Speaker verification method and device

Abstract

The invention provides a speaker verification method and a speaker verification device. The speaker verification method comdprises the following steps: acquiring second voice; converting first voice and the second voice, which are acquired in advance, into corresponding first spectrogram and second spectrogram; conducting feature extraction on the first spectrogram and the second spectrogram by virtue of convolutional neural network so as to acquire corresponding first features and second features; conducting feature extraction on the first features and the second features by virtue of time delay neural network so as to acquire corresponding third features and fourth features; and verifying a speaker in accordance with the third features and the fourth features. According to the speaker verification method and the speaker verification device provided by the invention, in a mode of combining the convolutional neural network and the ime delay neural network, the first voice and the second voice undergo the feature extraction, and the third features and the fourth features, which are finally extracted, are compared, so that speaker verification is implemented; and the speaker verification method and the speaker verification device provided by the invention are simple in computation and strong in robustness, and an excellent recognition effect can be achieved.

Description

technical field [0001] The present invention relates to the field of speech recognition, and more specifically, to a speaker confirmation method and device. Background technique [0002] Speaker verification is a method of authenticating a speaker through vocal characteristics. When confirming the speaker, the user first reserves a voice, and then inputs the verification voice. By comparing the verification voice with the voice reserved by the system, it can be judged whether the user exists. [0003] At present, the speaker confirmation method is mainly based on the statistical model, and the speaker confirmation method with better performance is generally based on the i-vector model and the PLDA model. The i-vector model establishes the following linear model for the speech signal: [0004] X=Tw+v [0005] Among them, X is the MFCC feature of the speech signal, T is a low-rank matrix, w is the sentence vector, that is, i-vector, and v is Gaussian noise. The model is i...

AI Technical Summary

Problems solved by technology

[0009] In order to overcome the above-mentioned problems that require a large amount of data, a large amount of calculation, and poor robustness, or at least partially solve the above-mentioned problems, the present invention provides a method and device for speaker confirmation

Images