A hidden Markov-model-based trainable speech synthesizer

✍ Scribed by R.E. Donovan; P.C. Woodland

• Book ID: 102566830
• Publisher: Elsevier Science
• Year: 1999
• Tongue: English
• Weight: 416 KB
• Volume: 13
• Category: Article
• ISSN: 0885-2308
• DOI: 10.1006/csla.1999.0123

✦ Synopsis

This paper presents a new approach to speech synthesis in which a set of cross-word decision-tree state-clustered context-dependent hidden Markov models are used to define a set of subphone units to be used in a concatenation synthesizer. The models, trees, waveform segments and other parameters representing each clustered state are obtained completely automatically through training on a 1 hour single-speaker continuous-speech database. During synthesis the required utterance, specified as a string of words of known phonetic pronounciation, is generated as a sequence of these clustered states using a TD-PSOLA waveform concatenation synthesizer. The system produces speech which, though in a monotone, is both natural sounding and highly intelligible. A Modified Rhyme Test conducted to measure segmental intelligibility yielded a 5•0% error rate. The speech produced by the system mimics the voice of the speaker used to record the training database. The system can be retrained on a new voice in less than 48 hours, and has been successfully trained on four voices.