2 papers
eess.AS2024
Efficient Area-based and Speaker-Agnostic Source Separation
Martin Strauss, Okan Köpüklü
This paper introduces an area-based source separation method designed for virtual meeting scenarios. The aim is to preserve speech signals from an unspecified number of sources wit…
cs.CV2021
How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild
Okan Köpüklü, Maja Taseska, Gerhard Rigoll
Successful active speaker detection requires a three-stage pipeline: (i) audio-visual encoding for all speakers in the clip, (ii) inter-speaker relation modeling between a referenc…