Sprachsyntheseeinrichtung nach dem phonetischen Hidden-Markov-Modell.
摘要
A method and a system for synthesizing speech from unrestricted text, based on the principle of associating to a written string of text the sequence of speech features vectors that most probably model the corresponding speech utterance. The synthesizer is based on the interaction between two different Ergodic Hidden Markov Models: an acoustic model reflecting the phonotactical constrains and a phonetic model interfacing phonemic transcription to the speech features representation. <IMAGE>
申请公布号
DE69022237(T2)
申请公布日期
1996.05.02
申请号
DE1990622237T
申请日期
1990.10.16
申请人
INTERNATIONAL BUSINESS MACHINES CORP., ARMONK, N.Y., US
发明人
GIUSTINIANI, MASSIMO, I-00173 ROMA, IT;PIERUCCI, PIERO, I-00146 ROMA, IT