Home page for Greg Beller

I'm currently a PhD candidate in computer science, in University of Paris VI, France. My laboratory is part of IRCAM: Instute for Research and Coordination Acoustic/Music. It is designed to analyze and synthesize sounds (music, speech, instruments...) The subject of my thesis is the following: Analysis and generative model of the expressivity: Application to speech.

Greg Beller
IRCAM

Key research interests:

Expressive Speech Synthesis, Prosody, Voice Quality, Text-To-Speech, Emotional Voices, Content-based Transformations, Artistic Purposes

    I've been working for two years on a french expressive TTS for artistic purposes : Expressive speech is a useful tool in cinema, theater and contemporary music.
    We also have been working on an hybrid concatenative synthetizer on the intersection of speech and music

    The analysis of a recorded french expressive speech database has lead me to content-based transformations thanks to a vocoder technology developed in the team. Some examples and more informations could be found on my personal website.

Document Actions

Print this

Deadlines: International Conference on Music and Emotion 01 March 2009; Emotion-Aware Natural Interaction 01 April 2009; Real-Time Affect Analysis and Interpretation: Closing the Affective Loop in Virtual Agents and Robots 06 April 2009; More...

Workshops: AISB 2009 Symposium on Affective Bodily Expression Edinburgh, UK,
06 April 2009; International Conference on Music and Emotion University of Durham,
31 August 2009; More...

Portal usage statistics