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
Research Topics
Deep Learning

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

Master's Research - Concordia University
Collaborating researcher - Concordia University University
Collaborating researcher - Concordia University University
Master's Research - Concordia University
PhD - Concordia University
Co-supervisor :
Undergraduate - Concordia University
Master's Research - Concordia University
PhD - Concordia University
Collaborating researcher - Concordia University University
Collaborating researcher - Concordia University University
Research Intern - Université de Montréal
Principal supervisor :
PhD - Université de Montréal
Co-supervisor :
PhD - Concordia University
PhD - Concordia University
Co-supervisor :
Postdoctorate - McGill University
PhD - Université de Montréal
Collaborating researcher - Concordia University University

Publications

How Should We Extract Discrete Audio Tokens from Self-Supervised Models?
Pooneh Mousavi
Jarod Duret
Salah Zaiem
Luca Della Libera
Artem Ploujnikov
Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice
Listenable Maps for Zero-Shot Audio Classifiers
Francesco Paissan
Luca Della Libera
Interpreting the decisions of deep learning models, including audio classifiers, is crucial for ensuring the transparency and trustworthines… (see more)s of this technology. In this paper, we introduce LMAC-ZS (Listenable Maps for Audio Classifiers in the Zero-Shot context), which, to the best of our knowledge, is the first decoder-based post-hoc interpretation method for explaining the decisions of zero-shot audio classifiers. The proposed method utilizes a novel loss function that maximizes the faithfulness to the original similarity between a given text-and-audio pair. We provide an extensive evaluation using the Contrastive Language-Audio Pretraining (CLAP) model to showcase that our interpreter remains faithful to the decisions in a zero-shot classification context. Moreover, we qualitatively show that our method produces meaningful explanations that correlate well with different text prompts.
Focal Modulation Networks for Interpretable Sound Classification
The increasing success of deep neural networks has raised concerns about their inherent black-box nature, posing challenges related to inter… (see more)pretability and trust. While there has been extensive exploration of interpretation techniques in vision and language, interpretability in the audio domain has received limited attention, primarily focusing on post-hoc explanations. This paper addresses the problem of interpretability by-design in the audio domain by utilizing the recently proposed attention-free focal modulation networks (FocalNets). We apply FocalNets to the task of environmental sound classification for the first time and evaluate their interpretability properties on the popular ESC-50 dataset. Our method outperforms a similarly sized vision transformer both in terms of accuracy and interpretability. Furthermore, it is competitive against PIQ, a method specifically designed for post-hoc interpretation in the audio domain.
Resource-Efficient Separation Transformer
Luca Della Libera
Samuele Cornell
Frédéric Lepoutre
François Grondin
Transformers have recently achieved state-of-the-art performance in speech separation. These models, however, are computationally demanding … (see more)and require a lot of learnable parameters. This paper explores Transformer-based speech separation with a reduced computational cost. Our main contribution is the development of the Resource-Efficient Separation Transformer (RE-SepFormer), a self-attention-based architecture that reduces the computational burden in two ways. First, it uses non-overlapping blocks in the latent space. Second, it operates on compact latent summaries calculated from each chunk. The RE-SepFormer reaches a competitive performance on the popular WSJ0-2Mix and WHAM! datasets in both causal and non-causal settings. Remarkably, it scales significantly better than the previous Transformer-based architectures in terms of memory and inference time, making it more suitable for processing long mixtures.
SKILL: Similarity-aware Knowledge distILLation for Speech Self-Supervised Learning
Luca Zampierin
Ghouthi Boukli Hacene
Bac Nguyen
Bayesian Deep Learning for Remaining Useful Life Estimation via Stein Variational Gradient Descent
Luca Della Libera
Jacopo Andreoli
Davide Dalle Pezze
Gian Antonio Susto
A crucial task in predictive maintenance is estimating the remaining useful life of physical systems. In the last decade, deep learning has … (see more)improved considerably upon traditional model-based and statistical approaches in terms of predictive performance. However, in order to optimally plan maintenance operations, it is also important to quantify the uncertainty inherent to the predictions. This issue can be addressed by turning standard frequentist neural networks into Bayesian neural networks, which are naturally capable of providing confidence intervals around the estimates. Several methods exist for training those models. Researchers have focused mostly on parametric variational inference and sampling-based techniques, which notoriously suffer from limited approximation power and large computational burden, respectively. In this work, we use Stein variational gradient descent, a recently proposed algorithm for approximating intractable distributions that overcomes the drawbacks of the aforementioned techniques. In particular, we show through experimental studies on simulated run-to-failure turbofan engine degradation data that Bayesian deep learning models trained via Stein variational gradient descent consistently outperform with respect to convergence speed and predictive performance both the same models trained via parametric variational inference and their frequentist counterparts trained via backpropagation. Furthermore, we propose a method to enhance performance based on the uncertainty information provided by the Bayesian models. We release the source code at https://github.com/lucadellalib/bdl-rul-svgd.
Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets
Shenyang Huang
Joao Alex Cunha
Zhiyi Li
Gabriela Moisescu-Pareja
Oleksandr Dymov
Samuel Maddrell-Mander
Callum McLean
Frederik Wenkel
Luis Müller
Jama Hussein Mohamud
Ali Parviz
Michael Craig
Michał Koziarski
Jiarui Lu
Zhaocheng Zhu
Cristian Gabellini
Kerstin Klaser
Josef Dean
Cas Wognum … (see 15 more)
Maciej Sypetkowski
Christopher Morris
Ioannis Koutis
Prudencio Tossou
Hadrien Mary
Therence Bois
Andrew William Fitzgibbon
Blazej Banaszewski
Chad Martin
Dominic Masters
Recently, pre-trained foundation models have enabled significant advancements in multiple fields. In molecular machine learning, however, wh… (see more)ere datasets are often hand-curated, and hence typically small, the lack of datasets with labeled features, and codebases to manage those datasets, has hindered the development of foundation models. In this work, we present seven novel datasets categorized by size into three distinct categories: ToyMix, LargeMix and UltraLarge. These datasets push the boundaries in both the scale and the diversity of supervised labels for molecular learning. They cover nearly 100 million molecules and over 3000 sparsely defined tasks, totaling more than 13 billion individual labels of both quantum and biological nature. In comparison, our datasets contain 300 times more data points than the widely used OGB-LSC PCQM4Mv2 dataset, and 13 times more than the quantum-only QM1B dataset. In addition, to support the development of foundational models based on our proposed datasets, we present the Graphium graph machine learning library which simplifies the process of building and training molecular machine learning models for multi-task and multi-level molecular datasets. Finally, we present a range of baseline results as a starting point of multi-task and multi-level training on these datasets. Empirically, we observe that performance on low-resource biological datasets show improvement by also training on large amounts of quantum data. This indicates that there may be potential in multi-task and multi-level training of a foundation model and fine-tuning it to resource-constrained downstream tasks. The Graphium library is publicly available on Github and the dataset links are available in Part 1 and Part 2.
Are LLMs Robust for Spoken Dialogues?
Seyed Mahed Mousavi
Gabriel Roccabruna
Simone Alghisi
Massimo Rizzoli
Giuseppe Riccardi
Large Pre-Trained Language Models have demonstrated state-of-the-art performance in different downstream tasks, including dialogue state tra… (see more)cking and end-to-end response generation. Nevertheless, most of the publicly available datasets and benchmarks on task-oriented dialogues focus on written conversations. Consequently, the robustness of the developed models to spoken interactions is unknown. In this work, we have evaluated the performance of LLMs for spoken task-oriented dialogues on the DSTC11 test sets. Due to the lack of proper spoken dialogue datasets, we have automatically transcribed a development set of spoken dialogues with a state-of-the-art ASR engine. We have characterized the ASR-error types and their distributions and simulated these errors in a large dataset of dialogues. We report the intrinsic (perplexity) and extrinsic (human evaluation) performance of fine-tuned GPT-2 and T5 models in two subtasks of response generation and dialogue state tracking, respectively. The results show that LLMs are not robust to spoken noise by default, however, fine-tuning/training such models on a proper dataset of spoken TODs can result in a more robust performance.
TARIC-SLU: A Tunisian Benchmark Dataset for Spoken Language Understanding
Salima Mdhaffar
Fethi Bougares
Renato de Mori
Salah Zaiem
Yannick Estève
In recent years, there has been a significant increase in interest in developing Spoken Language Understanding (SLU) systems. SLU involves e… (see more)xtracting a list of semantic information from the speech signal. A major issue for SLU systems is the lack of sufficient amount of bi-modal (audio and textual semantic annotation) training data. Existing SLU resources are mainly available in high-resource languages such as English, Mandarin and French. However, one of the current challenges concerning low-resourced languages is data collection and annotation. In this work, we present a new freely available corpus, named TARIC-SLU, composed of railway transport conversations in Tunisian dialect that is continuously annotated in dialogue acts and slots. We describe the semantic model of the dataset, the data and experiments conducted to build ASR-based and SLU-based baseline models. To facilitate its use, a complete recipe, including data preparation, training and evaluation scripts, has been built and will be integrated to SpeechBrain, a popular open-source conversational AI toolkit based on PyTorch.
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.
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 and to unify various fine-grained methods under a single objective, 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, 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.