| 本文已被：浏览 4677次 下载 6251次 |
码上扫一扫！ |
|
|
| 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
|
|
| 摘要: |
| 语音库裁剪或语音库去冗余,是大语料库语音合成技术的一个重要问题.提出了虚拟不定长替换的概念,以弥补不定长的损失.结合合成使用变体的频度,构建了语音库裁剪算法StaRp-VPA.该算法能够以任意比例裁剪语音库.实验表明:当裁剪率小于50%时,合成自然度几乎没有下降;当裁剪率大于50%时,合成自然度也不会严重降低. |
| 关键词: 语音合成 文语转换 语音库裁剪 可伸缩语音合成系统 |
| DOI： |
| 分类号: |
| 基金项目:Supported bythe National High-Tech Research and Development Plan of China under Grant No.2004AA114030(国家高技术研究发展计划(863)) |
|
| Virtual Non-Uniform Synthesis Instances Pruning Approach for Corpus-Based Speech Synthesis System |
|
ZHANG Wei,WU Xiao-Ru,ZHAO Zhi-Wei,WANG Ren-Hua
|
| 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 |
