# MSU-Bench: Towards Speaker-Centric Understanding in Conversational Multi-Speaker Scenarios

arXiv: https://arxiv.org/abs/2606.22868 · HTML: https://mlsanity.com/paper/2606.22868/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Jun 2026.

## Built on by (most cited first, 2 of 2)

- [Do Audio LLMs Listen Before They Act? Diagnosing Acoustic-Context Gating in Voice Agents](https://mlsanity.com/paper/2609.32536/) (2026)
- [PERSIST: Who-What-When Memory Across Sessions for Full-Duplex Spoken Dialogue](https://mlsanity.com/paper/2610.07725/) (2026)

## Abstract (arXiv)

Spoken Language Understanding (SLU) is moving from task-specific pipelines toward large audio language models (LALMs) that generate natural-language responses. However, existing speech benchmarks mainly focus on single-speaker settings or isolated subtasks, leaving speaker-centric understanding in realistic multi-speaker conversations insufficiently evaluated. We introduce MSU-Bench, a diagnostic benchmark for multi-speaker conversational understanding, covering 16 speaker-centric tasks and 2,300 QA instances in a two-tier framework from speaker grounding to dialogue reasoning. We build a Gemini-assisted annotation and QA generation pipeline with human-in-the-loop verification, achieving high QA validity and strong agreement between human answers and verified labels. We further analyze speaker-referencing schemes and diagnostic error types to reveal bottlenecks in speaker grounding and reasoning. Experiments reveal clear gaps across model families, with closed-source systems leading overall but all models still facing challenges in complex speaker grounding and multi-speaker reasoning. The benchmark annotations, metadata, and evaluation scripts will be available at the GitHub repository: https://github.com/ASLP-lab/MSU-Bench.