Low-Variance Multitaper MFCC Features: A Case Study in Robust Speaker Verification
Low-Variance Multitaper MFCC Features: A Case Study in Robust Speaker Verification
复制标题
DOI：
10.1109/tasl.2012.2191960
复制
发表时间：
2012-09-01
影响因子：
--
通讯作者：
Li, Haizhou
中科院分区：
文献类型：
--
作者：
Kinnunen, Tomi;Saeidi, Rahim;Li, Haizhou
在语音和音频应用中，通常使用加窗离散傅立叶变换(DFT)计算的梅尔倒谱系数(MFCC)来表示短期信号频谱。加窗减少了频谱泄漏，但频谱估计的方差仍然很高。加窗DFT的一个很好的扩展是所谓的多锥化方法，它使用多个时间域窗口(锥化)和频域平均。在语音处理中，尽管多层结构产生低方差特征，但它们几乎没有受到关注。在本文中，我们提出了具有实用价值的MFCC提取的多锥度方法。首先，我们在TIMIT语料库上使用自回归过程模拟对MFCC偏差和方差进行了详细的统计分析。对于NIST 2002和2008 SRE语料库上的说话人确认实验，我们考虑了三种基于高斯混合模型的分类器：通用背景模型(GMM-UBM)、支持向量机(GMM-SVM)和联合因子分析(GMM-JFA)。在NIST 2008中，在面试-面试条件下，多篇论文使MinDCF比基线窗口DFT提高了20.4%(GMM-SVM)和13.7%(GMM-JFA)。GMM-JFA系统在电话数据上进一步减少了18.7%的MinDCF。由于这些改进和通常非关键的参数选择，多锥MFCC是取代传统MFCC的一个可行的候选方案。
In speech and audio applications, short-term signal spectrum is often represented using mel-frequency cepstral coefficients (MFCCs) computed from a windowed discrete Fourier transform (DFT). Windowing reduces spectral leakage but variance of the spectrum estimate remains high. An elegant extension to windowed DFT is the so-called multitaper method which uses multiple time-domain windows (tapers) with frequency-domain averaging. Multitapers have received little attention in speech processing even though they produce low-variance features. In this paper, we propose the multitaper method for MFCC extraction with a practical focus. We provide, first, detailed statistical analysis of MFCC bias and variance using autoregressive process simulations on the TIMIT corpus. For speaker verification experiments on the NIST 2002 and 2008 SRE corpora, we consider three Gaussian mixture model based classifiers with universal background model (GMM-UBM), support vector machine (GMM-SVM) and joint factor analysis (GMM-JFA). Multitapers improve MinDCF over the baseline windowed DFT by relative 20.4% (GMM-SVM) and 13.7% (GMM-JFA) on the interview-interview condition in NIST 2008. The GMM-JFA system further reduces MinDCF by 18.7% on the telephone data. With these improvements and generally noncritical parameter selection, multitaper MFCCs are a viable candidate for replacing the conventional MFCCs.