基于虚拟不定长的语音库裁剪方法.PDFVIP

ISSN 1000-9825, CODEN RUXUEW E-mail: jos@ Journal of Software, Vol.17, No.5, May 2006, pp .983−990 http://www.j DOI: 10. 1360/jos170983 Tel/Fax : +86-10 © 2006 by Journal of Software. All rights reserved. ∗ 基于虚拟不定长的语音库裁剪方法 1+ 2 2 1 张 巍 , 吴晓如 , 赵志伟 , 王仁华 1( 中国科学技术大学 电子工程与信息科学系,安徽 合肥 230027) 2(安徽中科大讯飞信息科技有限公司,安徽 合肥 230088) Virtual Non-Uniform Synthesis Instances Pruning Approach for Corpus-Based Speech Synthesis System 1+ 2 2 1 ZHANG Wei , WU Xiao-Ru , ZHAO Zhi-Wei , WANG Ren-Hua 1(Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230027, China) 2(Anhui USTC Iflytek Co., Ltd., Hefei 230088, China) + Corresponding author: Phn: +86-551-5331851 ext 8048, E-mail: weizhang@, Zhang W, Wu XR, Zhao ZW, Wang RH. Virtual non-uniform synthesis instances pruning approach for corpus-based speech synthesis system. Journal of Softw are, 2006,17(5):983−990. .c n/1000- 9825/17/983.htm Abstract: Tailoring voice font, or pruning redundant synthesis instances, is an important issue of scalable Corpus-based Text To Speech (TTS) system. However, pruning redundant synthesis instances, usually results in the loss of non-uniform. In order to solve this problem, the concept of virtual non-uniform is proposed. According to this concept and the synthesis frequency of each instance, an algorithm named StaRp-VPA is constructed to make TTS scalable to hardware. In experiments, the naturalness scored by Mean Opinion Score (MOS) remains almost unch