A Synthesis Instance Pruning Approach Based on Virtual Non-uniform Replacements  

作　　者：张巍 凌震华 胡国平 王仁华 

机构地区：[1]Department of Computer Science, Ocean University of China, Qingdao 266100, China Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230027, China [2]Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230027, China [3]Anhui USTC Iflytek Co., Ltd., Hefei 230088, China

出　　处：《Tsinghua Science and Technology》2008年第4期515-521,共7页清华大学学报（自然科学版（英文版）

基　　金：the National Natural Science Foundation of China (No. 60602017)

摘　　要：The employment of non-uniform processes assists greatly in the corpus-based text-to-speech （TTS） system to synthesize natural speech. However, tailoring a TTS voice font, or pruning redundant synthesis instances, usually results in loss of non-uniform synthesis instances. In order to solve this problem, we propose the concept of virtual non-uniform instances. According to this concept and the synthesis frequency of each instance, the algorithm named StaRp-VPA is constructed to make up for the loss of nonuniform instances. In experimental testing, the naturalness scored by the mean opinion score （MOS） remains almost unchanged when less than 50% instances are pruned, and the MOS is only slightly degraded for reduction rates above 50%. The test results show that the algorithm StaRp-VPA is effective.The employment of non-uniform processes assists greatly in the corpus-based text-to-speech （TTS） system to synthesize natural speech. However, tailoring a TTS voice font, or pruning redundant synthesis instances, usually results in loss of non-uniform synthesis instances. In order to solve this problem, we propose the concept of virtual non-uniform instances. According to this concept and the synthesis frequency of each instance, the algorithm named StaRp-VPA is constructed to make up for the loss of nonuniform instances. In experimental testing, the naturalness scored by the mean opinion score （MOS） remains almost unchanged when less than 50% instances are pruned, and the MOS is only slightly degraded for reduction rates above 50%. The test results show that the algorithm StaRp-VPA is effective.

关 键 词：text-to-speech system speech synthesis synthesis instance pruning non-uniform unit 

分 类 号：TP391.42[自动化与计算机技术—计算机应用技术]