题名 | 汉语普通话韵律模型研究 |
作者 | 胡伟湘 |
学位类别 | 工学博士 |
答辩日期 | 2007-06-22 |
授予单位 | 中国科学院研究生院 |
授予地点 | 中国科学院自动化研究所 |
导师 | 徐波 |
关键词 | 韵律结构 韵律边界 重音 决策树 Prosody structure prosody boundary Stressed word CART decision tree |
其他题名 | Study on Prosody Modeling in Chinese |
学位专业 | 模式识别与智能系统 |
中文摘要 | 利用朗读语料库ASCCD,本文深入分析了汉语普通话韵律特征的声学表现,提出了针对普通话的韵律边界、重音的自动检测模型。用实验研究方法实现了从普通的语音到带有韵律结构特征的结构化语音的跨越。进一步根据说话人特点的不同,研究了应用极大后验概率MAP算法的说话人自适应方法。最后也简略分析了韵律结构与句法结构的部分相关关系,以及语法分词对韵律边界自动检测的贡献。具体来说,本文工作主要取得了以下几个方面的研究成果:(1)、研究了普通话朗读语音的韵律结构的声学表现特征,统计分析了部分特征的数值分布。进一步从语料库统计分析角度验证了有关韵律的研究结果:音高下倾、音高重置、音高低线的边界提示功能和音高高线的重音提示功能等等。(2)、通过构造合理的声学特征,提出了一种基于CART决策树的韵律边界自动检测模型,该模型不仅能有效地对韵律边界进行自动识别,而且还能够得到各类声学特征的贡献大小。(3)、在CART决策树自动检测模型基础上,依据韵律特征局部比较特性,进一步提出了分层解析的自动检测模型,较大地提高了韵律边界自动检测准确性。同时也提出了结合GMM的韵律边界自动检测模型。(4)、应用CART决策树建立了重音级别的自动检测模型,同时也提出了基于概率混合模型的重音自动检测模型。(5)、研究了应用极大后验概率MAP算法的说话人自适应方法。提高了韵律边界和重音级别检测模型的鲁棒性。(6)、初步研究了句法结构和韵律结构的比较关系,并尝试结合语法分词信息的韵律边界自动检测模型。 |
英文摘要 | Using large speech corpus (ASCCD) labeled with prosodic structure, the dissertation investigated the relationship between acoustic correlates and prosodic structure (involving prosodic boundary and stressed words) for Chinese Mandarin.We proposed automatic recognition model for prosodic boundary and stressed words. It explored the bridge from °at speech with combination syllables to structured speech with prosody information. We also studied the method for speaker adaptation by MAP algorithm. Finally, we analyzed the correlativity between prosodic structure and syntax structure.The dissertation includes the following work:(1) We studied the acoustic correlates for prosodic boundary and stressed words. By statistical method with large speech corpus, it validated some important argumentations in phonetics such as declination of pitch contour in a phrase,pitch resetting on boundary, prosodic structure correlated with bottom line and stressed words correlated with top pitch line separately, and so on.(2) In the dissertation, we constructed a series of feature vectors, and proposed a CART model for prosodic boundary location. Such model could also evaluate the importance of each feature vector.(3) Thinking about the prosody hierarchy, we proposed multi-step model for prosody boundary location, the GMM model also be tried. Both improved the performance.(4) Further, we used CART model for stressed words detecting, and a mixture model with probability was also proposed.(5) We investigated speaker adaptation method with MAP algorithm, which improve the models' robustness both for prosody boundary location and accent words detection.(6) In the end, we analyzed the correlativity between prosodic structure and syntax structure. And managed to combine the syntax information to improve the accuracy of boundary location. |
语种 | 中文 |
其他标识符 | 199918014605735 |
内容类型 | 学位论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/6035] ![]() |
专题 | 毕业生_博士学位论文 |
推荐引用方式 GB/T 7714 | 胡伟湘. 汉语普通话韵律模型研究[D]. 中国科学院自动化研究所. 中国科学院研究生院. 2007. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论