8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Articulatory Synthesis of Singing

Peter Birkholz

Institute for Computer Science, University of Rostock, Germany

Germany A system for the synthesis of singing on the basis of an articulatory speech synthesizer is presented. To enable the synthesis of singing, the speech synthesizer was extended in many respects. Most importantly, a rule-based transformation of a musical score into a gestural score for articulatory gestures was developed. Furthermore, a pitch-dependent articulation of vowels was implemented. The results of these extensions are demonstrated by the synthesis of the canon Dona nobis pacem. The two voices in the canon were generated with the same underlying articulatory models and the same musical score, the only difference being that their pitches differ by one octave. Index Terms: Articulatory singing synthesis

Full Paper
Audio Demonstration
- This is the canon "Dona nobis pacem" generated with an articulatory synthesizer ( for the Singing Synthesis Challenge. The two synthetic voices were generated with the same vocal tract model and differ only in the pitch (by one octave).

Bibliographic reference.  Birkholz, Peter (2007): "Articulatory synthesis of singing", In INTERSPEECH-2007, 4001-4004.