Deep learning-based single point sound source localization in spherical microphone arrays

초록

In this contribution, we present a sound source localization in spherical microphone arrays via a deep learning framework. While the spherical microphone arrays can be utilized to produce omnidirectional beams, it is widely known that the conventional spherical harmonics beamforming (SHB) has a limit in terms of its spatial resolution. To accomplish the sound source localization with preciseness, we propose a convolutional neural network (CNN)-based source localization model as a way of a data-driven approach. We mainly develop a multi-kernel operation and a residual skip connection-based deep neural network to improve the source localization performance. Both quantitative and qualitative results are demonstrated to evaluate the powerfulness of the proposed data-driven source localization model. © INTER-NOISE 2021. All right reserved.