文章基本信息

标题：Dynamically localizing multiple speakers based on the time-frequency domain
本地全文：下载
作者：Hodaya Hammer ; Shlomo E. Chazan ; Jacob Goldberger 等
期刊名称：EURASIP Journal on Audio, Speech, and Music Processing
印刷版ISSN：1687-4714
电子版ISSN：1687-4722
出版年度：2021
卷号：2021
期号：1
页码：1
DOI：10.1186/s13636-021-00203-w
出版社：Hindawi Publishing Corporation
摘要：In this study, we present a deep neural network-based online multi-speaker localization algorithm based on a multi-microphone array. Following the W-disjoint orthogonality principle in the spectral domain, time-frequency (TF) bin is dominated by a single speaker and hence by a single direction of arrival (DOA). A fully convolutional network is trained with instantaneous spatial features to estimate the DOA for each TF bin. The high-resolution classification enables the network to accurately and simultaneously localize and track multiple speakers, both static and dynamic. Elaborated experimental study using simulated and real-life recordings in static and dynamic scenarios demonstrates that the proposed algorithm significantly outperforms both classic and recent deep-learning-based algorithms. Finally, as a byproduct, we further show that the proposed method is also capable of separating moving speakers by the application of the obtained TF masks.
关键词：DOA ; UNET ; Tracking