Portrait of Mirco Ravanelli

Mirco Ravanelli

Associate Academic Member
Assistant Professor, Concordia University, Gina Cody School of Engineering and Computer Science
Adjunct Professor, Université de Montréal, Department of Computer Science and Operations Research
Website
Google Scholar
LinkedIn
X

Biography

Mirco Ravanelli is an assistant professor at Concordia University, adjunct professor at Université de Montréal and associate member of Mila – Quebec Artificial Intelligence Institute.

Ravanelli is an expert in deep learning and conversational AI, publishing over sixty papers in these fields. His contributions were honoured with a 2022 Amazon Research Award.

His research focuses primarily on novel deep learning algorithms, including self-supervised, continual, multimodal, cooperative and energy-efficient learning.

Formerly a postdoctoral fellow at Mila under Yoshua Bengio, he founded and now leads SpeechBrain, one of the most extensively used open-source toolkits in the field of speech processing and conversational AI.

Current Students

Arian Morteza
PhD - Concordia University
arian.morteza@mila.quebec
Website
Github
Google Scholar
Artem Ploujnikov
PhD - Université de Montréal
artem.ploujnikov@mila.quebec
Cordelle Briac
Collaborating researcher - Concordia University University
briac.cordelle@mila.quebec
Ritika Dhamija Ritika
Collaborating researcher - Concordia University University
dhamija.ritika@mila.quebec
Github
Eleonora Mancini
Research Intern - Université de Montréal
Principal supervisor :
Cem (Yusuf) Subakan
eleonora.mancini@mila.quebec
Github
Google Scholar
Fırat Öncel
PhD - Concordia University
Co-supervisor :
Laurent Charlin
firat.oncel@mila.quebec
Website
Github
Google Scholar
Gianfranco Dumoulin
Master's Research - Concordia University
gianfranco.bertucci@mila.quebec
Website
Github
Hiba Akhaddar
Master's Research - Concordia University
hiba.akhaddar@mila.quebec
Jama Mohamud
PhD - Université de Montréal
Co-supervisor :
Yoshua Bengio
hussein-mohamu.jama@mila.quebec
Website
Github
Google Scholar
Luca Della Libera
PhD - Concordia University
Co-supervisor :
Cem (Yusuf) Subakan
luca.dellalibera@mila.quebec
Github
Pooneh Mousavi
PhD - Concordia University
pooneh.mousavi@mila.quebec
Website
Github
Google Scholar
Salman Sami Hussain Ali
Collaborating researcher - Concordia University University
salman.hussainali@mila.quebec
Github
Seina Assadian
Collaborating researcher - Concordia University University
seina.assadian@mila.quebec
Github
Tristan Lueger Lueger
Collaborating researcher - Concordia University University
tristan.lueger@mila.quebec
Victor Cruz
Master's Research - Concordia University
victor.cruz@mila.quebec
Wagner Drew
Undergraduate - Concordia University
drew.wagner@mila.quebec
Github

Publications

Learning Representations for New Sound Classes With Continual Self-Supervised Learning
Zhepei Wang
Cem (Yusuf) Subakan
Xilin Jiang
Junkai Wu
Efthymios Tzinis
Mirco Ravanelli
Paris Smaragdis
In this article, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framew… (see more)ork where the model can be updated without relying on labeled data. For this purpose, we propose adopting representation learning, where an encoder is trained using unlabeled data. This learning framework enables the study and implementation of a practically relevant use case where only a small amount of the labels is available in a continual learning context. We also make the empirical observation that a similarity-based representation learning method within this framework is robust to forgetting even if no explicit mechanism against forgetting is employed. We show that this approach obtains similar performance compared to several distillation-based continual learning methods when employed on self-supervised representation learning methods.
2022-01-01
IEEE Signal Processing Letters (published)
doi.org
arxiv.org
OSSEM: one-shot speaker adaptive speech enhancement using meta learning
Cheng Yu
Szu‐wei Fu
Tsun-An Hsieh
Yu-shan Tsao
Mirco Ravanelli
Although deep learning (DL) has achieved notable progress in speech enhancement (SE), further research is still required for a DL-based SE s… (see more)ystem to adapt effectively and efficiently to particular speakers. In this study, we propose a novel meta-learning-based speaker-adaptive SE approach (called OSSEM) that aims to achieve SE model adaptation in a one-shot manner. OSSEM consists of a modified transformer SE network and a speaker-specific masking (SSM) network. In practice, the SSM network takes an enrolled speaker embedding extracted using ECAPA-TDNN to adjust the input noisy feature through masking. To evaluate OSSEM, we designed a modified Voice Bank-DEMAND dataset, in which one utterance from the testing set was used for model adaptation, and the remaining utterances were used for testing the performance. Moreover, we set restrictions allowing the enhancement process to be conducted in real time, and thus designed OSSEM to be a causal SE system. Experimental results first show that OSSEM can effectively adapt a pretrained SE model to a particular speaker with only one utterance, thus yielding improved SE results. Meanwhile, OSSEM exhibits a competitive performance compared to state-of-the-art causal SE systems.
2021-11-10
ArXiv (preprint)
doi.org
arxiv.org
Real-M: Towards Speech Separation on Real Mixtures
Cem (Yusuf) Subakan
Mirco Ravanelli
Samuele Cornell
François Grondin
In recent years, deep learning based source separation has achieved impressive results. Most studies, however, still evaluate separation mod… (see more)els on synthetic datasets, while the performance of state-of-the-art techniques on in-the-wild speech data remains an open question. This paper contributes to fill this gap in two ways. First, we release the REAL-M dataset, a crowd-sourced corpus of real-life mixtures. Secondly, we address the problem of performance evaluation of real-life mixtures, where the ground truth is not available. We bypass this issue by carefully designing a blind Scale-Invariant Signal-to-Noise Ratio (SI-SNR) neural estimator. Through a user study, we show that our estimator reliably evaluates the separation performance on real mixtures, i.e. we observe that the performance predictions of the SI-SNR estimator correlate well with human opinions. Moreover, when evaluating popular speech separation models, we observe that the performance trends predicted by our estimator on the REAL-M dataset closely follow the performance trends achieved on synthetic benchmarks.
2021-10-20
ArXiv (preprint)
doi.org
arxiv.org