mlsanityData to 7 Oct 2026

Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas

arXiv 2607.02504 ↗First posted 2 Jul 2026cs.CL cs.AI cs.CVcited by 0

On the map: LLM reasoning → Audio-language model reasoning

Abstract (arXiv)

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. textitAll the data and code will be made publicly available at the project page: https://www.github.com/198808xc/DramaSR-LRM.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Audio-language model reasoning, one of 17 directions in LLM reasoning. Builds on 30 of its 61 references that are in the map. First posted on arXiv 2 Jul 2026.

Builds on

30 of 61 references.

References · 30

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  5. 2025Qwen3 Technical Reportcited by 8,195
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  7. 2025Qwen2.5-VL Technical Reportcited by 5,418
  8. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  9. 2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextcited by 3,175
  10. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  11. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  12. 2025Qwen3-VL Technical Reportcited by 2,534
18 more
  1. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 810
  2. 2025Group Sequence Policy Optimizationcited by 788
  3. 2025Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Modelscited by 653
  4. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 606
  5. 2025PaddleOCR 3.0 Technical Reportcited by 136
  6. 2025Geometric-Mean Policy Optimizationcited by 107
  7. 2023CAM++: A Fast and Efficient Network for Speaker Verification Using Context-Aware Maskingcited by 95
  8. 2025PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Modelcited by 84
  9. 2020Spot the conversation: speaker diarisation in the wildcited by 75
  10. 2025Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learningcited by 68
  11. 2023An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verificationcited by 41
  12. 2024ERes2NetV2: Boosting Short-Duration Speaker Verification Performance with Computational Efficiencycited by 18
  13. 2024DiarizationLM: Speaker Diarization Post-Processing with Large Language Modelscited by 16
  14. 20233D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglementcited by 15
  15. 2025SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language Modelscited by 14
  16. 2024StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identificationcited by 13
  17. 2025From Long Videos to Engaging Clips: A Human-Inspired Video Editing Framework with Multimodal Narrative Understandingcited by 6
  18. 2026D-ORCA: Dialogue-Centric Optimization for Robust Audio-Visual Captioningcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025M3-SLU: Evaluating Speaker-Attributed Reasoning in Multimodal Large Language Models
  2. 2025SpeechR: A Benchmark for Speech Reasoning in Large Audio-Language Models
  3. 2024Character-aware audio-visual subtitling in context
  4. 2026Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR
  5. 2026SpeakerLLM: A Speaker-Specialized Audio-LLM for Speaker Understanding and Verification Reasoning
  6. 2025See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models
  7. 2026HEAR Who Said What: Unlocking Speaker-Attributed Reasoning via Counterfactual Voice Grounding
  8. 2025Learning LLM Preference over Intra-Dialogue Pairs: A Framework for Utterance-level Understandings