Mel Frequency Discrete Wavelet Coefficients for Kannada Speech Recognition using PCA
Mel Frequency Discrete Wavelet Coefficients for Kannada Speech Recognition using PCA
复制标题
使用 PCA 进行卡纳达语语音识别的梅尔频率离散小波系数
DOI：
--
复制
发表时间：
2010
期刊：
影响因子：
--
通讯作者：
S. Katti
中科院分区：
文献类型：
--
作者：
M. Anusuya;S. Katti
本文提出了一种基于离散小波变换（DWT）和主成分分析（PCA）的卡纳达语语音孤立词识别方法。首先，计算语音的DWT，然后计算MFCC系数。为此，将主成分分析过程应用于语音识别。本文还给出了与文献[12]中给出的结果的比较结果，其结果在识别精度方面是上级的。这种新的方法被应用到不同的小波族和结果进行了讨论。
In this paper, a new scheme for recognition of isolated words in kannada Language speech, based on the Discrete Wavelet Transform(DWT) and PCA has been proposed. First, the DWT of the speech is computed and then MFCC coefficients are calculated. For this, Principal Component Analysis procedure is applied for speech recognition. This paper also presents the comparative results with respect to the results given in [12] and the results are superior with respect to recognition accuracy. This novel method is applied to different wavelet families and the results have been discussed.