Unsupervised Acoustic Scene Mapping Based on Acoustic Features and Dimensionality Reduction

arXiv:2301.00448v2 Announce Type: replace-cross
Abstract: Classical methods for acoustic scene mapping require the estimation of time difference of arrival (TDOA) between microphones. Unfortunately, TDOA estimation is very sensitive to reverberation and additive noise. We introduce an unsupervised data-driven approach that exploits the natural structure of the data. Our method builds upon local conformal autoencoders (LOCA) - an offline deep learning scheme for learning standardized data coordinates from measurements. Our experimental setup includes a microphone array that measures the transmitted sound …

abstract arxiv cs.lg cs.sd data data-driven difference dimensionality eess.as exploits features mapping natural noise reverberation type unsupervised