Automatic generation of speech synthesis units based on closed loop training

• Published in: 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing Vol. 2; pp. 963 - 966 vol.2
• Main Authors: Kagoshima, T., Akamine, M.
• Format: Conference Proceeding
• Language: English
• Published: Washington DC IEEE 1997; IEEE Computer Society Press
• Subjects: Applied sciences; Clustering methods; Degradation; Dictionaries; Exact sciences and technology; Information, signal and communications theory; Minimization methods; Research and development; Signal processing; Speech processing; Speech processing and communication systems; Speech synthesis; Synthesizers; Telecommunications and information theory; Training data; Virtual colonoscopy; Cluster analysis; Closed loop; Prosody; Speech synthesis; Artificial intelligence
• ISBN: 0818679190; 9780818679193
• ISSN: 1520-6149; 2379-190X
• DOI: 10.1109/ICASSP.1997.596098

This paper proposes a new method for automatically generating speech synthesis units. A small set of synthesis units is selected from a large speech database by the proposed closed loop training method (CLT). Because CLT is based on the evaluation and minimization of the distortion caused by the synthesis process such as prosodic modification: the selected synthesis units are most suitable for synthesizers. The CLT is applied to a waveform concatenation based synthesizer, whose basic unit is CV/VC (diphone). It is shown that synthesis units can be efficiently generated by CLT from a labeled speech database with a small amount of computation. Moreover, the synthesized speech is clear and smooth even though the storage size of the waveform dictionary is small.