Speaker Diarization With Lexical Information

2018/11/27 by Park, Tae Jin, Han, Kyu, Lane, Ian +1
#Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.1811.10761

Abstract

This work presents a novel approach to leverage lexical information for speaker diarization. We introduce a speaker diarization system that can directly integrate lexical as well as acoustic information into a speaker clustering process. Thus, we propose an adjacency matrix integration technique to integrate word level speaker turn probabilities with speaker embeddings in a comprehensive way. Our proposed method works without any reference transcript. Words, and word boundary information are provided by an ASR system. We show that our proposed method improves a baseline speaker diarization system solely based on speaker embeddings, achieving a meaningful improvement on the CALLHOME American English Speech dataset.

Related

• Improving Speaker Diarization using Semantic Information: Joint Pairwise Constraints Propagation
• Multimodal Speaker Segmentation and Diarization using Lexical and\n Acoustic Cues via Sequence to Sequence Neural Networks
• Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization
• Lexical Speaker Error Correction: Leveraging Language Models for Speaker Diarization Error Correction
• Content-Aware Speaker Embeddings for Speaker Diarisation