Control concepts for articulatory speech synthesis
Peter Birkholz, Ingmar Steiner, Stefan Breuer · 2007
We present two concepts for the generation of gestural scores to control an articulatory speech synthesizer. Gestural scores are the common input to the synthesizer and constitute an or-ganized pattern of articulatory gestures. The first concept gen-erates the gestures for an utterance using the phonetic transcrip-tions, phone durations, and intonation commands predicted by the Bonn Open Synthesis System (BOSS) from an arbitrary in-put text. This concept extends the synthesizer to a text-to-speech synthesis system. The idea of the second concept is to use tim-ing information extracted from Electromagnetic Articulography signals to generate the articulatory gestures. Therefore, it is a concept for the re-synthesis of natural utterances. Finally, ap-plication prospects for the presented synthesizer are discussed. 1.