ISSN 1000-9825, CODEN RUXUEW E-mail: jos@iscas.ac.cn
Journal of Software, Vol.17, No.5, May 2006, pp.983990 http://www.jos.org.cn
DOI: 10.1360/jos170983 Tel/Fax: +86-10-62562563
C 2006 by Journal of Software. All rights reserved.
基于虚拟不定长的语音库裁剪方法
张巍1+
, 吴晓如 2
, 赵志伟 2
, 王仁华 1
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
ZHANG Wei1+
, WU Xiao-Ru2
, ZHAO Zhi-Wei2
, WANG Ren-Hua1
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@ustc.edu.cn, http://cheung.colin.googlepages.com
Zhang W, Wu XR, Zhao ZW, Wang RH. Virtual non-uniform synthesis instances pruning approach for
corpus-based speech synthesis system. Journal of Software, 2006,17(5):983990. http://www.jos.org.cn/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
unchanged when less than 50% instances are pruned off, and the MOS does not severely degrade when the reduction
rate is above 50%.
Key words: speech synthesis; text to speech; pruning redundant synthesis instances; scalable speech synthesis system

下一页