Anti-noise voiceprint recognition device with joint treatment of spectral subtraction and dynamic time warping algorithm

Abstract

The invention relates to a voiceprint recognition device, and particularly relates to an anti-noise voiceprint recognition device with joint treatment of spectral subtraction and dynamic time warping algorithm. The voiceprint recognition device comprises a microphone, a pre-amplification module, an analog-to-digital circuit (ADC), an endpoint detection module, a signal framing module, a spectral subtraction module, a first mel frequency cepstrum coefficient (MFCC) feature extraction module, a second MFCC feature extraction module, a third MFCC feature extraction module, a fourth MFCC feature extraction module, a current template, a user module, a first dynamic time warping (DTW) matching module, a second DTW matching module, a third DTW matching module, a score feedback module, an information compensation module and a result output module. Embedded voiceprint recognition based on isolated words is carried out by using figures from 0 to 9 as passwords, joint treatment is carried out by using signal domain and model domain of voice to prevent recognition performance reduction caused by information loss in the voice enhancing process and the voiceprint recognition performance under the noise background is improved. The system is convenient to implement and low in cost.

Description

technical field [0001] The invention relates to a voiceprint recognition device, in particular to an anti-noise voiceprint recognition device jointly processed by spectral subtraction and dynamic time warping algorithm. Background technique [0002] Voice Print Recognition (VPR) is also called speaker recognition, which is to identify who said a certain voice based on the characteristics of the speaker's voice. Voiceprint is a personality characteristic of a person, and it is difficult to find two people with exactly the same voiceprint. Therefore, voiceprint recognition is widely used in security, public security, military, banking, securities, personal identification and other fields. In isolated word recognition, the most effective and simplest method is to use Dynamic Time Warping algorithm (Dynamic Time Warping, referred to as DTW algorithm). The most notable advantages of this method are low complexity and high recognition rate. Fields such as speaker recognition have...

AI Technical Summary

Problems solved by technology

[0013] However, the improvement of the spectral subtraction method in the above work is aimed at restoring the waveform of the noisy speech signal and improving the signal-to-noise ratio. Two processes that are independent of each other, resulting in a lack of correlation between the improvement of signal-to-noise ratio and the improvement of voiceprint recognition performance

For example, the improved spectral subtraction algorithm can effectively improve the speech signal-to-noise ratio in the signal domain, but in the process of speech enhancement, because the matching degree of the back-end recognition model is not considered, it will cause the loss of useful speech information, that is, in the spectral subtraction process. The filtered "noise" actually contains a lot of useful speech signal information. In many cases, the improvement of the signal-to-noise ratio obtained by the spectral subtraction algorithm actually degrades the performance of voiceprint recognition in the back-end model domain.

Images