Recognition method and system based on dual voice signal verification, terminal and medium

Abstract

The invention discloses a recognition method and system based on dual voice signal verification, a terminal and a medium, and relates to the technical field of network security, and the key points of the technical scheme are as follows: real-time voice data are preprocessed and then matched and analyzed with registered voice data in a registered database; if the similarity is smaller than a set threshold value, influence factor information is acquired through an information window, and corresponding trained voice characteristic correction parameters are called; performing correction processing on voice characteristics in the real-time voice data according to the voice characteristic correction parameter to obtain verification voice data; performing secondary matching verification on the verification voice data and the registered voice data; if the similarity is smaller than a set threshold value, randomly forming a non-voice verification mode by taking the similarity of the verification voice data as a random number; and performing final verification in a non-voice verification mode. According to the invention, the success rate of voice recognition verification can be effectively enhanced, and the verification passing rate after a third party obtains a non-voice verification mode is reduced.

Description

technical field [0001] The present invention relates to the technical field of network security, and more particularly, to an identification method, system, terminal and medium based on dual voice signal verification. Background technique [0002] With the continuous development of intelligent technology and network technology, the security of network information has always been the focus of attention. For the security of network information transmission, encryption algorithms or anti-interference technology are generally used to ensure the security of information transmission. The security of information in network nodes, such as smart device terminals, is generally granted to users by means of network security verification. On the one hand, the scope of use of shared terminal equipment can be managed to prevent misoperations; , which can effectively prevent the leakage of network information. [0003] For the purpose, the network verification of the smart device terminal ...

AI Technical Summary

Problems solved by technology

[0004] However, the above speech recognition verification method still has the following defects: on the one hand, it is affected by the interference of the verifier's pronunciation ability, which leads to further improvement in the success rate of speech recognition verification; on the other hand, there are various ways to pass the verification. After the third party understands the relevant information of any of the other verification methods, it can still complete the verification directly when the voice recognition verification fails, and after the data is updated in the registration database in the way of verification failure, it is easy to cause the original valid voice verification. The party and the verifier after eliminating the interference factors lose the possibility of successful speech recognition verification

Images