Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Multi-sound-source tracking method for suppressing main sound source

A technology of multiple sound sources and main sound sources, applied in the field of multi-sound source tracking, can solve the problems of difficulty in tracking sound sources, loss and other problems

Active Publication Date: 2020-06-05
JIUJIANG VOCATIONAL & TECHN COLLEGE
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Even if the sound source distance increases again, it is difficult for the traditional tracking algorithm to track the weaker sound source, thus losing the target

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-sound-source tracking method for suppressing main sound source
  • Multi-sound-source tracking method for suppressing main sound source
  • Multi-sound-source tracking method for suppressing main sound source

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0063] The simulated room size is 4m×4m×2.7m, such as figure 1 , figure 2 and image 3 As shown, 8 microphones are installed on the walls around the room, and their heights are all 1.464m. The semicircle in the figure is the track of the sound source, the sound source moves in the direction indicated by the arrow, and its height is the same as the microphone. The sound source signals are two male voices with a duration of about 3.6s from the TIMIT database, and the sampling frequency is f s = 8kHz. The received signal of the microphone is generated by the image method, and a Gaussian white noise signal is added. Signal-to-noise ratio SNR=20dB, reverberation time T 60 = 0.132s. Frame length L=512 points, no overlap between frames, add Hanning window, the specific steps are as follows:

[0064] S1. Establish a two-dimensional rectangular coordinate system, determine the coordinates of each array element in the microphone array, divide the sound source signal received by ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a multi-sound-source tracking method for suppressing a main sound source. The multi-sound-source tracking method comprises the following steps: framing and windowing a voice sound source signal received by a microphone array; generating an initial particle group according to the initial state of the sound source; predicting a new particle state according to the state equation, and calculating a particle state observation value; judging a main source according to the positioning function value at the sound source position estimation position at the previous moment; calculating the distance between the weaker sound source particles and the main source, and constructing an attenuation coefficient according to the distance; multiplying the state observation value of theweaker sound source particles close to the main source by an attenuation coefficient to reduce the value of the weaker sound source particles; constructing a pseudo-likelihood function of each soundsource according to the positioning function and the attenuation coefficient, and calculating the particle weight of each sound source at the current moment according to the pseudo-likelihood function; normalizing the particle weight of each sound source, and estimating the position of each sound source at the current moment according to the particle weight and the particle state. According to theinvention, tracking of the two sound sources can be kept when the two sound sources are close to each other or sound source tracks are crossed, and the method can be widely applied to the fields of robot hearing, audio monitoring and the like.

Description

technical field [0001] The invention relates to the technical field of multi-sound source tracking based on a microphone array, in particular to a multi-sound source tracking method for suppressing a main sound source. Background technique [0002] Speech sound source localization and tracking technology based on microphone array has a very wide range of applications in digital hearing aids, robot hearing, intelligent monitoring and other fields. Early voice sound source localization and tracking technologies were mainly aimed at a single sound source, such as video conferencing, vehicle hands-free voice communication and other applications. After years of research, the localization and tracking algorithm of a single sound source has been able to achieve high accuracy. In recent years, with the expansion of the application field of sound source tracking technology, in many cases, the problem of multi-sound source localization and tracking needs to be considered. [0003] T...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G01S5/22
CPCG01S5/22
Inventor 蔡卫平黄印君刘瑞娟
Owner JIUJIANG VOCATIONAL & TECHN COLLEGE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products