University homepage
University of Helsinki Department of Speech Sciences - Faculty of Behavioural Sciences
 
Glott-HMM synthesis
 
Project members:
Tuomo Raitio
Paavo Alku
Helsinki University of Technology
Department of Signal Processing and Acoustics
P.O. Box 3000
FI-02015 TKK
Finland

Antti Suni
Martti Vainio
University of Helsinki
Department of Speech Sciences
Siltavuorenpenger 20 A
PO Box 9
00014 University of Helsinki
Finland

  
About GlottHMM
 The GlottHMM is a physiologically oriented HMM-based speech synthesis system. GlottHMM utilizes glottal inverse filtering in order to decompose speech into the glottal excitation and the vocal tract filter. Both the source and the filter characteristic are individually modeled in the framework of HMM. In GlottHMM synthesis, the glottal excitation is synthesized through interpolating and concatenating natural glottal flow pulses, and the excitation signal is further modified to reproduce the time-varying changes in the natural voice source. The proposed novel procedure enables both synthesis of natural sounding speech and easy control over individual speech features that contribute to the perceived quality of speech.

The GlottHMM project builds on the work of Dr. Alku's group on voice source modelling and signal processing and Dr.Vainio's group with expertise on prosody modelling and speech synthesis.