Picture for Philip Sperl

Philip Sperl

Harder or Different? Understanding Generalization of Audio Deepfake Detection

Add code
Jun 07, 2024
Viaarxiv icon

Imbalance in Regression Datasets

Add code
Feb 19, 2024
Viaarxiv icon

A New Approach to Voice Authenticity

Add code
Feb 09, 2024
Viaarxiv icon

MLAAD: The Multi-Language Audio Anti-Spoofing Dataset

Add code
Jan 17, 2024
Viaarxiv icon

Physical Adversarial Examples for Multi-Camera Systems

Add code
Nov 14, 2023
Viaarxiv icon

Protecting Publicly Available Data With Machine Learning Shortcuts

Add code
Oct 30, 2023
Viaarxiv icon

Complex-valued neural networks for voice anti-spoofing

Add code
Aug 22, 2023
Viaarxiv icon

Shortcut Detection with Variational Autoencoders

Add code
Feb 08, 2023
Viaarxiv icon

R2-AD2: Detecting Anomalies by Analysing the Raw Gradient

Add code
Jun 21, 2022
Figure 1 for R2-AD2: Detecting Anomalies by Analysing the Raw Gradient
Figure 2 for R2-AD2: Detecting Anomalies by Analysing the Raw Gradient
Figure 3 for R2-AD2: Detecting Anomalies by Analysing the Raw Gradient
Figure 4 for R2-AD2: Detecting Anomalies by Analysing the Raw Gradient
Viaarxiv icon

Visualizing Automatic Speech Recognition -- Means for a Better Understanding?

Add code
Feb 01, 2022
Figure 1 for Visualizing Automatic Speech Recognition -- Means for a Better Understanding?
Figure 2 for Visualizing Automatic Speech Recognition -- Means for a Better Understanding?
Figure 3 for Visualizing Automatic Speech Recognition -- Means for a Better Understanding?
Figure 4 for Visualizing Automatic Speech Recognition -- Means for a Better Understanding?
Viaarxiv icon