Large language models (LLMs) have shown great promise for capturing contextual information in natural language processing tasks. We propose a novel approach to speaker diarization that incorporates the prowess of LLMs to exploit contextual cues in human dialogues. Our method builds upon an acoustic-based speaker diarization system by adding lexical information from an LLM in the inference stage. We model the multi-modal decoding process probabilistically and perform joint acoustic and lexical beam search to incorporate cues from both modalities: audio and text. Our experiments demonstrate that infusing lexical knowledge from the LLM into an acoustics-only diarization system improves overall speaker-attributed word error rate (SA-WER). The experimental results show that LLMs can provide complementary information to acoustic models for the speaker diarization task via proposed beam search decoding approach showing up to 39.8% relative delta-SA-WER improvement from the baseline system. Thus, we substantiate that the proposed technique is able to exploit contextual information that is inaccessible to acoustics-only systems which is represented by speaker embeddings. In addition, these findings point to the potential of using LLMs to improve speaker diarization and other speech processing tasks by capturing semantic and contextual cues.

翻译：大型语言模型（LLMs）在自然语言处理任务中展现出强大的上下文信息捕获能力。本文提出一种创新的说话人日志方法，通过融合LLMs的推理能力来挖掘人类对话中的上下文线索。该方法在基于声学特征的说话人日志系统基础上，于推理阶段引入词法信息。我们采用概率化建模多模态解码过程，通过联合声学与词法束搜索整合音频与文本双模态线索。实验表明，将LLMs的词法知识注入纯声学日志系统后，整体说话人属性词错误率（SA-WER）显著下降。基于所提束搜索解码方法，LLMs可为声学模型提供互补信息，使系统相对基线实现最高39.8%的δ-SA-WER改进。由此证实，该技术能够有效利用声学系统无法获取的上下文信息——这种信息由说话人嵌入表征。此外，该成果揭示了通过捕获语义与上下文线索，LLMs在提升说话人日志及其他语音处理任务性能方面的巨大潜力。