Sounds and Interaction
Head: Myriam Desainte-Catherine

Research Groups


The Interaction Group

We explore new approaches for interaction between users and digital worlds, especially 3D worlds. In particular, this implies the design of new interaction techniques, the design of user study protocols, and the exploration of new input and output modalities.

  • Keywords: 3D interaction, tangible interaction, brain-computer interfaces, augmented reality, virtual reality.
  • This activity is led by Potioc (an Inria project-team, joint with Université de Bordeaux and CNRS) and the interaction group of ESTIA.


The Music and Sound Modelization (MSM) Group

We develop new sound and music descriptions to create new forms of interactivity for musical creation, music navigation, and music teaching. We study all musical dimensions, including temporal and spatial ones, by the mean of music processing, musicology of creating processus, while taking perception and cognition into account.

  • Keywords: sound modeling close to perception, musical similarity, interactivity modeling, analysis of spatialisation.
  • Projects: GIS SCRIME, the simbals company, ANR INEDIT, OSSIA, DIADEMS, MexCULTURE.


The Speech and Language Group

The Speech and Language group focuses on language both in its spoken and written forms.

  • The speech subgroup uses speech analysis and perception, mainly using prosody, for speech recognition, speaker and language identification, social affects characterisation, singing voice analysis.
  • The language subgroup works on language grammars and lexicons for text processing. We combine knowledge on both the language itself and the context to recover the structure of the spoken or written material.


  • Keywords: speech processing, prosody analysis, text processing, syntaxic analysis, automatic text generation.
  • Projects and Collaborations: DIADEMS, MexCULTURE, PADE, MaVoix, LIMSI (Orsay), IRIT (Toulouse), GIPSA-Lab (Grenoble), LAM (Paris), WASEDA (Japon).
Page mise à jour le 18/10/2017 à 19:50