Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
Lists
Only you see this
Abstract
Long-form TV dramas present a formidable challenge for comprehensive video understanding, where deciphering complex storyline often relies on **speaker recognition**, the task of accurately attributing each spoken utterance to its respective character. In this paper, we advance this field through two primary contributions. (1) We introduce **DramaSR-532K**, a large-scale benchmark comprising 532K annotated dialogue lines across more than 900 unique characters, necessitating the integration of auditory, linguistic, and visual cues for speaker recognition. (2) We propose **DramaSR-LRM**, a robust approach built upon a large reasoning model (LRM). DramaSR-LRM is designed to autonomously aggregate contextual evidence via multimodal tool-use, synthesizing diverse inputs to achieve high-fidelity attribution. Experimental results demonstrate that DramaSR-LRM significantly outperforms existing baselines, particularly on short utterances where acoustic biometrics are inherently unreliable. *All the data and code will be made publicly available.*
BibTeX
@inproceedings{li2026reasoning,
author = {Yuxuan Li and Lingxi Xie and Xinyue Huo and Jihao Qiu and Jiacheng Shao and Pengfei Chen and Jiannan Ge and Kaiwen Duan and Qi Tian},
title = {{Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas}},
booktitle = {International Conference on Machine Learning},
year = {2026},
url = {https://openreview.net/forum?id=h3TLVeukMA},
}Loading related content...