Music listening and recognizing method and system based on audio fingerprint and audio equipment

Abstract

The invention discloses a song listening and music recognizing method and system based on audio fingerprints and audio equipment. The method comprises the following steps: collecting song audios as template audios, obtaining spectrograms corresponding to the template audios, extracting peak points from the spectrograms as template audio fingerprints corresponding to the template audios, and constructing a template audio fingerprint database of the song audios according to the template audios and the template audio fingerprints; acquiring a recorded audio of the current music, acquiring a spectrogram corresponding to the recorded audio, and extracting a peak point from the spectrogram as a recorded audio fingerprint corresponding to the recorded audio; matching the recorded audio fingerprint with a template audio fingerprint in the template audio fingerprint database; and if the matching degree reaches a set threshold value, outputting the song audio corresponding to the recorded audio,so that the song can be automatically identified, the algorithm is efficient, the identification is accurate, and the portability is relatively high.

Description

technical field [0001] The invention relates to the technical field of voice communication, in particular to a method for listening to and recognizing music based on audio fingerprints and a system and audio equipment applying the method. Background technique [0002] The function of listening to songs and recognizing songs has been launched in many domestic music apps, such as NetEase Cloud Music and QQ Music. When users hear the audio they are interested in, they can use this function to identify the name of the song being played in the current environment. [0003] The realization of "listening to music" generally requires the following two elements: [0004] 1. Feature extraction for songs: Generally speaking, features that are highly robust and easy to distinguish exist in the frequency spectrum of audio files; from a musical point of view, the melody, rhythm, and rhythm of a song belong to such features; [0005] 2. Build a song library: The identification of songs sh...

AI Technical Summary

Problems solved by technology

[0006] However, the current recognition function of listening to songs has the problems of slow recognition speed and poor recognition effect, and what users hope to get is efficient and accurate results

Images