计算机技术与发展2016，Vol.26Issue(3)：18-22,5.DOI:10.3969/j.issn.1673-629X.2016.03.005
基于压缩感知的鲁棒性说话人识别参数研究
Research on Robust Speaker Recognition Parameters Based on Compressed Sensing
摘要
Abstract
Speaker recognition under Nyquist sampling has got a large amount of data in order to ensure a high recognition rate,resulting in a waste of sampling resources,and compressive sensing theory can solve this problem. Based on compressed sensing theory,it makes use of ladder observation matrix projection in this paper. When the compression ratio is 1:2,the system ensures the recognition rate,so that the sample data is reduced to half. Under noisy environment,spectral subtraction is applied in compressed sensing and feature extrac-tion,and feature parameters are extracted directly from estimated clean speech power spectrum CS-SSMFCC (Compressed Sensing Spec-tral Subtraction Mel Frequency Cepstral Coefficient) . Experimental results show that compared with the traditional identification parame-ter MFCC (Mel frequency Cepstral Coefficient),CS-SSMFCC based on spectral subtraction under CS framework can effectively im-prove the robustness of the system,with good anti-noise performance.关键词
压缩感知/谱减法/特征参数/鲁棒性Key words
compressed sensing/spectral subtraction/feature parameters/robustness分类
信息技术与安全科学引用本文复制引用
于云,周伟栋..基于压缩感知的鲁棒性说话人识别参数研究[J].计算机技术与发展,2016,26(3):18-22,5.基金项目
国家自然科学基金资助项目(61271335) （61271335）
国家“973”重点基础研究发展计划项目(2011CB302303) （2011CB302303）
江苏省自然科学基金项目(BK20140891) （BK20140891）
