ELECTRONIC DEVICE, VOICEPRINT-BASED IDENTITY VERIFICATION METHOD AND SYSTEM, AND STORAGE MEDIUM

摘要

An electronic device, a voiceprint-based identity verification method and system, and a storage medium. The method comprises: upon receipt of voice data of a target user, the identity of which is to be verified, invoking a predetermined convolutional neural network (CNN) model to perform framing and sampling on the voice data, to obtain voice sampling data (S1); using a preset filter to process the voice sampling data to extract a preset type of voiceprint feature, and constructing a voiceprint feature vector corresponding to the voice data on the basis of the preset type of voiceprint feature (S2); inputting the voiceprint feature vector into a pre-trained background channel model, to construct a current voiceprint discrimination vector of the voice data (S3); calculating a spatial distance between the current voiceprint discrimination vector and a pre-stored standard voiceprint discrimination vector of the target user, performing identity verification on the user on the basis of the spatial distance, and generating a verification result (S4). The method can improve the accuracy and efficiency of identity verification.