MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915440146513920 |
|---|---|
| author | Wang, Shuai Sun, Zhaokai Lin, Zhennan Wang, Chengyou Pan, Zhou Xie, Lei |
| author_facet | Wang, Shuai Sun, Zhaokai Lin, Zhennan Wang, Chengyou Pan, Zhou Xie, Lei |
| contents | Spoken Language Understanding (SLU) has progressed from traditional single-task methods to large audio language model (LALM) solutions. Yet, most existing speech benchmarks focus on single-speaker or isolated tasks, overlooking the challenges posed by multi-speaker conversations that are common in real-world scenarios. We introduce MSU-Bench, a comprehensive benchmark for evaluating multi-speaker conversational understanding with a speaker-centric design. Our hierarchical framework covers four progressive tiers: single-speaker static attribute understanding, single-speaker dynamic attribute understanding, multi-speaker background understanding, and multi-speaker interaction understanding. This structure ensures all tasks are grounded in speaker-centric contexts, from basic perception to complex reasoning across multiple speakers. By evaluating state-of-the-art models on MSU-Bench, we demonstrate that as task complexity increases across the benchmark's tiers, all models exhibit a significant performance decline. We also observe a persistent capability gap between open-source models and closed-source commercial ones, particularly in multi-speaker interaction reasoning. These findings validate the effectiveness of MSU-Bench for assessing and advancing conversational understanding in realistic multi-speaker environments. Demos can be found in the supplementary material. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_08155 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios Wang, Shuai Sun, Zhaokai Lin, Zhennan Wang, Chengyou Pan, Zhou Xie, Lei Audio and Speech Processing Sound Spoken Language Understanding (SLU) has progressed from traditional single-task methods to large audio language model (LALM) solutions. Yet, most existing speech benchmarks focus on single-speaker or isolated tasks, overlooking the challenges posed by multi-speaker conversations that are common in real-world scenarios. We introduce MSU-Bench, a comprehensive benchmark for evaluating multi-speaker conversational understanding with a speaker-centric design. Our hierarchical framework covers four progressive tiers: single-speaker static attribute understanding, single-speaker dynamic attribute understanding, multi-speaker background understanding, and multi-speaker interaction understanding. This structure ensures all tasks are grounded in speaker-centric contexts, from basic perception to complex reasoning across multiple speakers. By evaluating state-of-the-art models on MSU-Bench, we demonstrate that as task complexity increases across the benchmark's tiers, all models exhibit a significant performance decline. We also observe a persistent capability gap between open-source models and closed-source commercial ones, particularly in multi-speaker interaction reasoning. These findings validate the effectiveness of MSU-Bench for assessing and advancing conversational understanding in realistic multi-speaker environments. Demos can be found in the supplementary material. |
| title | MSU-Bench: Towards Understanding the Conversational Multi-talker Scenarios |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2508.08155 |