Audio identifying method, device and equipment and storage medium

Abstract

The embodiment of the invention discloses an audio identifying method, device and equipment and a storage medium. The method includes the steps of extracting audio fingerprints of a to-be-identified audio to serve as standard fingerprints and calculating the similarity between the standard fingerprints and audio fingerprints in a preset fingerprint base; according to the similarity between the standard fingerprints and the audio fingerprints in the preset fingerprint base, screening out a candidate fingerprint set from the fingerprint base; selecting reference fingerprints from the candidate fingerprint set and obtaining unisonant fingerprints of the reference fingerprints; selecting a target audio corresponding to the to-be-identified audio from the reference fingerprints and the audio corresponding to the unisonant fingerprints. The method improves the refining degree of audio identification, and the more accurate target audio is obtained through identification.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to an audio recognition method, device, equipment and storage medium. Background technique [0002] The function of listening to songs and identifying songs provides a very convenient search method for music lovers to search for their favorite music. Users only need to record music in the environment, or hum a song fragment, and input the application software to identify which song it is . The current recognition of songs by listening to songs is mainly to search in a massive music library according to the characteristic information of the input songs, and select the songs most similar to the input songs. [0003] During the research and practice of the existing technology, the inventors of the present invention found that the audio clips uploaded by users may correspond to multiple versions of audio, and the current music platform audio recognition process is rough ...

AI Technical Summary

Problems solved by technology

[0003] During the research and practice of the existing technology, the inventors of the present invention found that the audio clips uploaded by users may correspond to multiple versions of audio, and the current music platform audio recognition process is rough and does not take into account the differences between different versions. Due to the differences between the audio clips, the songs selected by the music platform based on the clips provided by the user may not be the real source of the audio clips and not what the user really wants.

It can be seen that the current audio recognition accuracy is poor

Images