Identifying Speakers in Dialogue Transcripts: A Text-based Approach Using Pretrained Language Models

TL;DR

This paper presents a new large-scale dataset and transformer-based models for text-based speaker identification in dialogue transcripts, significantly improving accuracy and setting new benchmarks.

Contribution

It introduces a novel large-scale dataset from MediaSum and develops transformer models tailored for speaker identification, addressing gaps in existing research.

Findings

Achieved 80.3% precision in speaker identification

Developed models leveraging contextual dialogue cues

Provided publicly available dataset and code

Abstract

We introduce an approach to identifying speaker names in dialogue transcripts, a crucial task for enhancing content accessibility and searchability in digital media archives. Despite the advancements in speech recognition, the task of text-based speaker identification (SpeakerID) has received limited attention, lacking large-scale, diverse datasets for effective model training. Addressing these gaps, we present a novel, large-scale dataset derived from the MediaSum corpus, encompassing transcripts from a wide range of media sources. We propose novel transformer-based models tailored for SpeakerID, leveraging contextual cues within dialogues to accurately attribute speaker names. Through extensive experiments, our best model achieves a great precision of 80.3\%, setting a new benchmark for SpeakerID. The data and code are publicly available here: \url{https://github.com/adobe-research/speaker-identification}