| 基于韵律信息的语种辨识系统 |
| |
| 引用本文： | 侯丽敏,缪炜.基于韵律信息的语种辨识系统[J].上海大学学报(自然科学版),2009,15(5):441-444. |
| |
| 作者姓名： | 侯丽敏 缪炜 |
| |
| 作者单位： | 上海大学 通信与信息工程学院,上海 200072 |
| |
| 基金项目： | 上海市教委重点学科建设资助项目，上海市教委基金资助项目 |
| |
| 摘 要： | 提出利用超声层次上的韵律信息来进行语种辨识.在子词分割的基础上结合元音/辅音检测模型,将语音分割为CnV的假音节模型,然后对每个假音节提取一个五维的特征韵律参数.分割结果比传统的分割方法更接近实际的音节结构.在韵律系统中,对所有的语言建立高斯混合模型(GMM),研究模型的离散度和模型间的干扰程度.实验表明,韵律模型对不同的语言、不同的语系和同一语系中不同语言均具有一定的区分效果.
|
| 关 键 词： | 语种辨识 韵律 高斯混合模型 |
| 收稿时间： | 2008-06-25 |
Prosodic Information Used in Language Identification |
| |
| HOU Li-Min,MIAO Wei.Prosodic Information Used in Language Identification[J].Journal of Shanghai University(Natural Science),2009,15(5):441-444. |
| |
| Authors: | HOU Li-Min MIAO Wei |
| |
| Affiliation: | School of Communication and Information Engineering, Shanghai University, Shanghai 200072, China |
| |
| Abstract: | This paper deals with automatic language identification based on prosodic features and rhythmic information.A segmentation method has been used to divide the speech signal into sub-word units,and with vowel/consonantal detection,segment the speech into vowel units and consonantal units.Pseudo-syllable units are then produced.Several parameters are extracted and modeled from pseudo-syllable and modeled with a Gaussian mixture model (GMM).Experiments are performed on free and telephone channel speech.The results show that the sub-word system and the rhythmic system are effective. |
| |
| Keywords: | language identification rhythm Gaussian mixture model (GMM) |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《上海大学学报(自然科学版)》浏览原始摘要信息 |
|
点击此处可从《上海大学学报(自然科学版)》下载全文 |
