Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
DramaSR-532K benchmarks speaker attribution over 532K dialogue lines and 900+ TV-drama characters; a reasoning LLM with multimodal tool use beats acoustic baselines, especially on short utterances.
**The gist** The paper ships **DramaSR-532K**, a benchmark of **532K annotated dialogue lines across 900+ characters** in long-form TV dramas, plus **DramaSR-LRM**, a reasoning LLM that calls audio, text, and visual tools to attribute each line to a speaker.
**Why it matters** It's a concrete case of the agentic pattern — reasoning model plus **multimodal tool use** — beating specialized pipelines where a single signal fails: voice biometrics collapse on **short utterances**, and cross-modal evidence aggregation recovers them. Relevant if you build media-understanding or transcription tooling.
**The gist** The paper ships **DramaSR-532K**, a benchmark of **532K annotated dialogue lines across 900+ characters** in long-form TV dramas, plus **DramaSR-LRM**, a reasoning LLM that calls audio, text, and visual tools to attribute each line to a speaker. **Why it matters** It's a concrete case of the agentic pattern — reasoning model plus **multimodal tool use** — beating specialized pipelines where a single signal fails: voice biometrics collapse on **short utterances**, and cross-modal evidence aggregation recovers them. Relevant if you build media-understanding or transcription tooling. **Watch out** The abstract reports improvements **without headline numbers**, language coverage beyond this drama corpus is unclear, and code and data are promised but the release couldn't be verified from the page.