Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
865672 | Tsinghua Science & Technology | 2008 | 7 Pages |
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
Related Topics
Physical Sciences and Engineering
Engineering
Engineering (General)
Authors
Wei (å¼ å·), Zhenhua (åéå), Guoping (è¡å½å¹³), Renhua (çä»å),