| HMM非特定人连续语音识别的嵌入式实现 |
| |
| 引用本文： | 杜利民,谢凌云,刘斌.HMM非特定人连续语音识别的嵌入式实现[J].电子与信息学报,2005,27(1):60-63. |
| |
| 作者姓名： | 杜利民 谢凌云 刘斌 |
| |
| 作者单位： | 中国科学院声学研究所语音交互技术实验室,北京,100080 |
| |
| 摘 要： | 嵌入式系统正逐渐成为语音识别实际应用的首选平台。该文在嵌入式平台上研究HMM连续语音识别的计算复杂度要素,提出特征系数屏蔽方法和综合剪枝相结合的瘦身计算方法,降低计算复杂度并保持识别率。该方法在嵌入式平台上研究的实验数据表明,HMM连续语音识别瘦身系统与基线系统相比,计算时间从基线系统的100％降低到27.91％,识别率仅从基线系统的89.65％下降到89.41％。
|
| 关 键 词： | 嵌入式系统 语音识别 搜索算法 特征屏蔽 |
| 文章编号： | 1009-5896(2005)01-0060-04 |
| 收稿时间： | 2003-8-4 |
| 修稿时间： | 2003年8月4日 |
Embedded Implementation of HMM Speaker-Independent Continuous Speech Recognition System |
| |
| Du Li-min,Xie Ling-yun,Liu Bin.Embedded Implementation of HMM Speaker-Independent Continuous Speech Recognition System[J].Journal of Electronics & Information Technology,2005,27(1):60-63. |
| |
| Authors: | Du Li-min Xie Ling-yun Liu Bin |
| |
| Institution: | Lab for Speech Interaction Technology Institute of Acoustics Chinese Academy of Sciences Beijing 100080 China |
| |
| Abstract: | The embedded systems are gradually becoming the first choice of platforms which should be used for real-time speech recognition system. This paper discusses the computation complexity factors of HMM-based continuous speech recognition for embedded system. An optimized way integrating feature masking and pruning is presented to reduce the computation complexity and keep the recognition accuracy. The experiments for embedded system show that, comparing with the base-line system, the computation time is reduced from 100% to 27.91%, and the recognition accuracy is degraded only from 89.65% to 89.41%. |
| |
| Keywords: | Embedded system Speech recognition Search algorithm Feature masking |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《电子与信息学报》浏览原始摘要信息 |
| 点击此处可从《电子与信息学报》下载免费的PDF全文 |
