INTERSPEECH 2006 - ICSLP
Ninth International Conference on Spoken Language Processing

Pittsburgh, PA, USA
September 17-21, 2006

A Technique for Controlling Voice Quality of Synthetic Speech Using Multiple Regression HSMM

Makoto Tachibana, Takashi Nose, Junichi Yamagishi, Takao Kobayashi

Tokyo Institute of Technology, Japan

This paper describes a technique for controlling voice quality of synthetic speech using multiple regression hidden semi-Markov model (HSMM). In the technique, we assume that the mean vectors of output and state duration distribution of HSMM are modeled by multiple regression with a parameter vector called voice quality control vector. We first choose three features for controlling voice qualities, that is, "smooth voice - nonsmooth voice," "warm - cold," "high-pitched - low-pitched," and then we attempt to control voice quality of synthetic speech for these features. From the results of several subjective tests, we show that the proposed technique can change these features of voice quality intuitively.

Full Paper

Bibliographic reference.  Tachibana, Makoto / Nose, Takashi / Yamagishi, Junichi / Kobayashi, Takao (2006): "A technique for controlling voice quality of synthetic speech using multiple regression HSMM", In INTERSPEECH-2006, paper 1778-Thu2A3O.3.