An Indoor Sound Source Localization Method Based on Ensemble Learning

An integrated learning and sound source localization technology, applied in positioning, speech analysis, instruments, etc., can solve problems such as poor noise robustness, and achieve the effect of improving performance

Active Publication Date: 2019-09-13
NANJING UNIV OF POSTS & TELECOMM
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to solve the problem of poor robustness in harsh indoor environments with strong noise and reverberation

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
  • An Indoor Sound Source Localization Method Based on Ensemble Learning
  • An Indoor Sound Source Localization Method Based on Ensemble Learning
  • An Indoor Sound Source Localization Method Based on Ensemble Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The invention will be described in further detail below in conjunction with the accompanying drawings. The working principle of the present invention is to convert the sound source signal data into a feature data set by using the generalized cross-correlation function of the signal as the position feature, and then use integrated learning technology (Bagging (bagning), AdaBoost (adaptive promotion), etc.) to The feature data is used for training and positioning testing, and the final integrated learning classifier can identify the sound source location well, overcoming the serious performance loss of traditional sound source localization algorithms in harsh environments.

[0036] Based on above-mentioned principle, the technical scheme that the present invention takes mainly comprises the following steps:

[0037] Step 1: Set the training position of the sound source l i (i=1, 2...n) (unit: angle), use several microphone arrays to record the reverberation signal X from...

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 an integrated-learning-based indoor sound source positioning method and especially relates to features used by the sound source positioning method. Sound source signal data are converted into a feature data set by using a phase transformation generalized cross correlation function of a signal as a position feature; training and positioning testing are carried out on the feature data by using integrated learning technologies like bagging and AdaBoost; and then an integrated learning classifier is obtained and is capable of identifying a sound source position. Therefore, a defect that the performance losses are heavy in a severe environment according to the traditional sound source positioning algorithm can be overcome. Compared with the traditional positioning algorithm, the method has the following advantage: the robust sound source positioning performance can be obtained in a severe environment with high noises and reverberation in an indoor environment.

Description

technical field [0001] The invention belongs to the field of radio wave reflection or reradiation positioning or presence detection, and relates to an indoor sound source localization method based on integrated learning in a reverberation and noise interference environment, in particular to the features used in the sound source localization identification method . Background technique [0002] Sound source localization technology based on microphone array is a research hotspot at home and abroad in recent years. Its main principle is: collect the sound source signal through a microphone array with a certain geometric topology, process and analyze the voice signal through array signal processing technology, so as to determine the position of the sound source. [0003] At present, sound source localization technology based on microphone arrays has been widely used in many fields, such as video conferencing, sound detection, speech enhancement, speech recognition, speaker reco...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G10L21/0216G10L21/028G10L25/06G01S5/18
Inventor 万新旺杨悦顾晓瑜王吉
Owner NANJING UNIV OF POSTS & TELECOMM
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap