vix.ing · top · new · best · stats · spec

Hierarchical RNN with Static Sentence-Level Attention for Text-Based Speaker Change Detection

2017/03/22 by Meng Zhao, Lili Mou, Meng, Zhao +3
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech Recognition and Synthesis #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1703.07713

openalex publication_date 2017/03/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/02

Abstract

Speaker change detection (SCD) is an important task in dialog modeling. Our paper addresses the problem of text-based SCD, which differs from existing audio-based studies and is useful in various scenarios, for example, processing dialog transcripts where speaker identities are missing (e.g., OpenSubtitle), and enhancing audio SCD with textual information. We formulate text-based SCD as a matching problem of utterances before and after a certain decision point; we propose a hierarchical recurrent neural network (RNN) with static sentence-level attention. Experimental results show that neural networks consistently achieve better performance than feature-based approaches, and that our attention-based model significantly outperforms non-attention neural networks.

Citations

Related