WoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizations
The World-of-Whale benchmark (WoW-Bench) is introduced to evaluate low-level auditory perception and cognition using marine mammal vocalizations to better assess models' low-level listening and so that the models do not rely on prior knowledge of the sound events.
Jaeyeon Kim, Heeseung Yun, S. Woo et al.
· Annual Meeting of the Associ... · 9 citations
· ⚡1