EUROSPEECH 2003 - INTERSPEECH 2003
Synthesis of expressive speech has demonstrated that convincing natural sounding results are impossible to obtain without dealing with voice quality parameters. Time-domain and spectral-domain models of the voice source signal are presented. Then algorithms for analysis and synthesis of voice quality are discussed, including modification of the periodic and aperiodic components. These algorithms may be useful for applications such as pre-processing of speech corpora, modification of voice quality parameters together with intonation in synthesis, voice transformation.
Bibliographic reference. d'Alessandro, Christophe / Doval, Boris (2003): "Voice quality modification for emotional speech synthesis", In EUROSPEECH-2003, 1653-1656.