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.