基于LPC和MFCC得分融合的说话人辨认

Speaker Identification Based on Score Combination of LPC and MFCC

实验室环境下,说话人识别研究已经取得很大进展,但是在实际生活中,说话人识别系统的性能受到环境噪声、健康状况等因素的影响很大。日常生活中,感冒是不可避免的。而感冒往往会诱发鼻腔的炎症,改变鼻腔的容积和形状,引起说话人声音的改变,导致说话人识别性能下降。文中研究测试者感冒时说话人识别系统的性能。为了有效利用不同特征参数得分的互补性,针对基于GMM模型的说话人辨认系统,提出了将特征LPC和MFCC分别应用于该系统,并将二者的得分归一化后进行融合计算。实验结果表明,对正常语音来说,与LPC特征系统相比,该方法能够有效提升辨认性能;对感冒语音来说,当高斯成分为16时,较之LPC特征系统,该方法提升辨认性能12.5%左右,较之MFCC特征系统,该方法也能提升8.5%左右的辨认性能。

At present,speaker recognition technology has made great progress in clean voice. But in daily life,there are various factors,such as environmental noise and healthy condition,impacting recognition rate of speaker recognition system. The cold tends to induce the nasal cavity ＇s inflammation,and changes the volume and shape of the nasal cavity and then changes the vocal characteristics of the speaker. In order to effectively use the complementarity of scores from different feature parameter,the performance＇s change of speaker identification system was studied when the speaker gets the cold. So the method was proposed using linear prediction coefficient and M EL cepstrum coefficient to train the speaker model respectively,and then score normalization method is used to process scores from two feature systems. Finally,two outputs were weighted. The experimental results showthat for normal speech,this method can improve the identification performance; for cold speech,the method improves the identification performance by 12. 5% when the number of Gaussian components equals to sixteen compared with the system taking M FCC as feature,by 8. 5% to the LPC system.