Recherche + Développement

Researcher Profile

  • Audio Indexation

  • Expressive speech synthesis and transformation

  • Multiple-F0 estimation, noise estimation, automatic music transcription, music signal processing

  • Large scale machine learning, speech and prosodic analysis

  • Détection d'événements sonores

  • Digital signal processing and machine learning

  • Audio signal processing, Audio content analysis, Music information retrieval, Source separation, Musical acoustics and technology, Pattern recognition, machine learning

  • Modelling the task of emergent musical rhythm perception - including models of syncopation, rhythmic complexity, rhythmic expectancy, downbeat determination, use of continuous wavelet transforms for time-frequency representations of musical rhythm

  • Speech processing, machine listening (detection, localization, separation), machine learning

  • Développement Ecrin, Cuidado, Semantic HIFI

  • Hidden Markov Models (HMM) for Image and Speech processing, Speech recognition, HMM Speech synthesis (HTS), Voice Conversion, Signal and Image Segmentation, Data fusion