AUDIO SIGNAL SCORING METHOD AND APPARATUS, TERMINAL DEVICE AND COMPUTER STORAGE MEDIUM

摘要

Provided are an audio signal scoring method and apparatus, a terminal device and a computer storage medium. The method comprises: performing audio separation on an audio signal concerning a singer to obtain a first singer voice signal, the audio signal concerning the singer being an audio signal comprising an accompaniment and the voice of the singer (S101); performing noise suppression processing on the first singer voice signal, to obtain a second singer voice signal (S102); and acquiring a score of a target audio signal on the basis of a difference between the second singer voice signal and the target audio signal (S103). By performing noise suppression processing on a first singer voice signal separated from a signal concerning a singer, a second singer voice signal with less accompaniment remaining can be obtained, allowing a relative accurate score of a target audio signal.