Improved MFCC feature extraction by PCA-optimized filter-bank for speech recognition
Improved MFCC feature extraction by PCA-optimized filter-bank for speech recognition
复制标题
通过 PCA 优化滤波器组改进 MFCC 特征提取以进行语音识别
DOI：
10.1109/asru.2001.1034586
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
Lin
中科院分区：
文献类型：
--
作者：
Shang;Shih;J. Hung;Lin
虽然梅尔频率倒谱系数（MFCC）已被证明在大多数情况下表现得很好，一些有限的努力已经在优化滤波器组中的滤波器的形状在传统的MFCC方法。本文提出了一种新的特征提取方法，设计滤波器组中的滤波器的形状。在这种新方法中，滤波器组系数是数据驱动的，并通过对训练数据的FFT频谱应用主成分分析（PCA）来获得。实验结果表明，该方法在噪声环境下具有较强的鲁棒性，并与其他噪声处理技术有很好的互补性。
Although Mel-frequency cepstral coefficients (MFCC) have been proven to perform very well under most conditions, some limited efforts have been made in optimizing the shape of the filters in the filter-bank in the conventional MFCC approach. This paper presents a new feature extraction approach that designs the shapes of the filters in the filter-bank. In this new approach, the filter-bank coefficients are data-driven and obtained by applying principal component analysis (PCA) to the FFT spectrum of the training data. The experimental results show that this method is robust under noisy environment and is well additive with other noise-handling techniques.