Seminar by Fernando Villavicencio on voice transformation applied to singing voice
Seminar by Fernando Villavicencio on voice transformation applied to singing voice
14 Nov 2014
Fernando Villavicencio, from National Institute of Informatics in Japan, gives a seminar titled "Some applications of Voice-Transformation to Singing-Voice" on Friday November 14th at 12:00h in room 52.s31.
Abstract:
Voice Conversion aims to the transformation of a “source” speaker in order to make it perceptually identifiable as a particular “target” one. Although the main work done in this field has been focused in spoken voice there are potential application for singing-voice synthesis (e.g. for singer’s database conversion on singing synthesis systems).
In this talk we will present previous work applying Voice-Conversion and related Voice-Transformation experimentation to Yamaha’s singing-voice synthesizer “VOCALOID”. The works include singer’s identity conversion by means of statistical timbre-features mapping (GMM) and accurate spectral envelope modelling. Also, aiming for large vocal-quality control from modal (normal) singing, experimentation for voice-quality transformation by source/filter estimation & transformation will be presented. The talk will include an introduction of the National Institute of Informatics and the Sound Media Group.
Biography:
Born in 1977 in Guadalajara, Mexico. Fernando Villavicencio received the Bachelor degree in Electronics and Communications Engineering by the Autonomous University of Guadalajara (1999) and Master degrees in Telecommunications (2002) and Signal Processing & Digital Design (2003) by the National Polytechnic Institute of Mexico and Rennes I University in France respectively. He received the Doctor degree at Pierre and Marie Curie University of Paris following his research work in High-Quality Voice Conversion at the Institute of Research and Acoustic-Music Coordination (IRCAM) under the supervision of Xavier Rodet and Axel Röbel.
F. Villavicencio joined the Music Technology Group of Pompeu Fabra University (2008-2009) to work on singing-voice transformation within a collaboration with Yamaha Corporation. From 2009 to September 2014 was member of the Speech Technology Group of Yamaha’s Sound Technology R&D center in Hamamatsu, Japan. He is currently post-doctoral fellow at the Sound Media Group of the National Institute of Informatics in Tokyo, Japan. His research interests include general topics on speech synthesis, voice transformation, and speaker verification.