Zero-shot Audio Captioning

1 papers with code • 2 benchmarks • 2 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.

Most implemented papers

Zero-shot audio captioning with audio-language model guidance and audio context keywords

explainableml/zeraucap 14 Nov 2023

In particular, our framework exploits a pre-trained large language model (LLM) for generating the text which is guided by a pre-trained audio-language model to produce captions that describe the audio content.