Digital signal processor (DSP) implementation system for two-channel convolution mixed voice signal blind source separation algorithm

Abstract

The invention provides a digital signal processor (DSP) implementation system for a two-channel convolution mixed voice signal blind source separation algorithm. The system comprises an embedded processor platform, a microphone access circuit, a power circuit and a signal pre-amplification circuit, wherein the embedded processor platform is used for finishing analogue / digital (A / D) conversion, D / A conversion and analogue signal output; the microphone access circuit comprises two single-channel microphones for acquiring voice signals and a two-channel microphone acquisition circuit; two-channel voice signals acquired by the two single-channel microphones are taken as the left and right channel signal input of a line in audio interface; the signal pre-amplification circuit effectively amplifies the signals of the microphones until gain required by the line in audio interface is achieved. A plurality of functions of microphone acquisition, pre-amplification, voice blind source separation, voice play and storage and the like of the two-channel voice signals of two speakers are realized, and the actually acquired mixed voices of the two speakers can be effectively separated under both an offline condition and an online condition.

Description

technical field [0001] The invention relates to a DSP implementation system for a blind separation algorithm of two-channel convolution mixed voice signals, belonging to the technical field of voice signal processing. Background technique [0002] Blind signal separation technology is a technology that can effectively estimate the source signal through signal processing algorithms only based on the observation signal obtained by the sensor when the source signal and transmission channel are unknown or have little prior knowledge. Due to the characteristics of the speech signal itself, speech blind separation has become a difficult and hot spot in the field of blind speech separation. It is usually used as the front-end processing of speech signal processing such as speaker positioning, speech enhancement and speech recognition, so it has great potential in practical applications. and broad prospects. [0003] Since the problem of blind separation of speech signals was propo...

AI Technical Summary

Problems solved by technology

[0004] At the same time, due to the complexity of the convolutional mixture model itself, the computational complexity of blind separation is much greater than that of the instantaneous mixture model. Most of the current algorithms are simulated and tested in the MATLAB environment of a PC with a high configuration. However, due to PC is a general-purpose device with high power consumption and poor specificity. At the same time, the PC is large in size and poor in portability. It does not conform to the trend of today's technological products towards intelligence and miniaturization.

Images