Multi-channel voiceprint signal synchronous acquisition system and method

Abstract

The invention provides a voiceprint signal acquisition system and method based on synchronous multiple channels. The voiceprint signal acquisition system comprises an analog microphone array, a conditioning circuit, an analog-to-digital conversion acquisition module and a field programmable logic gate array, the number of the analog microphone arrays is multiple, each analog microphone array is composed of multiple sets of positive and negative double microphones, and each set of positive and negative double microphones is sequentially connected with a conditioning circuit and an analog-to-digital conversion acquisition module. The analog microphone array comprises a first-direction high-frequency omnidirectional microphone and a second-direction low-frequency heart-shaped directional microphone, and sound receiving holes of the microphones in the two directions are arranged in opposite directions; the conditioning circuit comprises a signal attenuation circuit, a program control amplification circuit and a filter circuit, the embodiment provides a cyclic translation de-noising algorithm based on wavelet transform, the inherent defects of the wavelet transform in the aspects of expressing the direction characteristics of the edge of a signal image and the like are overcome, and the accuracy of de-noising is improved. According to the invention, synchronous multi-channel high-speed data acquisition and edge calculation are realized, and system data can be monitored in real time.

Description

technical field [0001] The disclosure belongs to the technical field of voiceprint acquisition, in particular to a multi-channel voiceprint signal synchronous acquisition system and method. Background technology [0002] With the continuous development of industrialization, more and more attention has been paid to the health detection of production equipment, especially the equipment failure rate in the initial failure period and loss failure period is generally high. Therefore, fault detection is of great significance for industrial production. Voiceprint recognition is a method commonly used in fault detection and has significant advantages in practical application. Structural damage detection based on sound signal has many advantages, such as high acquisition convenience, high accuracy, low acquisition cost, non-contact acquisition and high security. It is an inevitable trend in the future Internet era. Therefore, it is of great significance to collect and transmit voiceprint ...

AI Technical Summary

Problems solved by technology

[0005] 1. The quality of the sound source signal collected by the microphone is poor, and the low-frequency noise contained in it affects the analysis of the effective signal, which brings great difficulty to the subsequent denoising work. It needs to be collected in a room with a better sound field, such as a silent room, etc.;

[0006] 2. The traditional acquisition system has poor real-time acquisition of sound signals, and it is difficult to achieve multi-channel synchronous acquisition;

[0007] 3. The traditional acquisition system is difficult to achieve edge computing, which brings more data processing burden to the host computer;

[0008] 4. It is difficult to realize real-time remote monitoring of the system

Images