Full-Sphere Binaural Sound Source Localization Using Multi-task Neural Network

Yichen Yang, Jingwei Xi, Wen Zhang, Lijun Zhang

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 accuracy of binaural sound source localization is faced with the challenge of localizing azimuth and elevation simultaneously in noisy and reverberant environments. In this work, a full-sphere binaural sound source localization system is proposed using convolutional neural network and multi-task neural network connected to learn the localization features. The log-magnitudes and interaural phase difference (IPD) of binaural signals are used as inputs to a two-branch convolutional neural network, from which interaural and monaural cues are extracted and combined. Then, the full-sphere localization is formulated as two subtasks of estimating azimuth and elevation separately using multi-task neural network. To reduce reverberation effects, the interaural coherence based pre-processing is used to select the direct-path dominated time-frequency bins for localization. The proposed system is evaluated at a variety of noise and reverberation conditions, in comparison with two baseline systems. The results indicate that the proposed system achieves better localization performance, especially for elevation estimation, at low SNR and strong reverberation conditions.

源语言英语
主期刊名2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
432-436
页数5
ISBN(电子版)9789881476883
出版状态已出版 - 7 12月 2020
活动2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Virtual, Auckland, 新西兰
期限: 7 12月 202010 12月 2020

出版系列

姓名2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020 - Proceedings

会议

会议2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2020
国家/地区新西兰
Virtual, Auckland
时期7/12/2010/12/20

指纹

探究 'Full-Sphere Binaural Sound Source Localization Using Multi-task Neural Network' 的科研主题。它们共同构成独一无二的指纹。

引用此