WavCaps

WavCaps WavCaps is a ChatGPT-assisted weakly-labelled audio captioning dataset for audio-language multimodal research, where the audio clips are sourced from three websites (FreeSound, BBC Sound Effects, and SoundBible) and a sound event detection dataset (AudioSet Strongly-labelled Subset). Paper: https://arxiv.org/ab

Papers using WavCaps (3)

Representation Learning for Semantic Alignment of Language, Audio, and Visual Modalities2025 · 1 citesAC/DC: LLM-based Audio Comprehension via Dialogue Continuation2025MINT: a Multi-modal Image and Narrative Text Dubbing Dataset for Foley Audio Content Planning and Generation2024