Overview of the L3DAS23 Challenge on Audio-Visual Extended Reality
This challenge addresses the problem of improving 3D audio processing for Extended Reality applications by providing a new dataset and benchmarks, though it is incremental as it builds on previous L3DAS datasets.
The L3DAS23 Challenge introduced a new dataset with first-order Ambisonics recordings and images for 3D audio-visual tasks in Extended Reality, providing updated baseline models and participant results to advance research in 3D speech enhancement and sound event localization.
The primary goal of the L3DAS23 Signal Processing Grand Challenge at ICASSP 2023 is to promote and support collaborative research on machine learning for 3D audio signal processing, with a specific emphasis on 3D speech enhancement and 3D Sound Event Localization and Detection in Extended Reality applications. As part of our latest competition, we provide a brand-new dataset, which maintains the same general characteristics of the L3DAS21 and L3DAS22 datasets, but with first-order Ambisonics recordings from multiple reverberant simulated environments. Moreover, we start exploring an audio-visual scenario by providing images of these environments, as perceived by the different microphone positions and orientations. We also propose updated baseline models for both tasks that can now support audio-image couples as input and a supporting API to replicate our results. Finally, we present the results of the participants. Further details about the challenge are available at https://www.l3das.com/icassp2023.