Control concepts for articulatory speech synthesis

Abstract

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 organized pattern of articulatory gestures. The first concept generates the gestures for an utterance using the phonetic transcriptions, phone durations, and intonation commands predicted by the Bonn Open Synthesis System (BOSS) from an arbitrary input text. This concept extends the synthesizer to a text-to-speech synthesis system. The idea of the second concept is to use timing information extracted from Electromagnetic Articulography signals to generate the articulatory gestures. Therefore, it is a concept for the re-synthesis of natural utterances. Finally, application prospects for the presented synthesizer are discussed.