Skip to content
conftrace_

audio-visual speaker extraction

2 papers

Explore in graph

Also known as

AVSE

Co-occurring keywords · papers mentioning both

neural network (1) decoupled learning (1) pose-invariant model (1) speaker extraction (1) visual cue (1) model explainability (1) speaker identity (1) neural network optimization (1) face recognition (1) audio-visual learning (1)

Papers

PIAVE: A Pose-Invariant Audio-Visual Speaker Extraction Network Interspeech 2023 Rethinking the Visual Cues in Audio-Visual Speaker Extraction Interspeech 2023