Spatial feature learning for robust binaural sound source localization using a composite feature vector

Xiang Wu, Dumidu S. Talagala, Wen Zhang, Thushara D. Abhayapala

科研成果: 书/报告/会议事项章节会议稿件同行评审

7 引用 (Scopus)

摘要

The performance of binaural speech source localization systems can be significantly impacted by an imperfect selection of spatial localization cues, due to the limited bandwidth of speech, and the effects of noise. In order to mitigate these impacts, this paper presents a novel method that combines a deterministic localization approach with a spatial feature learning process. Here, we (i) obtain a composite feature vector derived from analysing the mutual information between different spatial cues and (ii) estimate the optimum feature combination that minimizes the angular localization error in three dimensional space. The performance of the proposed mutual information based feature learning approach is evaluated for a range of speech inputs and noise conditions. We also demonstrate that the proposed approach improves the localization accuracy and its robustness, with respect to traditional localization algorithms, especially in the relatively low signal-to-noise ratio localization scenarios.

源语言英语
主期刊名2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
6320-6324
页数5
ISBN(电子版)9781479999880
DOI
出版状态已出版 - 18 5月 2016
已对外发布
活动41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, 中国
期限: 20 3月 201625 3月 2016

出版系列

姓名ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2016-May
ISSN(印刷版)1520-6149

会议

会议41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
国家/地区中国
Shanghai
时期20/03/1625/03/16

指纹

探究 'Spatial feature learning for robust binaural sound source localization using a composite feature vector' 的科研主题。它们共同构成独一无二的指纹。

引用此