Identifying Speakers in Dialogue Transcripts: A Text-based Approach Using Pretrained Language Models
Nguyen, Minh, Dernoncourt, Franck, Yoon, Seunghyun, Deilamsalehy, Hanieh, Tan, Hao, Rossi, Ryan, Tran, Quan Hung, Bui, Trung, Nguyen, Thien Huu
–arXiv.org Artificial Intelligence
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}
arXiv.org Artificial Intelligence
Jul-16-2024
- Country:
- Asia (0.93)
- North America > United States
- Minnesota > Hennepin County > Minneapolis (0.14)
- Genre:
- Research Report (1.00)
- Industry:
- Leisure & Entertainment (0.93)
- Media > News (0.48)
- Technology: