Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Speech Quality Improvement in TTS System Using ABS/OLA Sinusoidal Model

Jae-Hyun Bae, Heo-Jin Byeon, Yung-Hwan Oh

Division of Computer Science, Department of Computer Science, KAIST, Kusong-dong, Yusong-gu, Taejon, Korea

In this paper, we propose a novel unit concatenation and synthesis method using ABS/OLA sinusoidal model. Phase succession is used in the unit synthesis assuming that the pitch onset time of the first frame in a given unit is the frame center. In the unit concatenation, the phase succession and interpolation of the sinusoid amplitudes via several frames around the concatenation point is utilized. As a result of applying this method to the Text-to- Speech(TTS) system, we got speech samples which were more intelligible and natural than those produced by conventional method.

Full Paper

Bibliographic reference.  Bae, Jae-Hyun / Byeon, Heo-Jin / Oh, Yung-Hwan (2000): "Speech quality improvement in TTS system using ABS/OLA sinusoidal model", In ICSLP-2000, vol.3, 905-908.