ACAVCaps

ACAVCaps is a large-scale, fine-grained, and multi-faceted audio captioning dataset designed to evaluate general audio understanding in large audio-language models.

Papers using ACAVCaps (2)

MiDashengLM: Efficient Audio Understanding with General Audio Captions2025 · 30 citesACAVCaps: Enabling large-scale training for fine-grained and diverse audio understanding2026