Information geometry theory of high-dimension space and application for speaker independent continuous digit speech recognition
文献类型：期刊论文
| 作者 | Wang SJ (Wang Shoujue) ; Cao WM (Cao Wenming) ; Pan XX (Pan Xiaoxia) |
| 刊名 | chinese journal of electronics
 |
| 出版日期 | 2006 |
| 卷号 | 15期号:4a页码:768-784 |
| ISSN号 | 1022-4653 |
| 关键词 | high-dimension space high-dimension space covering theory continuous speech of speaker-independent TONE RECOGNITION NEURAL-NETWORKS LANGUAGE CHINESE |
| 通讯作者 | wang, sj, chinese acad sci, inst semicond, beijing 100083, peoples r china. |
| 中文摘要 | in the light of descriptive geometry and notions in set theory, this paper re-defines the basic elements in space such as curve and surface and so on, presents some fundamental notions with respect to the point cover based on the high-dimension space (hds) point covering theory, finally takes points from mapping part of speech signals to hds, so as to analyze distribution information of these speech points in hds, and various geometric covering objects for speech points and their relationship. besides, this paper also proposes a new algorithm for speaker independent continuous digit speech recognition based on the hds point dynamic searching theory without end-points detection and segmentation. first from the different digit syllables in real continuous digit speech, we establish the covering area in feature space for continuous speech. during recognition, we make use of the point covering dynamic searching theory in hds to do recognition, and then get the satisfying recognized results. at last, compared to hmm (hidden markov models)-based method, from the development trend of the comparing results, as sample amount increasing, the difference of recognition rate between two methods will decrease slowly, while sample amount approaching to be very large, two recognition rates all close to 100% little by little. as seen from the results, the recognition rate of hds point covering method is higher than that of in hmm (hidden markov models) based method, because, the point covering describes the morphological distribution for speech in hds, whereas hmm-based method is only a probability distribution, whose accuracy is certainly inferior to point covering. |
| 学科主题 | 人工智能 |
| 收录类别 | SCI |
| 语种 | 英语 |
| 公开日期 | 2010-04-11 |
| 源URL | [http://ir.semi.ac.cn/handle/172111/10280]  |
| 专题 | 半导体研究所_中国科学院半导体研究所（2009年前） |
| 推荐引用方式 GB/T 7714 | Wang SJ ,Cao WM ,Pan XX . Information geometry theory of high-dimension space and application for speaker independent continuous digit speech recognition[J]. chinese journal of electronics,2006,15(4a):768-784. |
| APA | Wang SJ ,Cao WM ,&Pan XX .(2006).Information geometry theory of high-dimension space and application for speaker independent continuous digit speech recognition.chinese journal of electronics,15(4a),768-784. |
| MLA | Wang SJ ,et al."Information geometry theory of high-dimension space and application for speaker independent continuous digit speech recognition".chinese journal of electronics 15.4a(2006):768-784. |
入库方式： OAI收割
来源：半导体研究所
浏览0
下载0
收藏0
其他版本
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。