activity
20232026
most citedInvestigating Prosodic Signatures via Speech Pre-Trained Models for Audio Deepfake Source Attribution

1 citations · 4 across the 26 of their papers we have counts for

collaborators
Showing cs.SDShow all

1 paper · 1 filter

cs.SD2024

FastAST: Accelerating Audio Spectrogram Transformer via Token Merging and Cross-Model Knowledge Distillation

Swarup Ranjan Behera, Abhishek Dhiman, Karthik Gowda +1

Audio classification models, particularly the Audio Spectrogram Transformer (AST), play a crucial role in efficient audio analysis. However, optimizing their efficiency without com…