Structure constrained distributions matching using quadratic programming and its application to pronunciation evaluation
文献类型：会议论文
| 作者 | Yu Qiao; Masayuki Suzuki; Nobuaki Minematsu; Keikichi Hirose |
| 出版日期 | 2011 |
| 会议名称 | 1st Asian Conference on Pattern Recognition (ACPR) |
| 会议地点 | Beijing, PEOPLES R CHINA |
| 英文摘要 | We proposed a structural representation of speech that is robust to speaker difference due to its transformation-invariant property in previous works, where we compared two speech structures by calculating the distance between two structural vectors, each composed of the lengths of a structure's edges. However, this distance can not yield matching scores directly related to individual events (nodes) of the two structures. In spite of comparing structural vectors directly, this paper takes structures as constraints for optimal pattern matching. We derive the formulas of objective functions and constraint functions for optimization. Under assumptions of Gaussian and shared covariance matrices, we show that this optimal problem can be reduced to a quadratically constrained quadraticprogramming problem. To relieve the too strong invariance problem, we use a subspace decomposition method and perform the optimization in each subspace. We evaluate the proposed method on a task to assess the goodness of students' English pronunciation. Experimental results show that the proposed method achieves higher correlations with teachers' manuals cores than compared methods. |
| 收录类别 | EI |
| 语种 | 英语 |
| 源URL | [http://ir.siat.ac.cn:8080/handle/172644/3262]  |
| 专题 | 深圳先进技术研究院_集成所 |
| 作者单位 | 2011 |
| 推荐引用方式 GB/T 7714 | Yu Qiao,Masayuki Suzuki,Nobuaki Minematsu,et al. Structure constrained distributions matching using quadratic programming and its application to pronunciation evaluation[C]. 见:1st Asian Conference on Pattern Recognition (ACPR). Beijing, PEOPLES R CHINA. |
入库方式： OAI收割
来源：深圳先进技术研究院
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。