A Synthesis Instance Pruning Approach Based on Virtual Non-uniform Replacements |
| |
| Authors: | ZHANG Wei LING Zhenhua HU Guoping WANG Renhua |
| |
| Institution: | aDepartment of Computer Science, Ocean University of China, Qingdao 266100, China;bDepartment of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230027, China;cAnhui USTC Iflytek Co., Ltd., Hefei 230088, China |
| |
| Abstract: | 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 non-uniform 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. |
| |
| Keywords: | text-to-speech system speech synthesis synthesis instance pruning non-uniform unit |
| 本文献已被 维普 万方数据 ScienceDirect 等数据库收录！ |
|
