Title: An accuracy detection system of lyrics singing based on Gaussian mixture model

Authors: Jianshu Wang

Addresses: Chongqing Normal University College of Music, Chongqing 400000, China

Abstract: In order to solve the problems of low detection accuracy, long time consuming and high system resource occupancy in traditional lyrics accuracy detection system, a lyrics accuracy detection system based on Gaussian mixture model is designed. In the lyric data pre-processing module, through clustering the similarity of the lyric data. In the lyric audio data feature fusion module, the accuracy of the lyric singing is analysed. In the lyric singing accuracy detection module, with the help of Gaussian mixture model, the Gaussian distribution probability low density function of the lyric singing accuracy is determined to complete the lyric singing accuracy detection. The experimental results show that: the system designed in this paper has the highest accuracy of about 95%, the shortest detection time is about 3S, and the system has the lowest resource share of about 10%.

Keywords: Gaussian mixture model; GMM; lyrics singing; accuracy detection; audio data features; Gaussian distribution probability low density function.

DOI: 10.1504/IJICT.2023.132770

International Journal of Information and Communication Technology, 2023 Vol.23 No.2, pp.177 - 187

Received: 10 Jun 2021
Accepted: 22 Jul 2021
Published online: 09 Aug 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article