arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.08421eess.AScs.AIcs.CLcs.LGcs.SD
收藏

SEAL:使用声学条件化大语言模型的说话人错误校正

SEAL: Speaker Error Correction using Acoustic-conditioned Large Language Models

Ohio State University(俄亥俄州立大学);AWS AI Labs(亚马逊云科技人工智能实验室)

Anurag Kumar, Rohit Paturi, Amber Afshan, Sundararajan Srinivasan

AI总结:

针对传统说话人日志系统易产生说话人错误的问题,提出基于声学条件化大语言模型的SEAL方法,结合约束解码减少幻觉,在多个数据集上实现24%-43%的说话人错误率下降。

摘要:

说话人日志(Speaker Diarization,SD)是现代端到端自动语音识别(ASR)流水线的关键组成部分。传统SD系统通常基于音频且独立于ASR运行,常会引入说话人错误,尤其是在说话人转换和重叠语音阶段。近期,包括经微调的大语言模型(LLM)在内的语言模型,已被证明可利用转录输出中的词汇上下文,作为第二阶段说话人错误校正器发挥有效作用。本研究提出一种新颖的声学条件化方法,将来自声学日志器的更细粒度信息提供给LLM。研究还表明,一种更简单的约束解码策略可减少LLM的幻觉问题,同时避免复杂的后处理。在Fisher、Callhome和RT03-CTS数据集上,与第一阶段声学SD相比,该方法将说话人错误率显著降低了24%-43%。

英文摘要:

Speaker Diarization (SD) is a crucial component of modern end-to-end ASR pipelines. Traditional SD systems, which are typically audio-based and operate independently of ASR, often introduce speaker errors, particularly during speaker transitions and overlapping speech. Recently, language models including fine-tuned large language models (LLMs) have shown to be effective as a second-pass speaker error corrector by leveraging lexical context in the transcribed output. In this work, we introduce a novel acoustic conditioning approach to provide more fine-grained information from the acoustic diarizer to the LLM. We also show that a simpler constrained decoding strategy reduces LLM hallucinations, while avoiding complicated post-processing. Our approach significantly reduces the speaker error rates by 24-43% across Fisher, Callhome, and RT03-CTS datasets, compared to the first-pass Acoustic SD.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑