VOICE SIGNAL PROCESSING METHOD AND APPARATUS, AND ELECTRONIC DEVICE AND STORAGE MEDIUM

摘要

Disclosed are a voice signal processing method and apparatus, and an electronic device and a storage medium. The method comprises: acquiring a voice feature parameter of a voice signal to be processed, wherein the voice feature parameter comprises an initial spectrum of the voice signal to be processed (S110); on the basis of the voice feature parameter, obtaining a first set number of sub-band spectrum envelopes by means of prediction (S120), wherein the first set number is smaller than the number of initial spectrum coefficients included in the initial spectrum, and one sub-band spectrum envelope corresponds to a second set number of initial spectrum coefficients; adjusting the initial spectrum on the basis of the predicted sub-band spectrum envelopes to obtain an adjusted spectrum (S130); and on the basis of the adjusted spectrum, obtaining an enhanced voice signal corresponding to the voice signal to be processed (S140).