| 基于语料库的藏语语音合成单元选择算法 |
| |
| 引用本文： | 才让卓玛,才智杰. 基于语料库的藏语语音合成单元选择算法[J]. 中文信息学报, 2017, 31(5): 59-63 |
| |
| 作者姓名： | 才让卓玛 才智杰 |
| |
| 作者单位： | 青海师范大学 计算机学院,青海 西宁 810008 |
| |
| 基金项目： | 国家自然科学基金(61262051,61163018);国家社科基金(16BYY167,15BYY167,14BYY132,13BYY141);教育部“春晖计划”(Z2016077);青海省基础研究项目(2017-ZJ-767) |
| |
| 摘 要： | 在基于语料库的语音合成方法中,语音合成单元选择的优劣直接影响合成语音的自然度和流畅性。该文针对藏语言文字的特点,提出以基本构件、组合构件、字、词及句单元相融合的混合单元语音合成策略,并提出了藏语语音合成混合单元选择算法。主观评价与客观评测数据表明该策略与算法有效和合理,各类合成单元在开放语料上的覆盖率与语音合成效果均达到预期的目标。
|
| 关 键 词： | 语音合成 单元选择 基本构件 组合构件 |
Unit Selection Algorism for Corpus-based Tibetan Speech Synthesis |
| |
| CAI Rangzhuoma,CAI Zhijie. Unit Selection Algorism for Corpus-based Tibetan Speech Synthesis[J]. Journal of Chinese Information Processing, 2017, 31(5): 59-63 |
| |
| Authors: | CAI Rangzhuoma CAI Zhijie |
| |
| Affiliation: | College of Computer Science, Qinghai Normal University, Xining, Qinghai 810008, China |
| |
| Abstract: | In the corpus-based text to speech system, the choices of unit selection impact directly on the quality of synthesized speech. By analyzing the features of Tibetan language, this paper proposes not only a hybrid strategy which mixed components, characters, words and sentences, but also a corpus-based unit selection algorism for Tibetan Speech Synthesis. Subjective assessment results and objective evaluation results indicate that the algorithms are effective, the coverage and synthesized speech of units are satisfactory reached expected target. |
| |
| Keywords: | speech synthesis unit selection basic components combinational components |
|
| 点击此处可从《中文信息学报》浏览原始摘要信息 |
|
点击此处可从《中文信息学报》下载全文 |
|
