Identifying Speakers in Dialogue Transcripts: A Text-based Approach Using Pretrained Language Models
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}
Cite
@article{arxiv.2407.12094,
title = {Identifying Speakers in Dialogue Transcripts: A Text-based Approach Using Pretrained Language Models},
author = {Minh Nguyen and Franck Dernoncourt and Seunghyun Yoon and Hanieh Deilamsalehy and Hao Tan and Ryan Rossi and Quan Hung Tran and Trung Bui and Thien Huu Nguyen},
journal= {arXiv preprint arXiv:2407.12094},
year = {2024}
}
Comments
accepted to INTERSPEECH 2024