Sound and interaction

The Interaction group

We are exploring new approaches for the interaction between users and digital worlds, in particular 3D. This involves the design of new interaction techniques, the implementation 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 (Inria project-team common with the University of Bordeaux and CNRS) and the interaction group of ESTIA.

The Sound and Music Modeling Group (SMS)

We are looking for descriptions of sound and music that allow new forms of interactivity that can be used for music creation, browsing or learning music. We study all sound and musical dimensions, especially the temporal and spatial dimension, through computer processing of music, musicology of creative processes, and by taking into account perception and cognition.

  • Keywords: perceptual models of sound, musical similarity, interactivity modeling, spatialization analysis.

The Speech and Language group

The activities of the Speech and Language group deal with language in both oral and written form. The speech activity of the group deals with the analysis and perception of the voice from a prosodic point of view: voice recognition, identification of the speaker and the language, characterization of social affects, study of the sung voice. The language activity is interested in the functioning of languages in terms of grammar and lexicon for the needs of Automatic Language Processing. The structure of the sound or written material is formalized in relation to the language and the utterance.

  • Keywords: automatic speech processing, prosody analysis, TAL, syntactic analysis, automatic text generation.
  • Projects and collaborations : DIADEMS, MexCULTURE, PADE, MaVoix, LIMSI (Orsay), IRIT (Toulouse), GIPSA-Lab (Grenoble), LAM (Paris), WASEDA (Japan).