A song performance evaluation method and system

Abstract

The invention discloses a singing evaluation method and system, wherein the method comprises the following steps: S1. comparing the first audio frequency fingerprint of an original song with the second audio frequency fingerprint of an accompanying music, and marking the time interval with difference between the first audio frequency fingerprint and the second audio frequency fingerprint as a first difference area; S2. marking the start point of the first difference area as a first time point; S3. comparing the third audio frequency fingerprint of singing song with the second audio frequency fingerprint of the accompanying music, and marking the time interval with difference between the third audio frequency fingerprint and the second audio frequency fingerprint as a second difference area; S4. marking the start point of the second difference area as a second time point; S5. comparing the first time point with the second time point, and if the first time point is not equal to the second time point, the singing score of the singer is subtracted. By adopting the method, whether the singer sings too early or too late can be judged, and scoring of the singer is more objective and active.

Description

technical field [0001] The invention relates to the field of audio data processing, in particular to a song singing evaluation method and system. Background technique [0002] Singing scoring is a technology that provides real-time feedback on the user's personal singing. It can evaluate the singer's singing accuracy. Using the singing scoring system to provide singing scoring function can bring users a good experience and has a high entertainment. [0003] Due to the considerable instability of the sound, it is difficult to accurately evaluate it directly with a single acoustic model. The more common scoring methods for K songs are as follows: 1. Starting from the time domain waveform, the audio signal of the singer and the original singing signal that comes with the machine Sampling, and then compare the size of each sampling point, if they are consistent, the score is high, otherwise the score is low; 2. From the perspective of energy, the audio signal of the singer and ...

AI Technical Summary

Problems solved by technology

[0004] The mastery of the beat is a very important skill in song singing. The phenomenon of snapping or missing a beat has a greater impact on the singing effect of a song. It is impossible to clearly evaluate whether the singer has snapped or missed shots.

For songs with lyric files, you can determine the segment that the singer needs to sing through the time points marked in the lyric file, so as to determine whether the singer has rushed or missed shots; for songs without lyric files, you need to first determine The singer needs to sing the segment to determine whether the singer has snapped or missed shots. The existing technology is unable to evaluate whether there is a rush or missed shot when the singer sings a song without a lyrics file.

Images