Binaural sound source localization based on weighted template matching

In robot binaural sound source localization (SSL), locating the direction of the sound source accurately in the shortest time is important. It refers to the algorithm complexity, but even more to the shortest duration of the required signal. A novel binaural SSL method based on feature and frequency...

Full description

Saved in:
Bibliographic Details
Published in:CAAI Transactions on Intelligence Technology Vol. 6; no. 2; pp. 214 - 223
Main Authors: Liu, Hong, Sun, Yongheng, Yang, Ge, Chen, Yang
Format: Journal Article
Language:English
Published: Beijing John Wiley & Sons, Inc 01.06.2021
Wiley
Subjects:
acoustic generators
acoustic signal processing
Algorithms
Correlation
Datasets
Ears & hearing
Fourier transforms
Frequencies
hearing
image matching
Localization
maximum likelihood estimation
Microphones
Neural networks
robots
Similarity
Sound localization
Sound sources
Sound waves
Template matching
Weighting
ISSN:2468-2322, 2468-6557, 2468-2322
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In robot binaural sound source localization (SSL), locating the direction of the sound source accurately in the shortest time is important. It refers to the algorithm complexity, but even more to the shortest duration of the required signal. A novel binaural SSL method based on feature and frequency weighting is proposed. More specifically, in the training stage, the direction‐related interaural cross‐correlation function(CCF) and interaural intensity difference(IID) in each frequency band are calculated under noiseless conditions, which are considered the templates. In the testing stage, first the cosine similarities between the CCF and IID of the test signal and templates are calculated in all features and frequency bands. Then, the direction likelihood can be obtained by weighting the similarities. Finally, the direction with maximum likelihood is specified as the direction of the sound source. Experiments were carried out on CIPIC dataset subject 003 with different noises in the noisex‐92 dataset and demonstrated that the method can accurately locate the sound source with a short signal duration.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2468-2322
2468-6557
2468-2322
DOI:10.1049/cit2.12009