Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas

Source

Source name: arXiv
Source kind: paper
Authors / organization: Yuxuan Li, Lingxi Xie, Xinyue Huo, Jihao Qiu, Jiacheng Shao, Pengfei Chen, Jiannan Ge, Kaiwen Duan, Qi Tian
Venue: arXiv: cs.CL
Published: 2026-07-02
Collected: 2026-07-03
URL: http://arxiv.org/abs/2607.02504v1
PDF: https://arxiv.org/pdf/2607.02504v1
DOI: UNKNOWN

Plain-Language Brief

Researchers present two contributions aimed at improving speaker recognition in long-form TV dramas. They create a large-scale benchmark called DramaSR-532K with over 900 characters and propose using a large reasoning model (LRM) to autonomously aggregate contextual evidence via multimodal tool-use for high-fidelity attribution. Experimental results show that their proposed method, DramaSR-LRM, outperforms existing baselines, particularly on short utterances.

What the Document Says

The researchers introduce a large-scale benchmark called DramaSR-532K for speaker recognition in long-form TV dramas.
They propose a method called DramaSR-LRM which is built upon a large reasoning model (LRM) to achieve high-fidelity attribution.
DramaSR-LRM autonomously aggregates contextual evidence via multimodal tool-use.
Experimental results show that DramaSR-LRM outperforms existing baselines, particularly on short utterances.

Key Concepts Mentioned

speaker recognition
long-form TV dramas
DramaSR-532K
DramaSR-LRM
large reasoning model (LRM)
multimodal tool-use

Claims Made by the Document

DramaSR-532K is a large-scale benchmark for speaker recognition.
DramaSR-LRM is a method that outperforms existing baselines for speaker recognition.

Evidence Used

The paper mentions the creation of DramaSR-532K as a contribution.
The paper states experimental results showing the outperformance of DramaSR-LRM.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.}