| Robust Voice Command Understanding and Error Tolerance Algorithm Based on Word Graph Expansion |
| |
| 引用本文： | 陈俊燕,李涓子,王作英. Robust Voice Command Understanding and Error Tolerance Algorithm Based on Word Graph Expansion[J]. 清华大学学报, 2003, 8(2) |
| |
| 作者姓名： | 陈俊燕 李涓子 王作英 |
| |
| 作者单位： | Department of Electronic Engineering，Tsinghua University，Beijing 100084，China，Department of Electronic Engineering，Tsinghua University，Beijing 100084，China，Department of Electronic Engineering，Tsinghua University，Beijing 100084，China |
| |
| 基金项目： | Supported by the National High-Technology Development Program of China(No.863-306-ZD03-02-01) |
| |
| 摘 要： | A novel word graph expansion algorithm for voice command understanding is presented as the basis of a more accurate and robust voice command system. Tests show that the algorithm has much better performance than the generally-adopted N-best algorithm while maintaining high computational efficiency. Also the error tolerance method used to improve the robustness of the voice command understanding module further decreases the understanding error rate (UER) to 16. 6% with the computational efficiency almost unchanged compared to the case without error tolerance.
|
Robust Voice Command Understanding and Error Tolerance Algorithm Based on Word Graph Expansion |
| |
| CHEN Junyan,LI Juanzi,WANG Zuoying. Robust Voice Command Understanding and Error Tolerance Algorithm Based on Word Graph Expansion[J]. Tsinghua Science and Technology, 2003, 8(2) |
| |
| Authors: | CHEN Junyan LI Juanzi WANG Zuoying |
| |
| Affiliation: | CHEN Junyan,LI Juanzi,WANG ZuoyingDepartment of Electronic Engineering,Tsinghua University,Beijing 100084,China |
| |
| Abstract: | A novel word graph expansion algorithm for voice command understanding is presented as the basis of a more accurate and robust voice command system. Tests show that the algorithm has much better performance than the generally-adopted N-best algorithm while maintaining high computational efficiency. Also the error tolerance method used to improve the robustness of the voice command understanding module further decreases the understanding error rate (UER) to 16. 6% with the computational efficiency almost unchanged compared to the case without error tolerance. |
| |
| Keywords: | voice command N-best paths understanding word graph expansion (WGE) top-down chart parsing error tolerance |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
