Gaël Richard, Professor, Télécom Paris, Institut Polytechnique de Paris

ContactContact

Envoyer un e-mailSend an e-mail
Tél. 01 75 31 96 60
Curriculum vitæ (pdf)Résumé (pdf)
Site web personnelPersonal Web Site

Équipe de recherche :Research Team:
Signal, Statistique et Apprentissage (S2A)Signal, Statistics and Learning (S2A)
Laboratoire :Laboratory:
Laboratoire Traitement et Communication de l'Information (LTCI)Information Processing and Communication Laboratory (LTCI)
Département :Department:
Image, Données, Signal (IDS)Image, Data, Signal (IDS)

Repères biographiquesShort Biography

Gaël Richard is Professor at Télécom Paris, Institut polytechnique de Paris and scientific co-director of Hi! PARIS. His research work lies at the core of digitization and is dedicated to the analysis, transformation, understanding and automatic indexing of acoustic signals (including speech, music, environmental sounds) and to a lesser extent of heterogeneous and multimodal signals. In particular, he developed several source separation methods for audio and musical signals based on machine learning approaches.

Gaël Richard has received in 2020 the Grand Prix IMT-Académie des Sciences — read his interview on I’mTech

He is also awarded in 2022 of an advanced ERC grant of the European Union on AI for sounds for the project HI-Audio —- Check the current open positions.

More information (Preprints, Publications, CV,….) on the Personal web site or on Google scholar

Activités : enseignement, recherche, projetsActivities : Teaching, Research, Projects

Research

My research interests are mainly in the field of machine learning and speech/audio signal processing and include topics such as:

- Signal representations and signal models : Subspace methods, sparse representation, atomic decomposition, Non NEgative MAtrix factorisation (NMF), Source Separation…
- Machine learning methods for audio/music signals : machine listening, Music Information Retrieval (MIR), Audio/Music indexing, Speech/audio segmentation, Speech/music emotion recognition.
- Models for multipitch estimation in polyphonic music signals, rythmn/beat estimation,musical instrument recognition
- Audio Coding and 3D Audio
- Multimedia and speech signal analysis, speech synthesis

Teaching

Main courses include:

- Master MVA for a course on Audio signal processing (University ParisSaclay).
- Master M2-DataScience – Audio and music information retrieval (Institut Polytechnique de Paris)

Talks / Seminars

A selection of talks….:

- Keynote talk at the ICASSP 2024 Workshop on Explainable AI for Speech and Audio, « Explainable and interpretable deep audio processing based on hybrid deep learning« , April 15th, 2024, Seoul, Korea.
- Keynote talk at Winter School on Generative AI 2024, « Audio and cross-modal Generative AI, »Feb 27th-28th, 2024, EMINES conference Center, Morocco
- Keynote talk at SANE 2023, « Deep Hybrid Learning and Its Application to Unsupervised Singing Voice Separation, » Oct. 2023, New York, US
- Keynote talk at Dafx’2022: « Hybrid deep learning for audio« , Sept. 2022, Vienna, Austria.
- Talk at award ceremony National academy of sciences « Analysis, transformation and recognition of audio signals« , November 2020, Paris, France.
- Invited talk « Machine listening: AI for sounds and music« , Colloquium Colloque IMT – L’intelligence artificielle au coeur des mutations industrielles (slides in English), April 2019, Paris, France.
- Keynote talk at DCASE’2016, « Acoustic scene and events recognition:
  how similar is it to speech recognition and music genre/instrument recognition ?, Sept. 2016, Budapest, Hungary.
- Keynote talk at IWAENC’2014, « Melody Extraction from Polyphonic Music Signals« , Sept. 2014, Nice, France
- Invited talk at AES 53rd Conference on Semantic Audio : »Informed Audio Source Separation« , Jan. 2014, London, UK
- Keynote talk at WIAMIS’2012, « Audio and Multimedia Music Signals Indexing, May 2012, Dublin, Ireland