汉语文语转换系统中停顿指数的自动标注.pdfVIP

汉语文语转换系统中停顿指数的自动标注﹡ 赵永贞，刘挺，王志伟，陈惠鹏，邵艳秋 （哈尔滨工业大学计算机学院信息检索研究室 150001） （哈尔滨工业大学计算机学院语音处理研究室 150001） 摘要：本文采用了一个基于C-TOBI 的停顿指数标注的语料库，利用有指导的学习方法对 自动停顿指数标注方面做了一些有益的探索。本文共实现了三种方法：基本的马尔科夫模 型，引入了词长信息的马尔科夫模型，引入词长信息的马尔科夫模型结合基于转换的错误 驱动的学习方法。然后通过对 3000 句的真实文本进行开放测试，以基本的马尔科夫模型 的结果作为基准，实验结果不断改进，最终达到了 78.6% 的准确率，错误代价降低了 14.5%。 关键词：文语转换；停顿指数；马尔科夫模型；基于转换的错误驱动的学习 中图分类号：TP391 Assigning Break Indices for unrestricted texts in Mandarin Text to Speech System Zhao Yong-zhen, Liu Ting, Wang Zhi-wei, Chen Hui-peng , Shao Yan-qiu (Information Retrieval Laboratory, Department of computer, HIT, Harbin 150001, China) (Speech Processing Laboratory, Department of computer, HIT, Harbin 150001, China) Abstract: This paper uses a corpus with break indices based on C-TOBI. Applying supervised learning method, some useful attempts are made in the field of automatic break indices intonation. Three approaches, namely, the basic Markov model approach, the Markov model using word length approach, and the Markov model using word length combining Transformation-Based Error-Driven Learning approach, are presented. After implementing these three approaches, open tests are made on a corpus of 3,000 sentences. The performances are getting better and the last approach produces the highest accuracy, 78.5%, and results in 14.5% decrease in error-cost taking the result of Markov Model as baseline. Key Words: Text to Speech; Break Indices; Markov Model; Transformation-Based Error-Driven learning 1 引言 在汉语的文语转换系统中，要想得到流畅自然的合成语音，除了采用恰当的语音合成 技术之外，还必须有能准确地体现人类语音特征的韵律控制参数，比如重音、停顿、音调、 语调等。停顿指数[1]反映了人所能感知到的音节之间以及音节和无