文章摘要
古力努尔·艾尔肯,艾斯卡尔·艾木都拉.基于声学特征的母语非汉语者声调研究[J].声学技术,2018,37(6):571~578
基于声学特征的母语非汉语者声调研究
Tone investigation of non-native Chinese speakers based on acoustic features
投稿时间:2017-06-22  修订日期:2017-08-15
DOI:10.16300/j.cnki.1000-3630.2018.06.011
中文关键词: 一阶差分|声调偏误|对比分析|维吾尔族学习者|时长
英文关键词: first order difference|tone errors|contrastive analysis|Uyghur learners|duration
基金项目:国家973项目(2013CB329301);国家自然科学基金项目(61063023)资助项目。
作者单位E-mail
古力努尔·艾尔肯 新疆大学信息科学与工程学院, 新疆乌鲁木齐 830046  
艾斯卡尔·艾木都拉 新疆大学信息科学与工程学院, 新疆乌鲁木齐 830046 askarhamdulla@sina.com 
摘要点击次数: 948
全文下载次数: 593
中文摘要:
      从提高满足少数民族普通话高自然度语音合成与高精度语音识别的实际应用需求出发,首次从实验语音学的角度对初级、中级和高级阶段的50名维吾尔族汉语学习者与10名母语为汉语普通话的说话人声调的一阶差分与时长以及相似度进行对比,并对其声调的一阶差分模式、声调时长等韵律参数进行了实验分析,得出维吾尔族学生对汉语声调的偏误情况以及与中国少数民族汉语水平等级考试(Master of Human Kinetics,MHK)成绩的关系。通过实验结果可以发现,三组维吾尔族人学习普通话的声调都有困难。两种语言的音系,语调和重音等特性影响了第二语言中的声调特性。归纳了维吾尔族学习者声调的基本声学特征,总结出了一些重要的规则和结论;为解决给汉语语音处理带来的困难,尤其是少数民族汉语的语音合成和语音识别方面的声调问题,提供了重要的参考依据。
英文摘要:
      Starting from the practical application requirements of ethnic minorities to improve the capabilities in the mandarin speech synthesis with high naturalness and the high precision mandarin speech recognition, this paper makes a comparison of the first order difference, the time length and similarity of tones between 50 Uyghur students in the junior, intermediate and advanced stages and 10 native mandarin speakers from the perspective of experimental phonetics. The experimental results of the first order difference model, the tone duration and other prosodic parameters are analyzed, and the relationship between Uyghur students' Chinese tone errors and MHK scores is obtained. It can be found that the three groups have difficulty in learning Mandarin tones, and the characteristics of phonological, intonation and stress of the two kinds of languages affect the tone characteristics in the second language. The tonality feature and tone duration of Uyghur learners and some important rules and conclusions are summarized. The present research can help strengthen phonetic teaching among ethnic minorities and provide more effective empirical data for speech synthesis and speech recognition of the Chinese spoken by ethnic minorities.
查看全文   查看/发表评论  下载PDF阅读器
关闭