7th International Conference on Spoken Language Processing

September 16-20, 2002
Denver, Colorado, USA

A Data-Driven Approach to Source-Formant Type Text-to-Speech System

Hiroki Mori, Takahiro Ohtsuka, Hideki Kasuya

Utsunomiya University, Japan

A data-driven formant-type TTS system is proposed. The formanttype speech synthesizer is one of the most promising architectures to enable flexible control of various voice qualities. By applying the ARX-based speech analysis method, source and formant parameters are automatically obtained. It is shown that a TTS system can be built by using the parameters, without requiring any heuristic rules to control vocal tract characteristics.


Full Paper

Bibliographic reference.  Mori, Hiroki / Ohtsuka, Takahiro / Kasuya, Hideki (2002): "A data-driven approach to source-formant type text-to-speech system", In ICSLP-2002, 2365-2368.