| 基于仿生模式识别理论的高阶神经网络说话人识别方法 |
| |
| 引用本文： | 武妍,金明曦,王守觉.基于仿生模式识别理论的高阶神经网络说话人识别方法[J].计算机工程,2006,32(12):184-186. |
| |
| 作者姓名： | 武妍 金明曦 王守觉 |
| |
| 作者单位： | 1. 同济大学计算机科学与工程系,上海,200092
2. 中国科学院半导体研究所神经网络实验室,北京,100083 |
| |
| 摘 要： | 根据一种全新的仿生模式识别理论，提出了采用神经网络实现并完成说话人识别的新方法。该方法利用高阶神经网络形成的复杂包络在特征空间中构造不同说话人的覆盖区域达到识别目的。相关实验证明，这种新的说话人识别方法只要通过少量样本的训练即可达到比传统方法更高的识别率。
|
| 关 键 词： | 仿生模式识别 说话人识别 高阶神经网络 |
| 文章编号： | 1000-3428（2006）12-0184-03 |
| 收稿时间： | 09 6 2005 12:00AM |
| 修稿时间： | 2005-09-06 |
Speaker Recognition Method with High-order Neural Network Based on Biomimetics Pattern Recognition |
| |
| WU Yan,JIN Mingxi,WANG Shoujue.Speaker Recognition Method with High-order Neural Network Based on Biomimetics Pattern Recognition[J].Computer Engineering,2006,32(12):184-186. |
| |
| Authors: | WU Yan JIN Mingxi WANG Shoujue |
| |
| Affiliation: | 1. Department of Computer Science and Engineering, Tongji University, Shanghai 200092; 2. Lab of Artificial Neural Networks, Institute of Semiconductors, CAS, Beijing 100083 |
| |
| Abstract: | According to a brand-new biomimetics pattern recognition theory, a new method realized with neural network to fulfill speaker recognition is presented, which takes advantage of the complicated coverage formed by high-order neural network to construct area of different speakers in feature space to recognize. Relevant experiments show that, this new method can achieve higher recognition rate than traditional methods by training of small-number samples. |
| |
| Keywords: | Biomimetics pattern recognition Speaker recognition High-order neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
