Optimizing sub-cost functions for segment selection based on perceptual evaluations in concatenative speech synthesis

• Published in: 2004 IEEE International Conference on Acoustics, Speech and Signal Processing Vol. 1; pp. I - 657
• Main Authors: Toda, T., Kawai, H., Tsuzaki, M.
• Format: Conference Proceeding
• Language: English; Japanese
• Published: Piscataway, N.J IEEE 28.09.2004
• Subjects: Acoustic measurements; Acoustic testing; Applied sciences; Cost function; Degradation; Exact sciences and technology; Information, signal and communications theory; Laboratories; Natural languages; Performance evaluation; Signal processing; Speech analysis; Speech processing; Speech synthesis; Telecommunications and information theory; Degradation; Performance evaluation; Concatenation; Testing equipment; Cost function; Economic aspect; Cost analysis; Speech synthesis; Optimization
• ISBN: 9780780384842; 0780384849
• ISSN: 1520-6149
• DOI: 10.1109/ICASSP.2004.1326071

In concatenative speech synthesis, various factors affect the naturalness of synthetic speech. A cost for segment selection is calculated by integrating some sub-costs capturing the degradation of naturalness caused by such factors. In this paper, we optimize each sub-cost function for converting a linguistic feature or an acoustic parameter into a sub-cost based on perceptual evaluations. Two types of perceptual experiments are performed with test sets constructed by controlling the variations of sub-costs to evaluate the independent effect of each sub-cost and the interactions between them. We clarify the effectiveness of perceptually optimizing subcost functions from a result of a preference test comparing synthetic speech before and after the optimization.