé Bourlard
- A comparison of methods for OOV-word recognition on a new public dataset from Rudolf Braun, Srikanth Madikeri, and Petr Motlicek
- Automatic dysarthric speech detection exploiting pairwise distance-based convolutional neural networks from Parvaneh Janbakhshi, Ina Kodrasi, and Hervé Bourlard
- A Bayesian interpretation of the light gated recurrent unit from Alexandre Bittar and Philip N. Garner