An articulatory and phonatory synthesis model for production of high quality speech and singing

Peter Birkholz, Bernd J. Kröger

Recently a high quality articulatory voice and speech synthesizer
comprising a three dimensional articulatory model and a high quality
acoustic model has been developed [1]. Articulatory movements are
controlled using a gesture-based controll approach [2]. A parametric
voice source model is used comprizing detailled acoustic modeling
inclunding acoustic interaction between the subglottal, glottal, and
supraglottal system. The model is capable of producing high quality
samples for speech and singing. Demonstrations of homophonic and
polyphonic singing will be given on the conference.
[1] Birkholz P, Jackel D, Kröger BJ (2007) Simulation of losses due to
turbulence in the time-varying vocal system. IEEE Transactions on Audio,
Speech, and Language Processing 15: 1218-1225
[2] Birkholz P, Jackel D, Kröger BJ (2006) Construction and control of a
three-dimensional vocal tract model. Proceedings of the International
Conference on Acoustics, Speech, and Signal Processing (ICASSP 2006),
Toulouse, France, pp. 873-876

audio-example on demand

Dr.-Ing. Peter Birkholz
Institut for Computer Science, University of Rostock
Albert-Einstein-Str. 21, 18059 Rostock, Germany
Email: piet@informatik.uni-rostock.de Tel: +49-381-498-7483

(2)
Prof. Dr. phil. Dipl.-Phys. Bernd J. Kröger
Department of Phoniatrics, Pedaudiology, and Communication Disorders
University Hospital Aachen (UKA) and Aachen University, Pauwelsstraße 30, D-52074 Aachen, Germany
Email: bkroeger@ukaachen.de phone: +49-241-80-85222 fax: +49-241-80-82513