Choice of Mel Filter Bank in Computing MFCC of a Resampled Speech
This is an incremental improvement for speech and speaker recognition systems, addressing a specific technical issue in feature extraction.
The paper tackles the effect of resampling on MFCC features in speech recognition by deriving a relationship and proposing six methods to adjust the Mel filter bank, finding the best method through Pearson coefficient analysis to make resampled MFCCs closely match the original.
Mel Frequency Cepstral Coefficients (MFCCs) are the most popularly used speech features in most speech and speaker recognition applications. In this paper, we study the effect of resampling a speech signal on these speech features. We first derive a relationship between the MFCC param- eters of the resampled speech and the MFCC parameters of the original speech. We propose six methods of calculating the MFCC parameters of downsampled speech by transforming the Mel filter bank used to com- pute MFCC of the original speech. We then experimentally compute the MFCC parameters of the down sampled speech using the proposed meth- ods and compute the Pearson coefficient between the MFCC parameters of the downsampled speech and that of the original speech to identify the most effective choice of Mel-filter band that enables the computed MFCC of the resampled speech to be as close as possible to the original speech sample MFCC.