Pierre Lanchantin

Researcher Profile

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

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

  • Voice Conversion, Analysis-Transformation-Synthesis for Spoken and Sung Voices, Statistical Models, Digital Signal Processing for Audio/Music

Software Form


  • IrcamAlign performs alignment and segmentation of speech signals into phones and diphones, and calculates a measure of confidence for each phone.