Drift-Augmented

Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classification

arXiv:2606.04844v1 Announce Type: new Abstract: Contrastive audio-language models such as CLAP enable zero-shot audio classification: a sound is labelled by matching its embedding to text prompt embeddings, with no labelled audio. This matching breaks down under acoustic noise, where accuracy and mAP fall by 12-30 percentage points at 0 dB SNR on standard benchmarks. We propose Drift Augmented Scoring (DAS), a small per-class bonus added to the cosine score.