Abstract
The ability to localize and track acoustic events is a fundamental prerequisite for equipping machines with the ability to be aware of and engage with humans in their surrounding environment. However, in realistic scenarios, audio signals are adversely affected by reverberation, noise, interference, and periods of speech inactivity. In dynamic scenarios, where the sources and microphone platforms may be moving, the signals are additionally affected by variations in the source-sensor geometries. In practice, approaches to sound source localization and tracking are often impeded by missing estimates of active sources, estimation errors, as well as false estimates. The aim of the LOCAlization and TrAcking (LOCATA) Challenge is an open-access framework for the objective evaluation and benchmarking of broad classes of algorithms for sound source localization and tracking. This article provides a review of relevant localization and tracking algorithms and, within the context of the existing literature, a detailed evaluation and dissemination of the LOCATA submissions. The evaluation highlights achievements in the field, open challenges, and identifies potential future directions.
Highlights
T HE ABILITY to localize and track acoustic events is a fundamental prerequisite for equipping machines with awareness of their surrounding environment
The azimuth error in (12a) between associated source-to-track pairs is averaged over all time stamps and all recordings
The results indicated that the number of microphones in an array, to some extent, can be traded off against the array aperture
Summary
T HE ABILITY to localize and track acoustic events is a fundamental prerequisite for equipping machines with awareness of their surrounding environment. Open-access datasets recorded in realistic scenarios and suitable for objective benchmarking are available only for scenarios involving static sources, such as loudspeakers, and static microphone array platforms To provide such data for a wide range of dynamic scenarios, and foster reproducible and comparable research in this area, the LOCAlization and TrAcking (LOCATA) challenge provides a novel framework for evaluation and benchmarking of sound source localization and tracking algorithms, entailing: 1) An open-access dataset [15] of recordings from four microphone arrays in static and dynamic scenarios, completely annotated with the ground-truth positions and orientations for all sources and sensors, hand-labelled voice activity information, and close-talking microphone signals as reference.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have