Portrait de Mirco Ravanelli

Mirco Ravanelli

Membre académique associé
ravanelm@mila.quebec
Professeur agrégé, Concordia University, École de génie et d'informatique Gina-Cody
Professeur associé, Université de Montréal, Département d'informatique et de recherche opérationnelle
Sujets de recherche
Apprentissage profond
Site web
Google Scholar
LinkedIn
X

Biographie

Mirco Ravanelli est professeur adjoint à l'Université Concordia, professeur associé à l'Université de Montréal et membre associé de Mila – Institut québécois d’intelligence artificielle. Lauréat du prix Amazon Research 2022, il est expert en apprentissage profond et en IA conversationnelle, et a publié plus de 60 articles dans ces domaines. Il se concentre principalement sur les nouveaux algorithmes d'apprentissage profond, y compris l'apprentissage autosupervisé, continu, multimodal, coopératif et économe en énergie. Mirco Ravanelli a effectué son postdoctorat à Mila, sous la direction du professeur Yoshua Bengio. Il est notamment le fondateur et le chef de file de SpeechBrain, l'une des boîtes à outils en code source ouvert les plus largement adoptées dans le domaine du traitement de la parole et de l'IA conversationnelle.

Étudiants actuels

Allan Allan
Baccalauréat - Concordia
heidari.allan@mila.quebec
Github
Séverin Baroudi
Collaborateur·rice de recherche - Toulon University
severin.baroudi@mila.quebec
Github
Google Scholar
Gaspard Botté
Stagiaire de recherche - Concordia
gaspard.botte@mila.quebec
Github
LinkedIn
Cordelle Briac
Maîtrise recherche - Concordia University
briac.cordelle@mila.quebec
Github
Google Scholar
Leo Brodeur
Maîtrise recherche - Concordia
leobrod44@gmail.com
Github
Matthieu Cervera
Collaborateur·rice de recherche
Superviseur⋅e principal⋅e :
Cem Subakan
matthieu.cervera@mila.quebec
Github
Victor Cruz
Maîtrise recherche - Concordia
victor.cruz@mila.quebec
Luca Della Libera
Doctorat - Concordia
Co-superviseur⋅e :
Cem Subakan
luca.dellalibera@mila.quebec
Github
Wagner Drew
Maîtrise recherche - Concordia
Co-superviseur⋅e :
Irina Rish
drew.wagner@mila.quebec
Github
Gianfranco Dumoulin Bertucci
Maîtrise recherche - Concordia
gianfranco.bertucci@mila.quebec
Site web
Github
Nadine El-Mufti
Maîtrise recherche - Concordia
nadine.el-mufti@mila.quebec
Site web
Github
Google Scholar
Maab Elrashid Ahmed Mohamed
Doctorat - Concordia
Co-superviseur⋅e :
Cem Subakan
maab-elrashid.ahmed-mohamed@mila.quebec
Github
Bonzi Francesco
Doctorat - Concordia
francesco.bonzi@mila.quebec
Github
Salman Sami Hussain Ali
Maîtrise recherche - Concordia University
salman.hussainali@mila.quebec
Github
Sidra Intikhab
Stagiaire de recherche - Concordia
sidra.intikhab@mila.quebec
Github
LinkedIn
Lovenya Jain
Collaborateur·rice de recherche - Université Laval
Superviseur⋅e principal⋅e :
Cem Subakan
f20211732@pilani.bits-pilani.ac.in
Github
LinkedIn
Google Scholar
Jihoon Jeong
Doctorat - Université Laval
Superviseur⋅e principal⋅e :
Cem Subakan
jihoon.jeong@mila.quebec
Site web
Google Scholar
Haoyu Li
Maîtrise professionnelle - Concordia Univesity
lihaoyuwilson@gmail.com
Site web
Eleonora Mancini
Collaborateur·rice alumni - UdeM
Superviseur⋅e principal⋅e :
Cem Subakan
eleonora.mancini@mila.quebec
Github
Google Scholar
Ricard Marxer
Collaborateur·rice de recherche - University of Toulon
Superviseur⋅e principal⋅e :
Pablo Piantanida
ricard.marxer@mila.quebec
Site web
Github
Google Scholar
Pierfrancesco Melucci
Stagiaire de recherche - Concordia
pierfrancesco.melucci@mila.quebec
Site web
Github
LinkedIn
Google Scholar
Jama Mohamud
Doctorat - UdeM
hussein-mohamu.jama@mila.quebec
Site web
Github
Google Scholar
Pooneh Mousavi
Doctorat - Concordia
pooneh.mousavi@mila.quebec
Site web
Github
Google Scholar
Fırat Öncel
Doctorat - Concordia
Co-superviseur⋅e :
Laurent Charlin
firat.oncel@mila.quebec
Site web
Github
Google Scholar
Peter Peter
Postdoctorat - McGill
plantinp@mila.quebec
Site web
Github
Google Scholar
Artem Ploujnikov
Doctorat - UdeM
artem.ploujnikov@mila.quebec
Raphael Switzer
Stagiaire de recherche - Concordia
raphael.switzer@mila.quebec
Github
LinkedIn
Benjamin Van Niekerk
Postdoctorat - Concordia
benjamin.l.van.niekerk@gmail.com
Github
Google Scholar

Publications

Learning Speaker Representations with Mutual Information
Mirco Ravanelli
Yoshua Bengio
Learning good representations is of crucial importance in deep learning. Mutual Information (MI) or similar measures of statistical dependen… (voir plus)ce are promising tools for learning these representations in an unsupervised way. Even though the mutual information between two random variables is hard to measure directly in high dimensional spaces, some recent studies have shown that an implicit optimization of MI can be achieved with an encoder-discriminator architecture similar to that of Generative Adversarial Networks (GANs). In this work, we learn representations that capture speaker identities by maximizing the mutual information between the encoded representations of chunks of speech randomly sampled from the same sentence. The proposed encoder relies on the SincNet architecture and transforms raw speech waveform into a compact feature vector. The discriminator is fed by either positive samples (of the joint distribution of encoded chunks) or negative samples (from the product of the marginals) and is trained to separate them. We report experiments showing that this approach effectively learns useful speaker representations, leading to promising results on speaker identification and verification tasks. Our experiments consider both unsupervised and semi-supervised settings and compare the performance achieved with different objective functions.
2019-09-12
Interspeech 2019 (publié)
doi.org
arxiv.org
The PyTorch-Kaldi Speech Recognition Toolkit
Mirco Ravanelli
Titouan Parcollet
Yoshua Bengio
The availability of open-source software is playing a remarkable role in the popularization of speech recognition and deep learning. Kaldi, … (voir plus)for instance, is nowadays an established framework used to develop state-of-the-art speech recognizers. PyTorch is used to build neural networks with the Python language and has recently spawn tremendous interest within the machine learning community thanks to its simplicity and flexibility. The PyTorch-Kaldi project aims to bridge the gap between these popular toolkits, trying to inherit the efficiency of Kaldi and the flexibility of PyTorch. PyTorch-Kaldi is not only a simple interface between these software, but it embeds several useful features for developing modern speech recognizers. For instance, the code is specifically designed to naturally plug-in user-defined acoustic models. As an alternative, users can exploit several pre-implemented neural networks that can be customized using intuitive configuration files. PyTorch-Kaldi supports multiple feature and label streams as well as combinations of neural networks, enabling the use of complex neural architectures. The toolkit is publicly-released along with a rich documentation and is designed to properly work locally or on HPC clusters. Experiments, that are conducted on several datasets and tasks, show that PyTorch-Kaldi can effectively be used to develop modern state-of-the-art speech recognizers.
2019-04-16
ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (publié)
doi.org
arxiv.org
Speaker Recognition from Raw Waveform with SincNet
Mirco Ravanelli
Yoshua Bengio
Deep learning is progressively gaining popularity as a viable alternative to i-vectors for speaker recognition. Promising results have been … (voir plus)recently obtained with Convolutional Neural Networks (CNNs) when fed by raw speech samples directly. Rather than employing standard hand-crafted features, the latter CNNs learn low-level speech representations from waveforms, potentially allowing the network to better capture important narrow-band speaker characteristics such as pitch and formants. Proper design of the neural network is crucial to achieve this goal. This paper proposes a novel CNN architecture, called SincNet, that encourages the first convolutional layer to discover more meaningful filters. SincNet is based on parametrized sinc functions, which implement band-pass filters. In contrast to standard CNNs, that learn all elements of each filter, only low and high cutoff frequencies are directly learned from data with the proposed method. This offers a very compact and efficient way to derive a customized filter bank specifically tuned for the desired application. Our experiments, conducted on both speaker identification and speaker verification tasks, show that the proposed architecture converges faster and performs better than a standard CNN on raw waveforms.
2018-12-17
2018 IEEE Spoken Language Technology Workshop (SLT) (publié)
doi.org
arxiv.org