Titouan Parcollet

Research Interests

• Deep learning
• Efficient automatic speech processing technologies
• Self-supervised & unsupervised & representation learning
• AI for social good

Efficient Automatic Speech Processing

The term efficiency defines different problematics. My research focuses on three of them, including better performances of speech processing models, a better management of the available resources (i.e. training data), and finally making these models more efficient to be deployed on constrained systems. Overall, I am pursuing the ultimate goal of a light-weight task-agnostic speech processing system that would be trained with a combination of self-supervised, supervised and federated learning to ensure strong performance and data privacy. My recent work includes the investigation of distillation methods for acoustic models, self-supervised learning, new trully end-to-end speech processing methods and federated learning.

Funded Projects

LeBenchmark (2020 - 2021) Leader of the self-supervised models task

LeBenchmark project has been granted 200K hours of GPU time in the French datacenter Jean Zay. This project is a joint collaboration between the Laboratoire d'Informatique de Grenoble (LIG) and the Laboratoire Informatique d'Avignon (LIA) that aims to collect large quantities of raw speech in French (i.e. several thousand hours) with different styles (read speech, prepared speech, spontaneous speech), from various speakers and use them to learn self-supervised models to be shared with the research community. Furthermore, we also wish to establish a new benchmark data set for several speech processing tasks. I am in charge of finding the appropriate self-supervised methods (e.g wav2vec, PASE, MockingJay) and to deploy it on our new dataset. We wish to release various pre-trained models with a training set acounting for up to 10,000 hours of speech in French. Everything is nicely integrated to SpeechBrain for peoples interested in re-using our models for downstream tasks!

Models are available on HuggingFace .
Publications:

• Task Agnostic and Task Specific Self-Supervised Learning from Speech with LeBenchmark
• Solène Evain · Ha Nguyen · Hang Le · Marcely Zanon Boito · Salima Mdhaffar · Salima Mdhaffar · Sina Alisamir · Ziyi Tong · Natalia Tomashenko · Marco Dinarelli · Titouan Parcollet · Alexandre Allauzen · Yannick Estève · Benjamin Lecouteux · François Portet · Solange Rossato · Fabien Ringeval · Didier Schwab · Laurent Besacier
• NeurIPS 2021.

• LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech
• Solène Evain · Ha Nguyen · Hang Le · Marcely Zanon Boito · Sina Alisamir · Ziyi Tong · salima mdhaffar · Natalia Tomashenko · Marco Dinarelli · Titouan parcollet · Alexandre Allauzen · Yannick Estève · Benjamin Lecouteux · François Portet · Solange Rossato · Fabien Ringeval · Didier Schwab · Laurent Besacier
• Interspeech 2021.

SpeechBrain (2019 - ) Co-coordinator

The SpeechBrain project aims to develop an open-source and all-in-one toolkit based on PyTorch. The goal is to develop a single, flexible, and user-friendly toolkit that can be used to easily develop state-of-the-art speech systems for speech recognition (both end-to-end and HMM-DNN), speaker recognition, speech separation, multi-microphone signal processing (e.g, beamforming), self-supervised learning, and many others. The project is funded thanks to generous donations from five sponsors: the Montréal Institute for Learning Algorithms (MILA), Samsung, NVIDIA, Dolby and ViaDialog. SpeechBrain also benefits from the collaboration and expertise of around 20 different partner institutions (both academics and industrials) ranging from the University of Cambridge to HuggingFace. SpeechBrain already beats all the other toolkits on the considered datasets and with a much easier interface to play with. SpeechBrain reached 2.5K stars on GitHub in less than 4 months demonstrating a clear interest from the community for our toolkit. I'm co-leading SpeechBrain with Dr. Ravanelli Mirco, currently a post-doctoral researcher at MILA.

Have a look at: SpeechBrain! Or to our open access paper describing the toolkit!

Advised Ph.D. Students and Interns

Salah ZAIEM — Ph.D. Student — Started on October 2020 and is co-advised with Prof. Slim ESSID from Telecom Paris Sud.
Title: Informed Self-Supervised Speech Representations Learning.
Ideas: Self-supervised learning methods for speech are mostly empirically driven. In particular, there exist very few theoretical evidences on why a method performs better than an other one. With this thesis, we aim at providing theoreticaly grounded tools to design SSL models in an informed manner. For instance, we developed a solution to design a PASE-like architecture without the need for pre-text task search with empirical validation, potentially saving weeks of training (and compute / carbon emissions).
Publications:

• Pretext Tasks Selection for Multitask Self-Supervised Speech Representation Learning
• Salah Zaiem · Titouan parcollet · Slim Essid
• Submitted to ICLR 2022.

• Conditional Independence for Pretext Task Selection in Self-Supervised Speech Representation Learning
• Salah Zaiem · Titouan parcollet · Slim Essid
• Interspeech 2021. (ISCA Student Travel Grant)

Adel Moumen — Undergrad. Intern — June 2021 to August 2021.
Title: On the limitations of LiGRU networks.
Ideas: Adel investigates different ways of making LiGRU a mandatory alternative to LSTM/GRU for speech processing. There are theoretical and empirical evidences that LiGRU simply are better than LSTM and GRU. Unfortunately, they suffer from a poor GPU implementation and an instability in the recurrent connection. These problems will be tackled during the internship.

SpeechBrain Interns — Started on January 2020.
Format: this is a list of all the researchers that I mentored during their internship to work on SpeechBrain. Internships took place either in Avignon (LIA) or Montréal (Mila) and were co-advised with Dr. Ravanelli
Topics: all the topics and concepts developed within SpeechBrain.

Aku Rouhe, Aalto University (FI).
Peter Plantinga, now at JP Morgan.
Loren Lugosch, Mila (CA).
Ju-Chieh Chou, National Taiwan University (TW).
Abdel Heba, Linaroga / University of Toulouse (FR).
Samuele Cornell, now at Amazon.
Jianyuan Zhong, University of Rochester (USA).

Community Contributions

General Co-Chair

RECITAL (TALN session), June 28th (2022), Avignon (France).

Workshop Co-Organizer

ICML self-Supervision in Audio and Speech (held virtually), July 17th (2020), Vienna (Austria).

Tutorials

IEEE ASRU 2021: "SpeechBrain: Unifying Speech Technologies and Deep Learning With an Open Source Toolkit", December 2021.
Interspeech 2021: "SpeechBrain: Unifying Speech Technologies and Deep Learning With an Open Source Toolkit", August 2021.
University of Sheffield: "SpeechBrain: Unifying Speech Technologies and Deep Learning With an Open Source Toolkit", June 2021.

Invited Talks

Microsoft Research Summit Workshop on Federated Learning and Confidential Computing: "Federated Speech Technologies", October 21th (2021).
Machine Learning Summer Schools — Taipei: "Task Agnostic and Task Specific Self-Supervised Learning from Speech with LeBenchmark", August 20th (2021).
The Machine Learning / Data Science Meetup of Rome: "SpeechBrain: A General-Purpose Speech Toolkit", July 7th (2021).
The 2nd Annual Federated & Distributed / Decentralized Machine Learning Conference (remote): "Can Federated Learning Save the Planet", June 16th (2021).
Flower Summit 2021 (remote): "Federated speech technologies made easy: Flower and SpeechBrain", March 11th (2021).
Centre de Recherche en Automatique de Nancy (FR): "Should we use quaternion neural networks? Recent advances and limitations.", March 29th (2021).
Samsung AI Cambridge (UK): "SpeechBrain", February 27th (2021).
Samsung AI Cambridge (UK): "Quaternion neural networks", July 10th (2019).
University of Oxford (UK): "Quaternion neural networks", July 9th (2019), Computer Science Department.

Program Committee Member

• IEEE Signal Processing Letters. 2021
• IEEE Transactions on Neural Networks and Learning Systems. 2019, 2020
• IEEE International Journal of Wavelets, Multiresolution and Information Processing. 2020
• ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies. 2020
• Elsevier, Computers & Graphics, 2021
• ACM Multimedia. 2021
• Springer, Neural Processing Letters. 2020
• IEEE Transactions on Image Processing. 2020
• NeurIPS. 20(18-21), top 10% best reviewer 2020.
• ICLR. 20(19-20-21), top 10% best reviewer 2020.
• INTERSPEECH. 20(19-20-21)
• ICASSP. 2020

Expert for Research Projects Evaluation

• Agence Nationale de la Recherche. 2021
• Idex Lyon St-Étienne. 2021

Press Coverage

Le Devoir (Quebec News) — "Google, dis-moi si tu comprends mon accent québécois", April 10th (2021).