Voiceprint identity authentication device and authentication optimization method and system

Abstract

The invention discloses an authentication optimization method of a voiceprint identity authentication device. The authentication optimization method comprises the steps that the Mel-frequency cepstral coefficients corresponding to registration voice signals are extracted and preset number binding is performed on the Mel-frequency cepstral coefficients; the Mel-frequency cepstral coefficients act as an input layer and the bound numbers act as an output layer to perform differentiated deep belief network training and acquire the parameter space; the Mel-frequency cepstral coefficients are inputted to the differentiated deep belief network to acquire the hidden layer output to act as the feature vectors; all the feature vectors act as the input to construct a Gaussian mixture model; and the corresponding Mel-frequency cepstral coefficient of any registration voice signal is inputted to the differentiated deep belief network to acquire multiple hidden layer outputs, and the hidden layer outputs of which the degree of distinction is higher than the preset threshold are selected to act as the training data to update the Gaussian mixture model. The following spontaneously changed voice signal of the registrant acts as the raining data to update the Gaussian mixture model so as to be more adaptive to the present sound production state of the registrant, and the recognition rate can be guaranteed.

Description

technical field [0001] The invention relates to the technical field of signal processing, in particular to an authentication optimization method of a voiceprint identity authentication device. The present invention also relates to an authentication optimization system of a voiceprint identity authentication device and a voiceprint identity authentication device comprising the authentication optimization system. Background technique [0002] As burglary incidents occur frequently, how to upgrade home door locks to ensure indoor security is a new challenge that people have to face. [0003] At present, the traditional home door locks on the market are basically unlocked by keys and passwords. Due to the characteristics of easy loss, easy duplication, and weak characteristics of keys, similarly, password unlocking has the disadvantages of easy forgetting and leaking of passwords, which is easy to cause While wasting resources, it brings security risks to users. In addition, e...

AI Technical Summary

Problems solved by technology

In addition, when the recognized speech context of the non-target speaker is close to the recognized speech context of the target speaker, the probability of false acceptance will be greatly increased when the speech is used for the target speaker test.

Images