TEXT-TO-AUDIO-VISUAL SPEECH SYNTHESIS

BASED ON PARAMETER GENERATION FROM HMM

Demonstrations

to-bu-ji-yu-u-wo-e-ru-ko-to-wa,
ji-N-ru-i-no-yu-me-da-tta


Generated from 4-state triphone HMMs	Generated from 7-State syllable HMMs

Reall Utterance