Active Speaker Localization

Active Speaker Localization (ASL) is the process of spatially locating an active speaker in an environment using audio, visual, or a combination of both modalities. Its aim is to accurately determine the position of the speaker to enhance the performance of multimodal interaction systems. ASL holds significant application value in areas such as conference systems, intelligent surveillance, and human-computer interaction, capable of improving the perceptual capabilities of systems and user experience.