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
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

Hiba Akhaddar
Master's Research - Concordia University
Seina Assadian
Collaborating researcher - Concordia University University
Github
Cordelle Briac
Collaborating researcher - Concordia University University
Github
Victor Cruz
Master's Research - Concordia University
Luca Della Libera
PhD - Concordia University
Co-supervisor :
Cem Subakan
Github
Wagner Drew
Master's Research - Concordia University
Co-supervisor :
Irina Rish
Github
Gianfranco Dumoulin Bertucci
Master's Research - Concordia University
Website
Github
Nadine El-Mufti
Master's Research - Concordia University
nadine.el-mufti@mila.quebec
Website
Github
Google Scholar
Maab Elrashid Ahmed Mohamed
PhD - Concordia University
Co-supervisor :
Cem Subakan
Github
Bonzi Francesco
PhD - Concordia University
Github
Alessio Giuseppe Alessio
Collaborating researcher - International School for Advanced Studies (Trieste, Italy)
Salman Sami Hussain Ali
Collaborating researcher - Concordia University University
Github
Tristan Lueger
Collaborating researcher - Concordia University University
Eleonora Mancini
Collaborating Alumni - Université de Montréal
Principal supervisor :
Cem Subakan
Github
Google Scholar
Jama Mohamud
PhD - Université de Montréal
Co-supervisor :
Yoshua Bengio
Website
Github
Google Scholar
Pooneh Mousavi
PhD - Concordia University
Website
Github
Google Scholar
Fırat Öncel
PhD - Concordia University
Co-supervisor :
Laurent Charlin
Website
Github
Google Scholar
Peter Peter
Postdoctorate - McGill University
Website
Github
Google Scholar
Artem Ploujnikov
PhD - Université de Montréal
Ritika Dhamija Ritika
Collaborating researcher - Concordia University University
Github

Publications

Explaining Network Decision Provides Insights on the Causal Interaction Between Brain Regions in a Motor Imagery Task
Davide Borra
Mirco Ravanelli
2024-09-19
Lecture Notes in Computer Science (published)
doi.org
Multi-modal Decoding of Reach-to-Grasping from EEG and EMG via Neural Networks
Davide Borra
Matteo Fraternali
Mirco Ravanelli
Elisa Magosso
2024-09-19
Lecture Notes in Computer Science (published)
doi.org
LMAC-TD: Producing Time Domain Explanations for Audio Classifiers
Eleonora Mancini
Francesco Paissan
Mirco Ravanelli
Cem Subakan
2024-09-13
ArXiv (preprint)
doi.org
arxiv.org
Audio Editing with Non-Rigid Text Prompts
Francesco Paissan
Zhepei Wang
Mirco Ravanelli
Paris Smaragdis
Cem Subakan
In this paper, we explore audio-editing with non-rigid text edits. We show that the proposed editing pipeline is able to create audio edits … (see more)that remain faithful to the input audio. We explore text prompts that perform addition, style transfer, and in-painting. We quantitatively and qualitatively show that the edits are able to obtain results which outperform Audio-LDM, a recently released text-prompted audio generation model. Qualitative inspection of the results points out that the edits given by our approach remain more faithful to the input audio in terms of keeping the original onsets and offsets of the audio events.
2024-09-01
Interspeech 2024 (published)
doi.org
arxiv.org
Progres: Prompted Generative Rescoring on ASR N-Best
Ada Defne Tur
Adel Moumen
Mirco Ravanelli
Large Language Models (LLMs) have shown their ability to improve the performance of speech recognizers by effectively rescoring the n-best h… (see more)ypotheses generated during the beam search process. However, the best way to exploit recent generative instruction-tuned LLMs for hypothesis rescoring is still unclear. This paper proposes a novel method that uses instruction-tuned LLMs to dynamically expand the n-best speech recognition hypotheses with new hypotheses generated through appropriately-prompted LLMs. Specifically, we introduce a new zero-shot method for ASR n-best rescoring, which combines confidence scores, LLM sequence scoring, and prompt-based hypothesis generation. We compare Llama-3-Instruct, GPT-3.5 Turbo, and GPT-4 Turbo as prompt-based generators with Llama-3 as sequence scorer LLM. We evaluated our approach using different speech recognizers and observed significant relative improvement in the word error rate (WER) ranging from 5% to 25%.
2024-08-30
ArXiv (preprint)
doi.org
arxiv.org
Progres: Prompted Generative Rescoring on ASR N-Best
Ada Defne Tur
Adel Moumen
Mirco Ravanelli
Large Language Models (LLMs) have shown their ability to improve the performance of speech recognizers by effectively rescoring the n-best h… (see more)ypotheses generated during the beam search process. However, the best way to exploit recent generative instruction-tuned LLMs for hypothesis rescoring is still unclear. This paper proposes a novel method that uses instruction-tuned LLMs to dynamically expand the n-best speech recognition hypotheses with new hypotheses generated through appropriately-prompted LLMs. Specifically, we introduce a new zero-shot method for ASR n-best rescoring, which combines confidence scores, LLM sequence scoring, and prompt-based hypothesis generation. We compare Llama-3-Instruct, GPT-3.5 Turbo, and GPT-4 Turbo as prompt-based generators with Llama-3 as sequence scorer LLM. We evaluated our approach using different speech recognizers and observed significant relative improvement in the word error rate (WER) ranging from 5% to 25%.
2024-08-30
ArXiv (preprint)
doi.org
arxiv.org
Listenable Maps for Audio Classifiers
Francesco Paissan
Mirco Ravanelli
Cem Subakan
2024-07-08
Proceedings of the 41st International Conference on Machine Learning (published)
doi.org
openreview.net
Open-Source Conversational AI with SpeechBrain 1.0
Mirco Ravanelli
Titouan Parcollet
Adel Moumen
Sylvain de Langen
Cem Subakan
Peter William VanHarn Plantinga
Yingzhi Wang
Pooneh Mousavi
Luca Della Libera
Artem Ploujnikov
Francesco Paissan
Davide Borra
Salah Zaiem
Zeyu Zhao
Shucong Zhang
Georgios Karakasidis
Sung-Lin Yeh
Pierre Champion
Aku Rouhe
Rudolf Braun … (see 11 more)
Florian Mai
Juan Pablo Zuluaga
Seyed Mahed Mousavi
Andreas Nautsch
Xuechen Liu
Sangeet Sagar
Jarod Duret
Salima Mdhaffar
G. Laperriere
Renato De Mori
Yannick Estève
SpeechBrain is an open-source Conversational AI toolkit based on PyTorch, focused particularly on speech processing tasks such as speech rec… (see more)ognition, speech enhancement, speaker recognition, text-to-speech, and much more. It promotes transparency and replicability by releasing both the pre-trained models and the complete"recipes"of code and algorithms required for training them. This paper presents SpeechBrain 1.0, a significant milestone in the evolution of the toolkit, which now has over 200 recipes for speech, audio, and language processing tasks, and more than 100 models available on Hugging Face. SpeechBrain 1.0 introduces new technologies to support diverse learning modalities, Large Language Model (LLM) integration, and advanced decoding strategies, along with novel models, tasks, and modalities. It also includes a new benchmark repository, offering researchers a unified platform for evaluating models across diverse tasks.
2024-06-29
ArXiv (preprint)
doi.org
arxiv.org
Open-Source Conversational AI with SpeechBrain 1.0
Mirco Ravanelli
Titouan Parcollet
Adel Moumen
Sylvain de Langen
Cem Subakan
Peter William VanHarn Plantinga
Yingzhi Wang
Pooneh Mousavi
Luca Della Libera
Artem Ploujnikov
Francesco Paissan
Davide Borra
Salah Zaiem
Zeyu Zhao
Shucong Zhang
Georgios Karakasidis
Sung-Lin Yeh
Pierre Champion
Aku Rouhe
Rudolf Braun … (see 11 more)
Florian Mai
Juan Pablo Zuluaga
Seyed Mahed Mousavi
Andreas Nautsch
Xuechen Liu
Sangeet Sagar
Jarod Duret
Salima Mdhaffar
G. Laperriere
Renato De Mori
Yannick Estève
SpeechBrain is an open-source Conversational AI toolkit based on PyTorch, focused particularly on speech processing tasks such as speech rec… (see more)ognition, speech enhancement, speaker recognition, text-to-speech, and much more. It promotes transparency and replicability by releasing both the pre-trained models and the complete"recipes"of code and algorithms required for training them. This paper presents SpeechBrain 1.0, a significant milestone in the evolution of the toolkit, which now has over 200 recipes for speech, audio, and language processing tasks, and more than 100 models available on Hugging Face. SpeechBrain 1.0 introduces new technologies to support diverse learning modalities, Large Language Model (LLM) integration, and advanced decoding strategies, along with novel models, tasks, and modalities. It also includes a new benchmark repository, offering researchers a unified platform for evaluating models across diverse tasks
2024-06-29
ArXiv (preprint)
doi.org
arxiv.org
DASB -- Discrete Audio and Speech Benchmark
Pooneh Mousavi
Luca Della Libera
Jarod Duret
Artem Ploujnikov
Cem Subakan
Mirco Ravanelli
Discrete audio tokens have recently gained considerable attention for their potential to connect audio and language processing, enabling the… (see more) creation of modern multimodal large language models. Ideal audio tokens must effectively preserve phonetic and semantic content along with paralinguistic information, speaker identity, and other details. While several types of audio tokens have been recently proposed, identifying the optimal tokenizer for various tasks is challenging due to the inconsistent evaluation settings in existing studies. To address this gap, we release the Discrete Audio and Speech Benchmark (DASB), a comprehensive leaderboard for benchmarking discrete audio tokens across a wide range of discriminative tasks, including speech recognition, speaker identification and verification, emotion recognition, keyword spotting, and intent classification, as well as generative tasks such as speech enhancement, separation, and text-to-speech. Our results show that, on average, semantic tokens outperform compression tokens across most discriminative and generative tasks. However, the performance gap between semantic tokens and standard continuous representations remains substantial, highlighting the need for further research in this field.
2024-06-20
ArXiv (preprint)
doi.org
openreview.net
How Should We Extract Discrete Audio Tokens from Self-Supervised Models?
Pooneh Mousavi
Jarod Duret
Salah Zaiem
Luca Della Libera
Artem Ploujnikov
Cem Subakan
Mirco Ravanelli
2024-06-15
ArXiv (preprint)
doi.org
arxiv.org
How Should We Extract Discrete Audio Tokens from Self-Supervised Models?
Pooneh Mousavi
Jarod Duret
Salah Zaiem
Luca Della Libera
Artem Ploujnikov
Cem Subakan
Mirco Ravanelli
Discrete audio tokens have recently gained attention for their potential to bridge the gap between audio and language processing. Ideal audi… (see more)o tokens must preserve content, paralinguistic elements, speaker identity, and many other audio details. Current audio tokenization methods fall into two categories: Semantic tokens, acquired through quantization of Self-Supervised Learning (SSL) models, and Neural compression-based tokens (codecs). Although previous studies have benchmarked codec models to identify optimal configurations, the ideal setup for quantizing pretrained SSL models remains unclear. This paper explores the optimal configuration of semantic tokens across discriminative and generative tasks. We propose a scalable solution to train a universal vocoder across multiple SSL layers. Furthermore, an attention mechanism is employed to identify task-specific influential layers, enhancing the adaptability and performance of semantic tokens in diverse audio applications.
2024-06-15
ArXiv (preprint)
doi.org
arxiv.org