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

Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classification arXiv:2606.04844v1 Announce Type: cross 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 S