IrcamAlign

Researcher Profile

  • 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 effectue l’alignement et donc la segmentation de signaux de parole en phones et diphones, et calcule une mesure de confiance par phone