
Associate Professor — Maître de Conférences
Laboratoire Informatique d'Avignon (LIA)
Avignon Université (FR)
Remote Visiting Scholar
Machine Learning Systems Lab
University of Cambridge (UK)
Remote Visiting Scholar
Machine Learning Systems Lab
University of Cambridge (UK)
From september 2020, I joined the Laboratoire Informatique d'Avignon (LIA) and Avignon Université as an associate professor (Maître de Conférences) in computer science.
I am also a member of the Cambridge Machine Learning Systems Lab as a remote visiting scholar to build strong collaborations with Avignon Universite around shared projects.
My research focuses on artificial intelligence through the development of new deep learning methods via self-supervised / representation learning. I am also interested
on the efficiency problematic of large deep learning models alongside with finding elegant solutions to the privacy concerns raised by the big data. In this extent,
I investigate different potential solutions including federated learning and privacy preserving transformation of latent representations. As of now, I have mostly
applied these new concepts to automatic speech processing. I am involved in the management of community driven solutions such as SpeechBrain, an open source toolkit for
speech processing and deep learning entirely written in PyTorch. Finally, I am particularly attached to the concept of AI for Social Good, and I therefore dedicate a part of my research time
to solve concrete societal problems, such as the astonishing carbon footprint of modern deep learning models.
From february to august 2020, I was part of the Oxford Machine Learning Systems (OxMLSys) as a Senior Research Associate working in collaboration with Prof. Nicholas Lane, working on the fundations of the above described topics.
Prior to joining Oxford, I did my PhD thesis at the University of Avignon and the Laboratoire Informatique d'Avignon (LIA) under the supervision of Prof.
Linarès Georges and Assoc. Prof. Morchid Mohamed. The thesis was part of an industrial collaboration (CIFRE) with Orkis, a French company specialised in assets
and data managements. The thesis ended with more than 15 publications in well-known conferences and journals, and released new tools to the research community
to develop and investigate quaternion neural networks in the context of natural language processing and image processing.
During the thesis, I was given the opportunity to spend 4 months working at the Montréal Institute for Learning Algorithms (MILA), Montréal under the supervision
of Prof. Yoshua Bengio. The collaboration mainly concerned the development of new quaternion convolutional and recurrent neural networks for automatic speech
recognition. This period is also at the origin of long-term and funded projects including Pytorch-Kaldi and SpeechBrain.
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
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 four sponsors: the Montréal Institute for Learning Algorithms (MILA), Samsung, NVIDIA, and Dolby. SpeechBrain also benefits from the collaboration and expertise of other partners such as the University of Cambridge, the University of Sherbrook, the University of Avignon (LIA), Facebook, IBM Research, and Fluent.ai Inc.
The project runs thanks to 8-9 full-time interns based in Montréal and the various contributions of our partners.
I'm co-leading SpeechBrain with Dr. Ravanelli Mirco, currently a post-doctoral researcher at MILA.
Have a look at: SpeechBrain!
Community Contributions
Workshop Co-Organizer
ICML self-Supervision in Audio and Speech (held virtually), July 17th (2020), Vienna (Austria).
Invited Talks
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
- Springer, Neural Processing Letters. 2020
- IEEE Transactions on Image Processing. 2020
- NeurIPS. 20(18-20), top 10% best reviewer 2020.
- ICLR. 20(19-20)
- INTERSPEECH. 20(19-20)
- ICASSP. 2020)
Expert for Research Projects Evaluation
- Idex Lyon St-Étienne. 2021
Publications
International Journals
- Unsupervised Real to H-space Encoder-Decoder for Theme Identification in Telephone Conversations
- Titouan Parcollet · Mohamed Morchid · Xavier Bost · Georges Linarès · Renato De Mori
- IEEE, Transactions on Audio, Speech and Language Processing, IF: 3.531
- A survey of quaternion neural networks
- Titouan Parcollet · Mohamed Morchid · Georges Linarès
- Springer, Artificial Intelligence Review, IF: 5.095
International conferences
- Distilling Knowledge from Ensembles of Acoustic Models for Joint CTC-Attention End-to-End Speech Recognition
- Yan Gao · Titouan Parcollet · Nicholas Lane
- Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation
- Paul-Gauthier Noé · Mohammad MohammadAmini · Driss Matrouf · Titouan Parcollet · Jean-François Bonastre
- Flower: A Friendly Federated Learning Research Framework
- Daniel J. Beutel · Taner Topal · Akhil Mathur · Xinchi Qiu · Titouan Parcollet · Nicholas D. Lane
- Submitted to Machine Learning and Systems (MLSys, 2020)
- Virtual Conference (COVID)
- Can Federated Learning Save The Planet ?
- Xinchi Qiu · Titouan Parcollet · Nicholas Lane
- NeurIPS 2020 : Tackling Climate Change with Machine Learning Workshop
- December 11-12, Virtual Conference (COVID)
- FusionRNN: Shared Neural Parameters for Multi-Channel Distant Speech Recognition
- Titouan Parcollet · Xinchi Qiu · Nicholas Lane
- INTERSPEECH 2020
- October 25-29, Virtual Conference (COVID)
- Quaternion Neural Networks for Multi-channel Distant Speech Recognition
- Xinchi Qiu · Titouan Parcollet · Mirco Ravanelli · Nicholas Lane · Mohamed Morchid
- INTERSPEECH 2020
- October 25-29, Virtual Conference (COVID)
- E2E-SincNet: Toward Fully End-to-End Speech Recognition
- Titouan Parcollet · Mohamed Morchid · Georges Linarès
- ICASSP 2020
- May 4-8, Virtual Conference (COVID)
- CGCNN: Complex Gabor Convolutional Neural Network on Raw Speech
- Paul-Gauthier Noé · Titouan Parcollet · Mohamed Morchid
- ICASSP 2020
- May 4-8, Virtual Conference (COVID)
- Artificial Intelligence: A Tale of Social Responsibility
- Cécilia Darnault · Titouan Parcollet · Mohamed Morchid
- HumanIA 2019
- 26-28 November, Avignon (France)
- Real to H-space Encoder for Speech Recognition
- Titouan Parcollet · Mohamed Morchid · Georges Linarès · Renato De Mori
- INTERSPEECH 2019
- September 15-19 2019, Graz, (Austria)
- M2H-GAN: A GAN-based Mapping from Machine to Human Transcripts for Speech Understanding
- Titouan Parcollet · Mohamed Morchid · Xavier Bost · Georges Linarès
- INTERSPEECH 2019
- September 15-19 2019, Graz, (Austria)
- The PyTorch-Kaldi Speech Recognition Toolkit
- Mirco Ravanelli · Titouan Parcollet · Yoshua Bengio
- ICASSP 2019
- May 12-17 2019, Brighton, (UK)
- Bidirectional Quaternion Long-Short Term Memory Recurrent Neural Networks for Speech Recognition
- Titouan Parcollet · Mohamed Morchid · Georges Linarès · Renato De Mori
- ICASSP 2019
- May 12-17 2019, Brighton, (UK)
- Quaternion Convolutional Neural Networks for Heterogeneous Image Processing
- Titouan Parcollet · Mohamed Morchid · Georges Linarès
- ICASSP 2019
- May 12-17 2019, Brighton, (UK)
- Quaternion Recurrent Neural Networks
- Titouan Parcollet · Mirco Ravanelli · Mohamed Morchid · Georges Linarès · Chiheb Trabelsi · Renato De Mori · Yoshua Bengio
- ICLR 2019
- May 6-9 2019, New Orleans, (USA)
- Quaternion Convolutional Neural Networks for Theme Identification of Telephone Conversations
- Titouan Parcollet · Mohamed Morchid · Georges Linarès · Renato De Mori
- IEEE SLT 2018
- December 18-21 2018, Athens, (Greece)
- Speech Recognition with Quaternion Neural Networks
- Titouan Parcollet · Mirco Ravanelli · Mohamed Morchid · Georges Linarès · Renato De Mori
- NIPS 2018 - IRASL Workshop
- December 2-8 2018, Montréal, QC, (CA)
- Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition
- Titouan Parcollet · Ying Zhang · Mohamed Morchid · Chiheb Trabelsi · Georges Linarès · Renato De Mori · Yoshua Bengio
- INTERSPEECH 2018
- September 2-6 2018, Hyderabad, (India)
- Deep Quaternion Neural Networks for Spoken Language Understanding
- Titouan Parcollet · Mohamed Morchid · Georges Linarès
- ASRU 2017
- December 16-20 2017, Okinawa, (Japan)
- Quaternion Denoising Encoder-Decoder for theme identification of telephone conversations
- International Speech and Communication Association Grants - INTERSPEECH 2017
- Quaternion Neural Networks for Spoken Language Understanding
- Titouan Parcollet · Mohamed Morchid · Pierre-Michel Bousquet · Richard Dufour · Georges Linarès · Renato De Mori
- IEEE SLT 2016
- Decembre 13-16 2016, San Diego, (USA)
- Tracking Dialog States using an Author-Topic based Representation
- Richard Dufour · Mohamed Morchid · Titouan Parcollet
- IEEE SLT 2016
- Decembre 13-16 2016, San Diego, (USA)
National conferences
- Réseaux de neurones convolutifs de quaternions pour l'identification de thèmes de conversations téléphoniques
- Titouan Parcollet · Mohamed Morchid · Georges Linarès
- CORIA 2019
- March 27-29 2019, Lyon, (FRANCE)
- Réseaux de neurones de quaternions pour le traitement du language
- Titouan Parcollet · Mohamed Morchid · Georges Linarès
- CORIA 2017
- March 29-31 2017, Marseille, (FRANCE)
Teaching
All the tutorials and practical work classes are dispensed in addition to my standard research job
Year 2019/2020
Teaching | Tutorials | Practical Work | Total |
Innovation Application (AI) | 12h | 12h | |
Total | 12h |
Year 2018/2019
Teaching | Tutorials | Practical Work | Total |
Computer Science Basics | 10h | 10h | |
Object Oriented Programming C++ | 14h | 14h | 28h |
Tools for Machine Learning | 12h | 12h | |
Total | 50h |
Year 2017/2018
Teaching | Tutorials | Practical Work | Total |
Advanced programming and projects (B.Sc.) | 12h | 19h | 31h |
Total | 31h |
Year 2016/2017
Teaching | Tutorials | Practical Work | Total |
Advanced programming and projects (B.Sc.) | 12h | 18h | 30h |
Agorithms and programming (B.Sc.) | 12h | 18h | 30h |
Total | 60h |
Year 2015/2016
Teaching | Tutorials | Practical Work | Total |
C2I Certification (B.Sc.) | 144h | ||
Total | 144h |
Year 2013/2014
Teaching | Tutorials | Practical Work | Total |
C2I Certification (B.Sc.) | 144h | ||
Total | 144h |
CV
Education
- PhD in computer science (CIFRE) - 2019
- Thesis: Quaternion neural networks
- Advisors: Georges Linarès, Mohamed Morchid
- Reviewers: Thierry Artières, Allexandre Allauzen
- Committee: Yoshua Bengio, Benjamin Lecouteux, Xavier Bost, Nathalie Camelin
- Avignon Université, France & Orkis, Aix-en-provence, France
- Master Research in computer science - 2016
- Thesis: Quaternions and deep neural networks
- Avignon Université, France
- Bachelor in computer science - 2014
- Avignon Université, France
Experiences
- Visiting Scholar (remote) - 2020 / 2022
- Cambridge Machine Learning Systems Lab
- University of Cambridge
- Associate Professor at Avignon Université - 2020
- Laboratoire Informatique d'Avignon (LIA)
- 339 chemin des Meinajaries, 84000 Avignon, France
- Senior Research Associate - 2020
- Advisors: Nicholas Lane
-
The research focuses on efficient automatic speech recognition with an emphasis on representation learningm new ways of representing artificial neurons and self-supervised learning. I'm also involved in the supervision of students within the group. - University of Oxford, Department of Computer Science, OxMLSys lab, Oxford, United-Kingdom
- CIFRE PhD Student - 2017 / 2019
- Thesis: Quaternion neural networks
- Advisor: Georges Linarès, Mohamed Morchid
-
PhD Student in machine learning working on quaternion-valued neural networks with applications to speech recognition, spoken language understanding and image processing. Research engineer at ORKIS, working on new techniques on ASR and documents management with deep learning. Teacher assistant for Master and Bachelor students. Given courses mainly focused on machine learning, programming and algorithms. - Avignon Université, France & Orkis, Aix-en-provence, France
- Montréal Institute for Learning Algorithms (MILA) - Jan. 2018 / Apr. 2018
- Advisor: Yoshua Bengio
- Collaboration and release of the Pytorch-Kaldi toolkit. Research on quaternion convolutional neural networks for end-to-end automatic speech recognition. Introduction of quaternion-valued recurrent neural networks to speech recognition.
- Université de Montréal, Québec, Canada
- Research Engineer - Sep. 2016 / Mar. 2017
- Advisor: Mohamed Morchid
- Hyper-complex neural networks implementation on GPU (CUDA). Research on Spoken Language Understanding (Pattern Recognition).
- Avignon Université, France
Contact
parcollet.titouan@gmail.com
Address
339 Chemin des Meinajaries, 84000 Avignon, France