×
Jun 7, 2024 · Here, we investigate the use of large language models (LLMs) for diarization correction as a post-processing step.
Sep 17, 2024 · Abstract. Speaker diarization is necessary for interpreting conversations transcribed using automated speech recognition (ASR) tools.
Sep 10, 2024 · Our results demonstrate a maximum accuracy of 95.66%. Furthermore, the most notable improvement achieved through data augmentation was 4.67%.
Sep 16, 2024 · This paper introduces a novel approach for improving the accuracy of speaker diarization systems using large language models.
In this paper, we show how a fine-tuned large language model (LLM) we developed can dramatically improve speaker labeling accuracy in transcripts. We are ...
"LLM-based speaker diarization correction: A generalizable approach," in Submitted to IEEE/ACM TASLP, 2024. [Paper]; "AG-LSEC: Audio Grounded Lexical Speaker ...
Speaker diarization is necessary for interpreting conversations transcribed using automated speech recognition (ASR) tools. Despite significant developments ...
In this paper, we introduce DiarizationLM, a framework to leverage large language models (LLM) to post-process the outputs from a speaker diarization system.
Fine-tuned large language models can significantly improve speaker diarization accuracy in conversational transcripts as a post-processing step, ...
People also ask
LLM-based speaker diarization correction: A generalizable approach ... The ability of the models to improve diarization accuracy in a holdout dataset from the ...