Speaker-Reasoner is an end-to-end speech LLM that iteratively analyzes audio structure, predicts temporal boundaries, and jointly models speaker identity, gender, timestamps, and transcription using a speaker-aware cache for long audio.
Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Transcribing and understanding multi-speaker conversations requires speech recognition, speaker attribution, and timestamp localization. While speech LLMs excel at single-speaker tasks, multi-speaker scenarios remain challenging due to overlapping speech, backchannels, rapid turn-taking, and context window constraints. We propose Speaker-Reasoner, an end-to-end Speech LLM with agentic multi-turn temporal reasoning. Instead of single-pass inference, the model iteratively analyzes global audio structure, autonomously predicts temporal boundaries, and performs fine-grained segment analysis, jointly modeling speaker identity, gender, timestamps, and transcription. A speaker-aware cache further extends processing to audio exceeding the training context window. Trained with a three-stage progressive strategy, Speaker-Reasoner achieves consistent improvements over strong baselines on AliMeeting and AISHELL-4 datasets, particularly in handling overlapping speech and complex turn-taking.
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
SoulX-Transcriber is a unified LLM framework for end-to-end multi-speaker transcription using two-stage training (speaker-aware pre-training then supervised fine-tuning) that reports strong results on AliMeeting, AISHELL-4, and AMI.
citing papers explorer
-
Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR
Speaker-Reasoner is an end-to-end speech LLM that iteratively analyzes audio structure, predicts temporal boundaries, and jointly models speaker identity, gender, timestamps, and transcription using a speaker-aware cache for long audio.
-
SoulX-Transcriber: A Robust End-to-End Framework for Multi-Speaker Speech Transcription
SoulX-Transcriber is a unified LLM framework for end-to-end multi-speaker transcription using two-stage training (speaker-aware pre-training then supervised fine-tuning) that reports strong results on AliMeeting, AISHELL-4, and AMI.