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

The researchers introduce a large-scale benchmark called DramaSR-532K for speaker recognition in long-form TV dramas and propose a new method, DramaSR-LRM, built on a large reasoning model (LRM). This method aggregates contextual evidence through multimodal tool-use to improve accuracy in attributing spoken utterances to characters. The new approach outperforms existing baselines, particularly for short utterances.

What the Document Says

The paper presents two contributions for speaker recognition in long-form TV dramas.
A large-scale benchmark named DramaSR-532K is introduced, consisting of 532K annotated dialogue lines across over 900 characters.
DramaSR-LRM, a robust approach based on a large reasoning model (LRM), is proposed. It aggregates contextual evidence using multimodal tool-use for high-fidelity attribution.
Experimental results show that DramaSR-LRM outperforms existing baselines, especially for short utterances.

Key Concepts Mentioned

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

Claims Made by the Document

The proposed method, DramaSR-LRM, outperforms existing baselines for speaker recognition in long-form TV dramas.
The new benchmark, DramaSR-532K, requires integration of auditory, linguistic, and visual cues.

Evidence Used

Experimental results demonstrate that DramaSR-LRM significantly outperforms existing baselines.

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.}