Researchers have developed an LLM-assisted system designed to correct speaker attribution errors in real-time during meetings. The system leverages automatic speech recognition (ASR) and diarization, then uses LLM-generated summaries to help users pinpoint and fix mistakes. It incorporates user feedback to update transcripts and enroll new speakers, with mechanisms to precisely identify intended corrections. Evaluations on the AMI headset test set showed significant reductions in DER and speaker substitution errors compared to a baseline system. AI
IMPACT This system could improve the accuracy and usability of meeting transcripts, making them more valuable for analysis and record-keeping.
RANK_REASON This is a research paper detailing a novel system for in-meeting speaker correction. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
