Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Long-distance sound source positioning method and system based on microphone array

A microphone array, sound source localization technology, applied in the direction or offset system, positioning, radio wave measurement system and other directions, can solve the problem of insufficient accuracy of the positioning algorithm, to suppress background noise and reflected echo, improve the accuracy , the effect of increasing robustness

Pending Publication Date: 2021-02-23
西安合谱声学科技有限公司
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method and system for collecting and locating a remote sound source based on a microphone array, so as to solve the problem of insufficient accuracy of the positioning algorithm in the prior art

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
  • Long-distance sound source positioning method and system based on microphone array
  • Long-distance sound source positioning method and system based on microphone array
  • Long-distance sound source positioning method and system based on microphone array

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] At first the technical vocabulary that appears in the present invention is explained:

[0042] GMM-UBM model: Gaussian mixture model, the model adopts the mode of supervised learning, has better effect for the sample that target sound source data amount is few, in the present invention this model is the well-trained model and is used for carrying out target sound source and noise Classification. The model training process is as follows:

[0043] (1) Application scene analysis; determine some basic properties of the target sound source, such as: loudness, frequency, etc.; determine the noise category of interference; such as: wind, footsteps, etc.;

[0044] (2) Collect data; According to the voice data collected in (1), the distribution is required to be as complete as possible;

[0045] (3) Data cleaning; this step includes the screening, identification and structure design of the data; including the labeling of the sample, obtaining the target sound source signal lab...

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 belongs to the technical field of sound pickup, and discloses a long-distance sound source positioning method and system based on a microphone array. The method comprises the following steps: 1, acquiring multiple paths of noisy signals, and preprocessing the multiple paths of noisy signals to obtain multiple paths of to-be-detected sound signals; 2, judging the current frame of anyone of the multiple paths of to-be-detected sound signals, if the signal-to-noise ratio of the current frame meets a first threshold value and the energy of the current frame meets a second thresholdvalue, obtaining the current frames of all the paths of to-be-detected sound signals, and executing the step 3; otherwise, returning to execute the step 2; 3, classifying the previous frames of all paths of to-be-detected sound signals to obtain the current frames of multiple paths of target sound source signals; 4, performing cross-correlation calculation on the multiple paths of target sound source signals to obtain a plurality of cross-power spectrums; and 5, obtaining the maximum value of the peak value in the cross-power spectrum, and performing angle backstepping according to the time delay corresponding to the maximum value of the peak value to obtain the direction information of the target sound source signal.

Description

technical field [0001] The invention belongs to the technical field of sound pickup, and in particular relates to a method and system for remote sound source localization based on a microphone array. Background technique [0002] Sound is an important information to perceive the world and an important way to interact with the external environment. According to different sounds, the location information of the sound source can be judged, and a specific meaning can be obtained. In some specific scenarios, the machine needs to accurately determine a specific sound and be able to locate the positional relationship between the sound source and the device. The traditional single microphone input is difficult to meet this application, therefore, the sound source localization based on the microphone array has been developed rapidly. [0003] A microphone array (Microphone Array, MA) mainly includes three structures: a one-dimensional line array, a one-dimensional area array and a ...

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): G01S5/20G01S3/802
CPCG01S5/20G01S3/802
Inventor 黄绍锋向阳靳冠军刘芳
Owner 西安合谱声学科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products