arxiv
PublishedJuly 10, 2026 at 4:00 AM
—neutral
PS4: Proxy-Supervised Joint Training for Real Target Speaker Extraction
Publisher summary· verbatim
arXiv:2607.08111v1 Announce Type: cross Abstract: Training target speaker extraction (TSE) models for real conversational mixtures remains challenging because large-scale training corpora and clean target speech for supervision are unavailable. We present PS4, a proxy-supervised training framework f
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivCalibration-First Reward-Component Auditing for Reinforcement Learning Control in Smart Greenhouses9marxivOptimal Adaptive Market Making: A Theoretical Framework for High-Yield Liquidity Provision in Perpetual Futures Markets9marxivIn-Context Reinforcement Learning under Non-Stationarity: A Survey9marxivGRID: Grammar-Railed Decoding for Enterprise SQL Generation9mThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗