| 基于自适应同源方差控制的法庭自动说话人识别 |
| |
| 引用本文： | 王华朋,杨军,吴鸣,许勇.基于自适应同源方差控制的法庭自动说话人识别[J].应用科学学报,2014,32(6):582-587. |
| |
| 作者姓名： | 王华朋 杨军 吴鸣 许勇 |
| |
| 作者单位： | 1. 中国科学院噪声与振动重点实验室，北京100190
2. 中国刑事警察学院刑事科学技术系，沈阳110854 |
| |
| 基金项目： | 国家自然科学基金(No.11004217，No.11074279)资助 |
| |
| 摘 要： | 提出了自动说话人识别系统得分到法庭证据强度量化值似然比的转换方法. 为了更准确地评估嫌疑人的
统计模型，提出了自适应同源方差控制算法，该算法能自适应地融合来自参考人群和嫌疑人的同源语音得分模型
信息，降低了对嫌疑人数据量大小的需求. 与基本识别系统相比的测试结果表明，使用该算法的识别系统不但具有
更优良的识别性能和可靠性，而且提高了语音证据对判别结论的支持强度.
|
| 关 键 词： | 法庭自动说话人识别 背景模型-高斯混合模型 似然比 自适应同源方差控制 |
| 收稿时间： | 2012-07-24 |
| 修稿时间： | 2014-09-10 |
Automatic Speaker Recognition for Courtroom Based on Adaptive Within-Source-Variance Control |
| |
| WANG Hua-peng,YANG Jun,WU Ming,XU Yong.Automatic Speaker Recognition for Courtroom Based on Adaptive Within-Source-Variance Control[J].Journal of Applied Sciences,2014,32(6):582-587. |
| |
| Authors: | WANG Hua-peng YANG Jun WU Ming XU Yong |
| |
| Affiliation: | 1. Key Laboratory of Noise and Vibration Research, Institute of Acoustics, Chinese Academy of Sciences,;
Beijing 100190, China;
2. Department of Forensic Science and Technology, China Criminal Police University,;
Shenyang 110854, China |
| |
| Abstract: | This paper proposes a method to transfer the scores generated from a speaker recognition system to
likelihood ratios (LR) for evaluating the strength of forensic voice evidence. A robust LR estimation algorithm
using adaptive within-source-variance control is developed to accurately estimate a model of the suspect. The
algorithm adaptively combines information of reference speakers and that of the suspect to model the withinsource-
variability of the suspect. Compared with a baseline recognition system, the system using the proposed
algorithm has better discrimination capability and reliability, and the magnitude of evidence strength is also
improved. |
| |
| Keywords: | forensic automatic speaker recognition background-model-Gaussian mixture model (BM-GMM) likelihood ratio adaptive within-source variance control |
|
| 点击此处可从《应用科学学报》浏览原始摘要信息 |
|
点击此处可从《应用科学学报》下载全文 |
