Denoising autoregressive predictive coding pretraining improves target-speaker voice activity detection in noise by roughly two percentage points, with FiLM conditioning performing best.
Audiovisual speaker indexing for web-tv automations,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Noise-Robust Target-Speaker Voice Activity Detection Through Self-Supervised Pretraining
Denoising autoregressive predictive coding pretraining improves target-speaker voice activity detection in noise by roughly two percentage points, with FiLM conditioning performing best.