| 基于汉语语音音节特点的N-Best改进算法 |
| |
| 引用本文： | 田斌,易克初,周战馨. 基于汉语语音音节特点的N-Best改进算法[J]. 西安电子科技大学学报(自然科学版), 1999, 0(1) |
| |
| 作者姓名： | 田斌 易克初 周战馨 |
| |
| 作者单位： | 西安电子科技大学综合业务网国家重点实验室，第二炮兵工程学院 |
| |
| 摘 要： | 连续语音识别中，由于各声学单元之间没有明显的间隔或声学标志，匹配和搜索算法成为影响系统实时性能的核心问题．基于汉语语音的特点，提出了一种改进的Ｎ－Ｂｅｓｔ搜索算法．该算法大大降低了传统Ｎ－Ｂｅｓｔ程序搜索空间而不至于失去最优解，有利于算法的实时实现．
|
| 关 键 词： | 汉语语音识别 N－Best算法 连续语音识别 搜索算法 |
A modified N-Best algorithm based on Chinese syllable features |
| |
| Tian Bin,Yi Kechu,Zhou Zhanxin. A modified N-Best algorithm based on Chinese syllable features[J]. Journal of Xidian University, 1999, 0(1) |
| |
| Authors: | Tian Bin Yi Kechu Zhou Zhanxin |
| |
| Abstract: | In continuous speech recognition, search strategy is of great importance in determining the practicability of a recognizer because there is no explicit interval or delimiter between acoustic units. This paper proposes a fast search matching algorithm based on the features of Chinese syllables for finding N Best hypotheses, which can greatly reduce the search space without loosing the optimal path, and remarkably improve the N Best search algorithm in the performance of implementation in real time. |
| |
| Keywords: | Chinese speech recognition N Best algorithm continuous speech recognition search algorithm |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
