Method and device for classifying audio files

Abstract

The embodiment of the invention discloses a method and a device for classifying audio files. The method comprises the following steps of pre-classifying music, and obtaining a spectrogram of each type of music; for a target audio file to be classified, obtaining a spectrogram of the target audio file; according to the similarity of the spectrogram of the target audio file and the spectrogram of each type of music, determining the type of the target audio file. The method disclosed by the embodiment is used for classifying the audio files according to the spectrograms.

Description

technical field [0001] The invention relates to the field of audio technology, in particular to a method and device for classifying audio files. Background technique [0002] In the Internet multimedia era, people's demands for music are becoming more and more diverse. Music classification helps people to label music, such as labeling different emotions for different music genres, and it also facilitates users to better obtain music resources according to their interests. [0003] The traditional music classification method extracts features from the audio and then uses a classifier to classify. Audio features include: time-domain features, including short-term average energy, linear prediction coefficient, zero-crossing rate, and derivative features; frequency-domain features, including Mel coefficients, LPC cepstral coefficients, and entropy features; time-frequency features, including wavelet coefficients. In this process, effective audio feature extraction and selectio...

AI Technical Summary

Problems solved by technology

In this process, effective audio feature extraction and selection is a relatively complicated process.

Images