4. Wavelet Analysis for a Text-to-Speech (TTS) System
Mei Kobayashi, Masaharu Sakamoto, Takashi Kei SAITO, Yasuhide Hashimoto, Masafumi Nishimura, Kazuhiro Suzuki · Society for Industrial and Applied Mathematics eBooks · 1998
This chapter presents results from a case study in which wavelet analysis was used in the development of a Japanese text-to-speech (TTS) system for personal computers (PCs). We developed two new wavelet-based technologies to improve the quality of speech output from TTS systems: accurate pitch mark determination by wavelet analysis and speech waveform generation using a modified time domain pitch-synchronous overlap-add (TD-PSOLA) method.