audio-17
Active Speaker Localization
3260 papers • 126 benchmarks • 313 datasets
Active Speaker Localization (ASL) is the process of spatially localizing an active speaker (talker) in an environment using either audio, vision or both.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in active-speaker-localization-17
Trend
Dataset
Best Model
Actions
EasyCom
EasyCom
Libraries
iUse these libraries to find active-speaker-localization-17 models and implementations
Datasets
No datasets available.
Subtasks
No subtasks available.