Singing evaluation method and system

Abstract

The invention discloses a singing evaluation method and system, and belongs to the technical field of voice signal processing. The singing evaluation method comprises the steps of acquiring recording data of a song sung by a user; sequentially intercepting a plurality of segments of recording data with a set length at different positions between a starting end point and a finishing end point of the recording data so as to acquire a plurality of data segments; calculating a pitch difference value between each of the data segments and standard audio data of the song one by one, and using the starting end point of the data segment with the minimum pitch difference value as a detection starting point; calculating a similarity score of the data segment starting from the detection starting point and the standard audio data of the song; and using the similarity score as an evaluation result. The singing evaluation method and system disclosed by the invention are simple in calculating process, accurate in scoring, and capable of meeting an application requirement of real-time scoring.

Description

technical field [0001] The invention relates to the technical field of voice signal processing, in particular to a singing evaluation method and system. Background technique [0002] In the karaoke singing evaluation system, in order to evaluate the user's singing level, the standard pitch of the song is usually preset to form a standard pitch curve about time. After obtaining the pitch curve of the recording data of the user's singing song, compare it with the standard pitch curve, and evaluate the user's singing level by calculating the area error between it and the standard pitch curve. The closer the curve is to the standard pitch curve (that is, the smaller the curve area error is), the higher the user's singing level is. [0003] In order to enhance the user experience, the singing evaluation system usually adopts a real-time scoring mode, so that users can obtain feedback results in real time during the singing process. In the real-time scoring mode, every time the ...

AI Technical Summary

Problems solved by technology

The time warping function obtained by calculating the Euclidean distance can solve the scoring error problem caused by the time mismatch between the user recording data and the standard pitch data to a certain extent, but due to the large amount of calculation and the complexity of the calculation process, it cannot meet the requirements. Application requirements for real-time scoring

Images