Mirco Ravanelli

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

Allan Allan

Undergraduate - Concordia University

Séverin Baroudi

Collaborating researcher - Toulon University

Gaspard Botté

Research Intern - Concordia University

Cordelle Briac

Master's Research - Concordia University University

Leo Brodeur

Master's Research - Concordia University

Matthieu Cervera

Principal supervisor :

Victor Cruz

Master's Research - Concordia University

Luca Della Libera

PhD - Concordia University

Co-supervisor :

Wagner Drew

Master's Research - Concordia University

Co-supervisor :

Irina Rish

Gianfranco Dumoulin Bertucci

Master's Research - Concordia University

Nadine El-Mufti

Master's Research - Concordia University

Maab Elrashid Ahmed Mohamed

PhD - Concordia University

Co-supervisor :

Bonzi Francesco

PhD - Concordia University

Salman Sami Hussain Ali

Master's Research - Concordia University University

Lovenya Jain

Research Intern - Université Laval

Principal supervisor :

PhD - Université Laval

Principal supervisor :

Haoyu Li

Professional Master's - Concordia University Univesity

Eleonora Mancini

Collaborating Alumni - Université de Montréal

Principal supervisor :

Collaborating researcher - University of Toulon

Principal supervisor :

Pierfrancesco Melucci

Research Intern - Concordia University

PhD - Université de Montréal

PhD - Concordia University

PhD - Concordia University

Co-supervisor :

Peter Peter

Postdoctorate - McGill University

PhD - Université de Montréal

Benjamin Van Niekerk

Postdoctorate - Concordia University

FocalCodec: Giving LLMs Ears and a Voice at Ultra-Low Bitrates

Blog Posts

Visual of FocalCodec,nouvelle méthode pour compresser la parole sans sacrifier la qualité, en vue d'obtenir des LLM multimodaux plus efficaces.

January 23, 2026

Luca Della Libera

Francesco Paissan

Cem Subakan

Mirco Ravanelli

Read the article

June 13, 2024

SpeechBrain 1.0: Making Conversational AI Accessible to Everyone

Mirco Ravanelli

Read the article

April 28, 2021

Introducing SpeechBrain: A General-Purpose PyTorch Speech Processing Toolkit

Mirco Ravanelli

Loren Lugosch

Read the article

Publications

RescueSpeech: A German Corpus for Speech Recognition in Search and Rescue Domain

Sangeet Sagar

Bernd Kiefer

Ivana Kruijff-Korbayová

Josef van Genabith

Despite the recent advancements in speech recognition, there are still difficulties in accurately transcribing conversational and emotional … (see more)speech in noisy and reverberant acoustic environments. This poses a particular challenge in the search and rescue (SAR) domain, where transcribing conversations among rescue team members is crucial to support real-time decision-making. The scarcity of speech data and associated background noise in SAR scenarios make it difficult to deploy robust speech recognition systems. To address this issue, we have created and made publicly available a German speech dataset called RescueSpeech. This dataset includes real speech recordings from simulated rescue exercises. Additionally, we have released competitive training recipes and pre-trained models. Our study highlights that the performance attained by state-of-the-art methods in this challenging scenario is still far from reaching an acceptable level.

2023-12-15

2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (published)

Speech Emotion Diarization: Which Emotion Appears When?

Yingzhi Wang

Alaa Nfissi

Alya Yacoubi

Speech Emotion Recognition (SER) typically relies on utterance-level solutions. However, emotions conveyed through speech should be consider… (see more)ed as discrete speech events with definite temporal boundaries, rather than attributes of the entire utterance. To reflect the fine-grained nature of speech emotions, we propose a new task: Speech Emotion Diarization (SED). Just as Speaker Diarization answers the question of "Who speaks when?", Speech Emotion Diarization answers the question of "Which emotion appears when?". To facilitate the evaluation of the performance and establish a common benchmark for researchers, we introduce the Zaion Emotion Dataset (ZED), an openly accessible speech emotion dataset that includes non-acted emotions recorded in real-life conditions, along with manually-annotated boundaries of emotion segments within the utterance. We provide competitive baselines and open-source the code and the pre-trained models.

2023-12-15

2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) (published)

Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets (Ultra Large Dataset)

Dominique Beaini

Shenyang Huang

Joao Alex Cunha

Zhiyi Li

Gabriela Moisescu-Pareja

Oleksandr Dymov

Samuel Maddrell-Mander

Callum McLean

Ali Parviz

Luis T. Díaz Müller

Jama Hussein Mohamud

Michael Craig

Cristian Gabellini

Jian Tang … (see 8 more)

Christopher G. Morris

Guy Wolf

Prudencio Tossou

Hadrien Mary

Błażej Banaszewski

Chad Martin

Dominic Masters

2023-09-21

Zenodo (unknown)

Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?

Salah Zaiem

Youcef Kemiche

Titouan Parcollet

Slim Essid

Self-supervised learning (SSL) has recently allowed leveraging large datasets of unlabeled speech signals to reach impressive performance on… (see more) speech tasks using only small amounts of annotated data. The high number of proposed approaches fostered the need and rise of extended benchmarks that evaluate their performance on a set of downstream tasks exploring various aspects of the speech signal. However, and while the number of considered tasks has been growing, most rely upon a single decoding architecture that maps the frozen SSL representations to the downstream labels. This work investigates the robustness of such benchmarking results to changes in the decoder architecture. Interestingly, it appears that varying the architecture of the downstream decoder leads to significant variations in the leaderboards of most tasks. Concerningly, our study reveals that benchmarking using limited decoders may cause a counterproductive increase in the sizes of the developed SSL models.

2023-08-19

INTERSPEECH 2023 (published)

Simulated Annealing in Early Layers Leads to Better Generalization

Amir M. Sarfi

Zahra Karimpour

Muawiz Chaudhary

Nasir M. Khalid

Sudhir Mudur

Eugene Belilovsky

Recently, a number of iterative learning methods have been introduced to improve generalization. These typically rely on training for longer… (see more) periods of time in exchange for improved generalization. LLF (later-layer-forgetting) is a state-of-the-art method in this category. It strengthens learning in early layers by periodically re-initializing the last few layers of the network. Our principal innovation in this work is to use Simulated annealing in EArly Layers (SEAL) of the network in place of re-initialization of later layers. Essentially, later layers go through the normal gradient descent process, while the early layers go through short stints of gradient ascent followed by gradient descent. Extensive experiments on the popular Tiny-ImageNet dataset benchmark and a series of transfer learning and few-shot learning tasks show that we outperform LLF by a significant margin. We further show that, compared to normal training, LLF features, although improving on the target task, degrade the transfer learning performance across all datasets we explored. In comparison, our method outperforms LLF across the same target datasets by a large margin. We also show that the prediction depth of our method is significantly lower than that of LLF and normal training, indicating on average better prediction performance.

2023-06-16

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (published)

Fine-Tuning Strategies for Faster Inference Using Speech Self-Supervised Models: A Comparative Study

Salah Zaiem

Robin Algayres

Titouan Parcollet

Slim Essid

Self-supervised learning (SSL) has allowed substantial progress in Automatic Speech Recognition (ASR) performance in low-resource settings. … (see more)In this context, it has been demonstrated that larger self-supervised feature extractors are crucial for achieving lower downstream ASR error rates. Thus, better performance might be sanctioned with longer inferences. This article explores different approaches that may be deployed during the fine-tuning to reduce the computations needed in the SSL encoder, leading to faster inferences. We adapt a number of existing techniques to common ASR settings and benchmark them, displaying performance drops and gains in inference times. Interestingly, we found that given enough downstream data, a simple downsampling of the input sequences outperforms the other methods with both low performance drops and high computational savings, reducing computations by 61.3% with an WER increase of only 0.81. Finally, we analyze the robustness of the comparison to changes in dataset conditions, revealing sensitivity to dataset size.

2023-06-03

2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) (published)

Exploring Self-Attention Mechanisms for Speech Separation

Samuele Cornell

François Grondin

Mirko Bronzi

Transformers have enabled impressive improvements in deep learning. They often outperform recurrent and convolutional models in many tasks w… (see more)hile taking advantage of parallel processing. Recently, we proposed the SepFormer, which obtains state-of-the-art performance in speech separation with the WSJ0-2/3 Mix datasets. This paper studies in-depth Transformers for speech separation. In particular, we extend our previous findings on the SepFormer by providing results on more challenging noisy and noisy-reverberant datasets, such as LibriMix, WHAM!, and WHAMR!. Moreover, we extend our model to perform speech enhancement and provide experimental evidence on denoising and dereverberation tasks. Finally, we investigate, for the first time in speech separation, the use of efficient self-attention mechanisms such as Linformers, Lonformers, and ReFormers. We found that they reduce memory requirements significantly. For example, we show that the Reformer-based attention outperforms the popular Conv-TasNet model on the WSJ0-2Mix dataset while being faster at inference and comparable in terms of memory consumption.

2022-12-31

IEEE/ACM Transactions on Audio, Speech, and Language Processing (published)

Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads

Salah Zaiem

Youcef Kemiche

Titouan Parcollet

Slim Essid

Self-supervised learning (SSL) leverages large datasets of unlabeled speech to reach impressive performance with reduced amounts of annotate… (see more)d data. The high number of proposed approaches fostered the emergence of comprehensive benchmarks that evaluate their performance on a set of downstream tasks exploring various aspects of the speech signal. However, while the number of considered tasks has been growing, most proposals rely upon a single downstream architecture that maps the frozen SSL representations to the task labels. This study examines how benchmarking results are affected by changes in the probing head architecture. Interestingly, we found that altering the downstream architecture structure leads to significant fluctuations in the performance ranking of the evaluated models. Against common practices in speech SSL benchmarking, we evaluate larger-capacity probing heads, showing their impact on performance, inference costs, generalization and multi-level feature exploitation.

2022-12-31

arXiv (preprint)

OSSEM: One-Shot Speaker Adaptive Speech Enhancement Using Meta Learning

Cheng Yu

Szu-wei Fu

Tsun-An Hsieh

Yu Tsao

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.

2022-09-17

Interspeech 2022 (published)

SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation

Artem Ploujnikov

End-to-end speech synthesis models directly convert the input characters into an audio representation (e.g., spectrograms). Despite their im… (see more)pressive performance, such models have difficulty disambiguating the pronunciations of identically spelled words. To mitigate this issue, a separate Grapheme-to-Phoneme (G2P) model can be employed to convert the characters into phonemes before synthesizing the audio. This paper proposes SoundChoice, a novel G2P architecture that processes entire sentences rather than operating at the word level. The proposed architecture takes advantage of a weighted homograph loss (that improves disambiguation), exploits curriculum learning (that gradually switches from word-level to sentence-level G2P), and integrates word embeddings from BERT (for further performance improvement). Moreover, the model inherits the best practices in speech recognition, including multi-task learning with Connectionist Temporal Classification (CTC) and beam search with an embedded language model. As a result, SoundChoice achieves a Phoneme Error Rate (PER) of 2.65% on whole-sentence transcription using data from LibriSpeech and Wikipedia. Index Terms grapheme-to-phoneme, speech synthesis, text-tospeech, phonetics, pronunciation, disambiguation.

2022-09-17

Interspeech 2022 (published)

Real-M: Towards Speech Separation on Real Mixtures

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. The performance predictions of the SI-SNR estimator indeed correlate well with human opinions. Moreover, we observe that the performance trends predicted by our estimator on the REAL-M dataset closely follow those achieved on synthetic benchmarks when evaluating popular speech separation models.

2022-05-22

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (published)

Learning Representations for New Sound Classes With Continual Self-Supervised Learning

Zhepei Wang

Xilin Jiang

Junkai Wu

Efthymios Tzinis

Paris Smaragdis

In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framewor… (see more)k 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.

2021-12-31

IEEE Signal Processing Letters (published)