Voiceprint verification method, apparatus, device, and storage medium

Abstract

The invention relates to the field of biological recognition. Specifically, a pre-trained phoneme model is adopted to realize the voice processing. The invention discloses a voiceprint verification method, an apparatus, a device and a storage medium. The method comprises the steps: carrying out the text conversion of voice information, so as to obtain corresponding text information; according to apreset phoneme model, obtaining a phoneme set corresponding to the text information, wherein the phoneme set comprises initial consonants and final consonants corresponding to each character in the text information; calculating an initial consonant coverage rate of the phoneme set according to an initial consonant table and each initial consonant in the phoneme set; calculating the vowel coveragerate of the phoneme set according to a vowel table and each vowel in the phoneme set; and performing voiceprint verification on the voice information according to the initial consonant coverage rateand the final coverage rate to generate a verification result. Therefore, the voice information with high voice feature integrity of the user is found out. An important reference is provided for voiceprint identity verification.

Description

technical field [0001] The present application relates to the field of biometric identification, and in particular to a voiceprint verification method, device, equipment and storage medium. Background technique [0002] In a speech-independent speaker recognition system, the voice registered by the voiceprint usually allows the user to speak at will, and the speaking time exceeds a certain threshold. Through this voice, the speaker's pronunciation features are extracted, and a machine learning method is used to extract a series of feature vectors. Generally, for this segment of speech, the signal-to-noise ratio is required to be above a certain threshold. However, it is difficult for the speech whose signal-to-noise ratio meets the requirements to completely reflect the speech characteristics of the user. For example, if the user keeps repeating the same word during the period of speaking, although the duration and signal-to-noise ratio of this speech can meet the standard...

AI Technical Summary

Problems solved by technology

However, it is difficult to fully reflect the user's voice characteristics if the signal-to-noise ratio meets the requirements.

For example, if the user keeps repeating the same word during the period of speaking, although the duration and signal-to-noise ratio of this speech can meet the standard, the pronunciation characteristics reflected are very limited

Images