Multiple Source Location Estimation on a Dataset of Real Recordings in a Wireless Acoustic Sensor Network

Abstract

Recently, wireless acoustic sensor networks (WASNs) have received significant attention from the research community and a variety of methods have been proposed for numerous applications, such as location estimation and speech enhancement. The lack of publicly available datasets with signals recorded in WASNs, presents difficulties in obtaining consistent performance indicators across the different approaches. In this paper, we present and release a dataset of real recorded signals in an outdoor WASN comprised of four microphone arrays. Our dataset consists of several speakers recorded at various locations within the WASN and can be used for benchmarking purposes. We also present location estimation results using our real recorded dataset. Our results can serve as a baseline indicator of localization performance of single and multiple sources in a real environment.

Learning Multiple Sound Source 2D Localization

“…However, in multiple SSL where the number of source keypoints is unknown beforehand, such a mapping is not straightforward. Previously, Alexandridis et al [17] circumvent the issue by allowing one PK to be associated with more than one GK. However, this method only takes into account the closest PK to every GK and does not reflect mismatch in the number of PKs and GKs.…”