MFCC VOICE RECOGNITION METHOD, STORAGE MEDIUM, ELECTRONIC DEVICE, AND SYSTEM

摘要

The present invention relates to the field of voice recognition, and discloses an MFCC voice recognition method, a storage medium, an electronic device, and a system. The method comprises the steps of: preprocessing a voice signal requiring voice recognition to obtain an MFCC initial signal; calculating a low frequency, an intermediate frequency, and a high frequency of the MFCC initial signal; fusing the low, intermediate, and high frequencies of the MFCC initial signal to obtain an MFCC characteristic parameter; and performing dimension reduction on the MFCC characteristic parameter F to obtain a dimension-reduced MFCC characteristic parameter. The present invention significantly improves the recognition accuracy of an MFCC characteristic parameter in a noisy environment and in a high-frequency region, and further achieves the purpose of extracting the MFCC characteristic parameter from a voice signal in the noisy environment and in the high-frequency region, and thus is very suitable for promotion.