Speech recognition method, device, equipment and computer storage medium

Abstract

The invention discloses a speech recognition method, a device, equipment and a computer-readable storage medium. The method comprises the following steps: extracting preselected feature vectors of real speech in a pre-established corpus; extracting preselected feature vectors of real speech in the pre-established corpus; extracting preselected feature vectors of real speech in the pre-establishedcorpus; extracting preselected feature vectors of real speech in the pre-established corpus; according to the preset speech synthesis algorithm and the text information corresponding to the real speech in the corpus, extracting the forged speech is synthesized and the preselected feature vector of the forged speech; training a true / false speech classifier by using a preselected feature vector of the real speech and a preselected feature vector of the forged speech; recognizing the speech to be detected by the trained true-false speech separator so as to judge whether the speech to be detectedis forged speech or not. The method, the device, equipment and the computer-readable storage medium provided by the invention can accurately and efficiently recognize the counterfeit speech in the actual scene and effectively prevent the pseudo sound attack.

Description

technical field [0001] The present invention relates to the technical field of voiceprint recognition, in particular to a voice recognition method, device, equipment and computer-readable storage medium. Background technique [0002] In recent years, voiceprint recognition has been used in various applications such as voiceprint payment, voiceprint lock, etc. The demand for anti-counterfeit voice attacks is increasing. [0003] By comparing the voiceprint features of the real voice and the fake voice, the requirements for identifying false voices are high, and the same vowel will be compared repeatedly, so a lot of labor costs will be spent. A single phoneme search cannot be directly used in the case handling of voiceprint identification, because the voiceprint identification of the case must have very professional and accurate comparison evidence. Therefore, in the prior art, the pseudo-sound is generally identified through text content and pronunciation rules, so as to ac...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method, device, equipment and computer-readable storage medium for speech recognition, which has solved the problem that the anti-counterfeit sound attack method in the prior art cannot effectively identify false sounds

Images