Spoof-SUPERB benchmark shows large-scale discriminative SSL models such as XLS-R, UniSpeech-SAT, and WavLM Large outperform others in audio deepfake detection and maintain robustness under acoustic degradations.
DeCoAR 2.0: Deep Contextualized Acoustic Repre- sentations with Vector Quantization,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Speech-FT applies drift-reduced fine-tuning followed by weight-space interpolation to improve both task performance and cross-task generalization in models such as HuBERT and WavLM.
citing papers explorer
-
A SUPERB-Style Benchmark of Self-Supervised Speech Models for Audio Deepfake Detection
Spoof-SUPERB benchmark shows large-scale discriminative SSL models such as XLS-R, UniSpeech-SAT, and WavLM Large outperform others in audio deepfake detection and maintain robustness under acoustic degradations.
-
Speech-FT: Merging Pre-trained And Fine-Tuned Speech Representation Models For Cross-Task Generalization
Speech-FT applies drift-reduced fine-tuning followed by weight-space interpolation to improve both task performance and cross-task generalization in models such as HuBERT and WavLM.