计算机科学与应用  >> Vol. 6 No. 7 (July 2016)

傣语语音合成中的文本归一化方法
An Approach to Normalization of Dai Text for Speech Synthesis

DOI: 10.12677/CSA.2016.67051, PDF, HTML, XML, 下载: 1,506  浏览: 2,995  国家自然科学基金支持

作者: 伍烛梅, 杨鉴*, 王展:云南大学信息学院,云南 昆明

关键词: 傣语语音合成文本分析归一化 Dai Language Speech Synthesis Text Analysis Normalization

摘要: 本文以开发傣语语音合成系统为目的,重点研究傣语文本中的数字归一化和特殊字符归一化问题。数字和特殊字符都属于傣语文本中的非标准词,文本归一化的主要目的是用标准词表示非标准词的发音。归一化处理过程包括:非标准词识别、歧义判断、消歧处理和非标准词转换为标准词4个步骤。本文采用基于规则和上下文关键词相结合的方法识别非标准词,利用正则表达式判断其歧义类型,根据转换规则对非标准词进行消歧并确定其正确的傣文读音。实验结果表明,本文提出的文本归一化方法的正确率达到了94.6%,可以完全满足傣语文语转换系统前端文本分析的需求,并具有良好的自然语言处理应用价值。
Abstract: With the purpose of developing a Dai speech synthesis system, this paper focuses on the study of Dai numbers and special characters normalization. Both numbers and special characters are the non-standard words in Dai text. The main purpose of the text normalization is to represent the pronunciation of non-standard words with standard words. The normalization process includes non-standard words recognition, ambiguity judgment, disambiguation and non-standard transla-tion. Firstly, the non-standard words are recognized and the ambiguous types of these non-stan- dard words are determined using a method based on rule-based and context-keyword, in this paper. Then, the types of ambiguity are judged on regular expression. Lastly, the correct pronunciation of no-standard words is determined according to the transformation rules. Experimental results show that the correct rate of this normalization is more than 94.6%. This purposed method can fully satisfy the front-end text analysis in Dai text to speech conversion system, and has a good natural language processing application value.

文章引用: 伍烛梅, 杨鉴, 王展. 傣语语音合成中的文本归一化方法[J]. 计算机科学与应用, 2016, 6(7): 415-422. http://dx.doi.org/10.12677/CSA.2016.67051

参考文献

[1] 戴红亮, 张公瑾. 西双版纳傣语基础教程[M]. 北京: 中央民族大学出版社, 2012.
[2] 玉康, 张秋生, 岩温龙. 西双版纳傣语基础教程[M]. 昆明: 云南民族出版社, 2006.
[3] Gao, L., Chen, Q., Li, Y.H., et al. (2010) Several Problems of Text Analysis in Tibetan Speech Synthesis. Journal of Northwest University for Nationalities (Natural Science Edition), 2, 1-7.
[4] Hopkins, H. and Edmunds, T. (2016) Broadcast System Using Text to Speech Conversion. United States Patent 9263027.
[5] Haunschild, R. and Bornmann, L. (2016) Normalization of Mendeley Reader Counts for Impact Assessment. Journal of in Formetrics, 10, 62-73.
http://dx.doi.org/10.1016/j.joi.2015.11.003
[6] Sproat, R., Black, A.W. and Chen S. (2001) Normalization of Non-Standard Words. Computer Speech & Language, 15, 287-333.
http://dx.doi.org/10.1006/csla.2001.0169
[7] 戴红亮. 西双版纳傣语数词层次分析[J]. 民族语文, 2004(4): 22-26.
[8] 邱涛, 王斌, 杨晓春. 利用关键因子过滤的正则表达式匹配算法[J]. 计算机科学与探索, 2016(3): 326-337.