Control of Fundamental Frequency Contours Using the Generation Process Model in HMM–Based Speech Synthesis

摘要：

A method was proposed to increase the naturalness of prosody generated with speech synthesis based on hidden Markov models (HMMs). This method adds a constraint to the fundamental frequency contours (F0 contours) during the HMM-based speech synthesis. The constraint adopted is the generation process model of F0 contours (F0 model). The method first extracts the F0 model parameters from the original F0 contour (generated by the HMM-based speech synthesis) and then optimizes them successively by referring to the pre-trained HMMs. The experimental results show that the proposed method can improve naturalness when the F0 control by the original method is inadequate.

关键词： HMM-based speech synthesis generation process model F0 contour

作者: Tetsuya Matsuda Keikichi Hirose Nobuaki Minematsu

作者单位: Graduate School of Information Science and Technology, The University of Tokyo 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan

会议类型: 国际会议

会议名称: 2010 IEEE 10th International Conference on Signal Processing(第十届信号处理国际会议 ICSP 2010)

会议地点: 北京

会议语种:英文

页码: 617-620

在线出版日期: 2010-08-24（万方平台首次上网日期，不代表论文的发表时间）