audio-5
Zero-shot Audio Captioning
3260 papers • 126 benchmarks • 313 datasets
Zero-shot audio captioning aims at automatically generating descriptive textual captions for audio content without any prior training for this task. Audio captioning is commonly concerned with ambient sounds, or sounds produced by a human performing an action.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in zero-shot-audio-captioning-5
Trend
Dataset
Best Model
Actions
AudioCaps
AudioCaps
Clotho
Clotho
Libraries
iUse these libraries to find zero-shot-audio-captioning-5 models and implementations
Datasets
Subtasks
No subtasks available.
Most implemented papers
Zero-shot audio captioning with audio-language model guidance and audio context keywords
Leonard Salewski, Zeynep Akata, A. S. Koepke, Stefan Fauth•Mon Nov 13 2023
This work proposes ZerAuCap, a novel framework for summarising general audio signals in a text caption without requiring task-specific training that achieves state-of-the-art results in zero-shot audio captioning on the AudioCaps and Clotho datasets.
15