Papers with Code · CC BY-SA 4.0

Zero-shot Audio Captioning

Audio captioning › Zero-shot Audio Captioning 5 평가 기록 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.

논문

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

2311.08396 2023-11-14 이 페이지의 평가 3건

BLEU-4: 6.8METEOR: 12.3ROUGE-L: 33.1CIDEr: 28.1

Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities

2402.01831 2024-02-02 이 페이지의 평가 1건

BLEU-4: 14.3METEOR: 20.5ROUGE-L: 40.8CIDEr: 50.2

Zero-Shot Audio Captioning via Audibility Guidance

2309.03884 2023-09-07 이 페이지의 평가 1건

BLEU-4: 9.8METEOR: 8.6ROUGE-L: 8.2CIDEr: 9.2