# Target-speaker ASR

2 related articles

Subscribe to updates

arXiv Nov 12, 2026
Meeting transcription stops reading only who is talking: structured speaker conditioning steadies target recognition under overlap
Meeting transcription must output text for a requested speaker, but four-state activity conditioning collapses different interferer counts and hand-over histories into one target condition. Structured speaker conditioning encodes each speaker's activity track separately, combines it with session-level acoustic identity, and controls the acoustic encoder through condition-dependent low-rank cross-channel modulation. On Qwen3-ASR-0.6B with oracle diarization, the complete method uses 1.46M conditioning parameters and achieves a 6.23% mean relative cpER reduction over four-state diagonal conditioning across four meeting test sets.
Meeting transcription must output text for a requested speaker, but four-state activity conditioning collapses different interferer counts and hand-over histories into one target condition. Structured speaker conditioning encodes each speaker's activity track separately, combines it with session-level acoustic identity, and controls the acoustic encoder through condition-dependent low-rank cross-channel modulation. On Qwen3-ASR-0.6B with oracle diarization, the complete method uses 1.46M conditioning parameters and achieves a 6.23% mean relative cpER reduction over four-state diagonal conditioning across four meeting test sets.
Structured Speaker Conditioning Target-speaker ASR Conditional Low-Rank Modulation Speaker Diarization Qwen3
arXiv Nov 7, 2026
Multi-talker transcription stops decoding each speaker alone: Pandemonium lets speakers see each other and reaches 14.7 average cpWER on meeting benchmarks
Target-speaker recognition for multi-talker meetings previously decoded each speaker independently and was confined to 30-second windows. Pandemonium moves the diarization conditioning onto the longform Parakeet backbone, which decodes a whole conversation in one pass, and adds cross-speaker attention plus a mask refiner so that the speakers of one conversation become visible to each other inside the encoder. Trained on synthetic, pseudo-labeled and real data, it reaches state-of-the-art results across several meeting benchmarks, with an average cpWER of 19.2 under predicted diarization.
Target-speaker recognition for multi-talker meetings previously decoded each speaker independently and was confined to 30-second windows. Pandemonium moves the diarization conditioning onto the longform Parakeet backbone, which decodes a whole conversation in one pass, and adds cross-speaker attention plus a mask refiner so that the speakers of one conversation become visible to each other inside the encoder. Trained on synthetic, pseudo-labeled and real data, it reaches state-of-the-art results across several meeting benchmarks, with an average cpWER of 19.2 under predicted diarization.
Johns Hopkins University Brno University of Technology Nvidia (United States)Carnegie Mellon University
Alexander Polok（First author）
Pandemonium DiCoP Cross-speaker attention Target-speaker ASR Pseudo-labeling

You’re all caught up

Meeting transcription stops reading only who is talking: structured speaker conditioning steadies target recognition under overlap

Multi-talker transcription stops decoding each speaker alone: Pandemonium lets speakers see each other and reaches 14.7 average cpWER on meeting benchmarks