PATSE is a DOA-guided target speaker extraction system that produces speaker-attributed streams for diarization-free ASR in multi-party conversations.
GPU-accelerated guided source separation for meeting transcription,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Position-Aware Target Speaker Extraction for Long-Form Multi-Party Conversations: A Diarization-Free Framework for ASR
PATSE is a DOA-guided target speaker extraction system that produces speaker-attributed streams for diarization-free ASR in multi-party conversations.