Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
For researchers in video understanding and speaker recognition, this work provides a new benchmark and a method that leverages multimodal reasoning to improve attribution accuracy in complex narrative contexts.
The paper tackles speaker recognition in long-form TV dramas, introducing a large-scale benchmark (DramaSR-532K) and a reasoning-based model (DramaSR-LRM) that outperforms baselines, especially on short utterances where acoustic cues are unreliable.
Long-form TV dramas present a formidable challenge for comprehensive video understanding, where deciphering complex storyline often relies on \textbf{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 \textbf{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 \textbf{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. \textit{All the data and code will be made publicly available at the project page: https://www.github.com/198808xc/DramaSR-LRM.}