FMSU-Bench

Existing benchmarks predominantly cater to macroscopic tasks and suffer from coarse annotation granularity. We construct **FMSU-Bench**, a pioneering Fine-grained Multi-dimensional Speech Understanding Benchmark. * **Scale & Scope:** Comprises over **24,000 bilingual instances** (Chinese/English), manually verified by domain experts. * **Comprehensive Taxonomy:** Systematically covers **14 distinct speech dimensions** structured into a 5-tier taxonomy: 1. *Speaker Demographics:* Gender, Age, Accent 2. *Acoustic-Prosodic Features:* Pitch, Speaking Rate, Rhythm, Voice Texture 3. *Affective and Semantic Reasoning:* Emotion, Tone, Contextual Inference 4. *Acoustic Scene Analysis:* Background Sound, Acoustic Environment 5. *Linguistic-Paralinguistic Integration:* Paralinguistic Events, Transcription with Paralinguistic Tags (Evaluated via our novel **PATA** metric).