改进的多窗谱MFCC在说话人确认中的应用

摘要

Speech exists additive noise which is the main reason for reduced MFCC robustness. Then reduced MFCC robustness makes the speaker verification system identification rate decreased. To solve the problem, multitaper technology is introduced, which is a little effective in improving the noise robustness of MFCC. To get a better result, we propose a improved multitaper MFCC extraction algorithm which combines multitaper and spectral subtraction methods. Multitaper technology improve the robustness of MFCC, then spectral subtraction method enhance the speech and reduce the effect of noise. Simulation results show that when the test speech contains the additive noise, new algorithm could achieve better result in EER and minDCF which are the evaluation index of speaker verification system.%语音中存在加性噪声降低了MFCC参数的鲁棒性,使得说话人确认系统性能下降。多窗谱MFCC引入了多窗谱估计技术在增强 MFCC 特征的噪声鲁棒性上取得了一定效果,但改善的程度有限。为了使 MFCC 参数对噪声具有更强的鲁棒性,提出了一种改进的多窗谱 MFCC 提取算法。改进算法在多窗谱 MFCC 的基础上引入谱减思想,谱减法(Spectral Subtraction, SS)能够增强语音并降低噪音的干扰。因此,采用了Multitaper+SS组合的改进算法融合了两者的优势,具备了更好的性能。仿真结果表明,当测试语音中含有加性噪声时,与多窗谱 MFCC提取算法相比,采用改进的多窗谱 MFCC 的说话人确认系统性能在等错误率 EER 和最小检测代价函数值minDCF两项评测指标上都取得了更好的结果。