Preprint
Sep 2026
Foreground Voice Activity Detection: Learning Speaker Selectivity from Supervision
Voice activity detection (VAD) fronts most voice-agent pipelines, yet production detectors treat all human speech, background talkers included, as valid activity; in crowded settings this floods recognition, stalls turn-taking, and triggers false barge-in. We formalize Foreground VAD (FVAD): a frame-synchronous, enroll...
Guang-Zhao Yang, Muhammad Huzaifah, Yu Pan et al.
· 0 citations