GPT-4o classifies environmental sounds from spectrogram images in a few-shot setting with 59% cross-validated accuracy on ESC-10, beating a commercial audio language model and roughly matching human experts.
A survey of vision-language pre-trained models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Vision Language Models Are Few-Shot Audio Spectrogram Classifiers
GPT-4o classifies environmental sounds from spectrogram images in a few-shot setting with 59% cross-validated accuracy on ESC-10, beating a commercial audio language model and roughly matching human experts.