Method and device for extracting mfcc features

Abstract

The invention provides an extraction method and device for mel frequency cepstrum coefficient (MFCC) characteristics. The extraction method comprises the steps of utilizing a high-frequency section Mel filter contained in a Mel filter group to perform filtration treatment on preprocessed audio signals so as to generate Mel region high-frequency components, performing discrete cosine transform on the Mel region high-frequency components so as to generate conversion characteristics of every Mel region high-frequency component, and obtaining the MFCC characteristics of the audio signals according to the conversion characteristics of every Mel region high-frequency component. Due to the fact that the high-frequency section Mel filter contained in the Mel filter group is utilized to perform filtration treatment on the preprocessed audio signals, the Mel region high-frequency components can be obtained, Mel region low-frequency components subjected to environmental influence easily can be removed, the MFCC characteristics extracted from test data and MFCC characteristics extracted from training data do not have large difference, and accordingly robustness of the MFCC characteristics is improved.

Description

【Technical field】 [0001] The present invention relates to audio feature extraction technology, in particular to a method and device for extracting Mel Frequency Cepstrum Coefficient (MFCC) features. 【Background technique】 [0002] With the development of communication technology, the terminal integrates more and more functions, so that the system function list of the terminal includes more and more corresponding applications, for example, applications installed in the computer, third-party smart phones Installed applications (Application, APP), etc. Some applications involve the feature extraction of Mel Frequency Cepstrum Coefficient (MFCC) of some audio signals, for example, content-based music identification (Music Identification) service, similar music recommendation (Music Recommendation) service and other audio recognition services. In the prior art, a Mel filter bank is used to filter the preprocessed audio signal; then, a discrete cosine transform (DiscreteCosine Tr...

AI Technical Summary

Problems solved by technology

[0003] However, since the training data is pure audio data without any interference, and the test data is audio data collected in a natural environment, there may be obvious distortion due to some reasons, such as the noise of the surrounding environment, the transmission system introduced channel distortion, etc., so that the test data may not completely match the training data. Therefore, there may be a large difference between the MFCC features extracted from the test data and the MFCC features extracted from the training data using the existing technology, so that the MFCC features less robust

Images