Speech Prosody 2010 Chicago, IL, USA May 10-14, 2010

Expressive Speech Style Transformation: Voice Quality and Prosody Modification Using a Harmonic plus Noise Model

Carlos Monzo, Angel Calzada, Ignasi Iriondo, Joan Claudi Socoro

Grup de Recerca en Tecnologies Media, Universitat Ramon Llull, Barcelona, Spain

This paper proposes an approach to transform speech from a neutral style into other expressive styles using both prosody and voice quality (VoQ). The main aim is to validate the usefulness of VoQ in the enhancement of expressive synthetic speech. A Harmonic plus Noise Model (HNM) is used to modify speech following a set of rules extracted from an expressive speech corpus with five categories (neutral, happy, sensual, aggressive and sad). Finally, modified speech utterances were used to perform a perceptual test. These results indicate that listeners prefer prosody together with VoQ transformation instead of only prosody modification.

Index Terms: Expressive speech transformation, voice quality, prosody, Harmonic plus Noise Model

Full Paper

Bibliographic reference.  Monzo, Carlos / Calzada, Angel / Iriondo, Ignasi / Socoro, Joan Claudi (2010): "Expressive speech style transformation: voice quality and prosody modification using a harmonic plus noise model", In SP-2010, paper 985.