| 基于二级搜索模型的有声出版物语音分割算法 |
| |
| 引用本文： | 张俊星,刘宇.基于二级搜索模型的有声出版物语音分割算法[J].吉林大学学报(工学版),2009(Z2). |
| |
| 作者姓名： | 张俊星 刘宇 |
| |
| 作者单位： | 大连民族学院机电信息工程学院;吉林大学辊锻工艺研究所; |
| |
| 基金项目： | 国家自然科学基金项目(60573124) |
| |
| 摘 要： | 提出了一种二级搜索模型,该模型首先利用最小音节步长搜索算法进行语音段检测,然后采用二分搜索算法确定语音段的精确位置。理论分析及实际运行结果表明,与传统的基于能量的端点检测算法相比,其搜索效率能够提高70%以上。该算法对语音环境有较高的要求,可用于有声出版物语音自动分割,以及具有良好信噪比系统的语音端点检测。
|
| 关 键 词： | 信息处理技术 语音分割 基于音节的搜索算法 二分搜索算法 有声出版物 |
Talking publications speech automatic segmentation algorithm based on two levels search model |
| |
| ZHANG Jun-xing,YU Liu.Talking publications speech automatic segmentation algorithm based on two levels search model[J].Journal of Jilin University:Eng and Technol Ed,2009(Z2). |
| |
| Authors: | ZHANG Jun-xing YU Liu |
| |
| Affiliation: | 1.Dept of Electromechanical Engineering;Dalian Nationalities University;Dalian 116600;China;2.Roll Forging Research Institute of Jilin University;Jilin University;Changchun 130022;China |
| |
| Abstract: | The two levels search model is put forward,the minimum syllable step search algorithm is adopted for speech detection in this model,and then the binary search algorithm is used to determine the exact position of speech segmentation.The theoretical analysis and practical operation results show that the searching efficiency can improve 70% than the traditional endpoint detection algorithm.This algorithm require good recording environment,it can be used for talking publications speech automatic segmentation an... |
| |
| Keywords: | information processing technology speech segmentation search algorithm based on minimum syllable binary search algorithm talking publications |
| 本文献已被 CNKI 等数据库收录！ |
