在文语转换(TTS)系统中,正确标记短语间的停顿对提高合成语音的自然度起着重要作用。本文介绍了一种在汉语语句中自动预测短语间停顿的方法。首先,文本进行分词,并转换为一列由词性标记所组成的序列;然后使用马尔可夫模型,利用人工标注数据库训练词语连接处词性标注序列的概率分布和连接类型序列的距离信息,得到输入的词性标记序列对应的具有最大似然概率的连接类型序列,最后利用后处理规则进行适当的纠错。本文针对不同的模型参数进行了测试,短语间停顿自动预测的召回率和连接类型正确率分别达到了68.2%和85.1% ,取得了比较满意的结果。
Abstract
In TTS system , it is very important to mark phrase breaks correctly for high naturalness and quality of output speech. The paper discusses an algorithm for automatically predicting phrase breaks in Chinese sentences. At first , the text is segmented to words and converted to a sequence of part-of-speech tags ; then based on the POS tags sequence parameters and phrase-break distance information from training , Markov model is used to get the most likely phrase break sequence. In this paper several model parameters and rules are used , the recalling rate of predicated breaks is 68.2% , the overall predicted juncture correct rate is 85.1%.
关键词
计算机应用 /
中文信息处理 /
短语间停顿 /
词性标注 /
马尔可夫模型
{{custom_keyword}} /
Key words
computer application /
Chinese information processing /
phrase break /
part-of-speech tagging /
markov model
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Taylor , P and Black , A. Assigning Phrase Breaks from Part-of-Speech Sequences[A] . Proceedings of Eurospeech97 , Rhodes , Greece , 1997 ,12 :995 - 998.
[2] Ostendorf , M. and Veilleux , N. A Hierarchical Stochastic Model for Automatic Prediction of Prosodic Boundary Location[J] . Computational Linguistics , 1994 ,20 (1) .
[3] Church , K. W. and Gale , W. A. A Comparison of the Enhanced Good - Turing and Deleted Estimation Methods for Estimating Probabilities of English Bigrams [J] . Computer Speech and Language. 1991. 5 :19 - 54.
[4] Wang , M. Q. and Hirschberg , J. Automatic Classification of Intonational Phrasing Boundaries [J] . Computer Speech and Language , 1992. 6 (2) :175 - 196.
[5] Veilleux , N. M. , Ostendorf , M. , Price , P. J. , and Hufnagel , S. S. Markov Modelling of Prosodic Phrase Structure[A] . International Conference on Speech and Signal Processing. IEEE ,1990.
[6] Steven Abney. Prosodic Structure , Performance Structure and Phrase Structure [A] . In : Proceedings , Speech and Natural Language Workshop , Morgan Kaufmanns Publishers , San Mateo , CA , 1992 , 425 - 428.
[7] 牛正雨,柴佩琪. 基于边界点词性特征统计的韵律短语切分[J] . 中文信息学报,2001 ,15 (5) .
[8] 曹剑芬. 普通话节奏的声学语音学特性[A] . 第四届全国现代语音学学术会议论文集,1999.
[9] 谌卫军,林福宗,李建民,张钹. 基于概率统计的韵律短语分析[J] . 计算机工程与应用,2001 , (3) .
[10] 周强. 汉语短语的自动划分与标注[J] . 中文信息学报,1996. 10 (1) .
[11] 应宏,蔡莲红. 基于结构助词驱动韵律短语界定的研究[J] . 中文信息学报,1999 ,13 (6) .
[12] 潘伟锵,贺前华,韦岗. 文语转换系统中虚词停顿的研究[J] . 华南理工大学学报(自然科学版) , 2002 , (6) .
[13] 胡伟湘,徐波,黄泰翼. 汉语韵律边界的声学实验研究[J] . 中文信息学报,2002 ,16 (1) .
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(243 KB)
