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 introduce DramaSR-532K, a large-scale benchmark for speaker recognition in long-form TV dramas. They also propose DramaSR-LRM, a robust approach that uses a large reasoning model to improve speaker recognition by integrating auditory, linguistic, and visual cues. This method outperforms existing baselines, particularly on short utterances.

What the Document Says

• The paper introduces DramaSR-532K, a large-scale benchmark for speaker recognition in long-form TV dramas.
• DramaSR-LRM is proposed as a robust approach for speaker recognition that uses a large reasoning model (LRM).
• DramaSR-LRM aggregates contextual evidence via multimodal tool-use and synthesizes diverse inputs for high-fidelity attribution.
• Experimental results show that DramaSR-LRM outperforms existing baselines, particularly on short utterances where acoustic biometrics are unreliable.

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 in long-form TV dramas.
• DramaSR-LRM is a robust approach that improves speaker recognition using a large reasoning model.

Evidence Used

• The paper provides details about DramaSR-532K and DramaSR-LRM.

Methods / Approach

• Multimodal tool-use to aggregate contextual evidence and synthesize diverse inputs for speaker recognition.

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

The paper does not discuss potential limitations of the proposed method.

Open Questions

• What specific large reasoning model is used in DramaSR-LRM?
• How does DramaSR-LRM perform on various types and lengths of TV dramas?

Notes for Future Q&A

May include interpretation. Labeled where it does.

• The paper mentions 'acoustic biometrics' but does not define it. It may refer to the unique physical characteristics of a person's voice used for identification.
• The paper promises that all data and code will be made publicly available, but does not specify when this will happen.

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.}