Voiceprint recognition payment information anti-counterfeiting method combined with spatial information

Abstract

The invention discloses a voiceprint recognition payment information anti-counterfeiting method combined with spatial information. The method comprises the following steps: S1, establishing a voice feature model representing the identity of the speaker, extracting the speaker features from the voice data by programming and establishing an MFCC model in the matlab environment by using the text-related data, firstly using the wavread function for read-in, then performing framing according to the 256 frame length and the 80 frame shift, then realizing high frequency emphasis by the sentence x=filter ([1-0.9375], 1, x) to filter the low frequency interference, especially the power frequency interference of 50Hz to 60Hz so as to enhance the frequency spectrum of the high frequency part which ismore useful for voice recognition, and then maintaining the short-term stability of the voice signal. Multiple verification can be performed to improve the payment security; besides, the random dynamic verification text is used, and the voice is obtained through artificial voice reading and then the obtained voice is verified to be compared with the voiceprints saved in the system so that the problem that the single voiceprint is liable to be embezzled and duplicated can be avoided and the security can be improved.

Description

technical field [0001] The invention relates to the technical field of voiceprint recognition, in particular to an anti-counterfeiting method for voiceprint recognition and payment information combined with spatial information. Background technique [0002] The so-called voiceprint is the sound wave spectrum that carries speech information displayed by electroacoustic instruments. The production of human language is a complex physiological and physical process between the language center of the human body and the vocal organs. The vocal organs used by people when speaking-tongue, teeth, larynx, lungs, and nasal cavities vary greatly from person to person in terms of size and shape. , so there are differences in the voiceprint maps of any two people. Each person's speech acoustic features are both relatively stable and variable, not absolute or immutable. This variation can come from physiology, pathology, psychology, simulation, camouflage, and is also related to environme...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the shortcomings of the existing payment methods, mostly static password verification, low payment security, and high equipment requirements for face verification, and propose a voiceprint recognition payment information anti-counterfeiting method combined with spatial information