Zero-shot audio-language models are not reliable spoof detectors because they over-predict 'spoof', and FP16 quantization keeps this bias while INT8 worsens it.
The authors also gratefully acknowledge the support of IndiaAI and Meta through Srijan: Centre of Excellence for Generative AI
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Can Quantized Audio Language Models Perform Zero-Shot Spoofing Detection?
Zero-shot audio-language models are not reliable spoof detectors because they over-predict 'spoof', and FP16 quantization keeps this bias while INT8 worsens it.