6 citations · 11 across the 13 of their papers we have counts for
13 papers
Evidence Subspace Projection: Measuring How Much Evidence Explains Deepfake Detection in Self-Supervised Speech Models
Yixuan Xiao, Cheng-Wei Lin, Xin Wang +5
Self-supervised learning (SSL) models are widely used as feature extractors for state-of-the-art audio deepfake detection, but it remains unclear how to directly and quantitatively…
DeepFense: A Unified, Modular, and Extensible Framework for Robust Deepfake Audio Detection
Yassine El Kheir, Arnab Das, Yixuan Xiao +6
Speech deepfake detection is a well-established research field with different models, datasets, and training strategies. However, the lack of standardized implementations and evalu…
DFKI-Speech System for WildSpoof Challenge: A robust framework for SASV In-the-Wild
Arnab Das, Yassine El Kheir, Enes Erdem Erdogan +3
This paper presents the DFKI-Speech system developed for the WildSpoof Challenge under the Spoofing aware Automatic Speaker Verification (SASV) track. We propose a robust SASV fram…
Content Leakage in LibriSpeech and Its Impact on the Privacy Evaluation of Speaker Anonymization
Carlos Franzreb, Arnab Das, Tim Polzehl +1
Speaker anonymization aims to conceal a speaker's identity, without considering the linguistic content. In this study, we reveal a weakness of Librispeech, the dataset that is comm…
A Parameter-Efficient Multi-Scale Convolutional Adapter for Synthetic Speech Detection
Yassine El Kheir, Fabian Ritter-Guttierez, Arnab Das +2
Recent synthetic speech detection models typically adapt a pre-trained SSL model via finetuning, which is computationally demanding. Parameter-Efficient Fine-Tuning (PEFT) offers a…
Generalizable Audio Spoofing Detection using Non-Semantic Representations
Arnab Das, Yassine El Kheir, Carlos Franzreb +3
Rapid advancements in generative modeling have made synthetic audio generation easy, making speech-based services vulnerable to spoofing attacks. Consequently, there is a dire need…
Improving the Speaker Anonymization Evaluation's Robustness to Target Speakers with Adversarial Learning
Carlos Franzreb, Arnab Das, Tim Polzehl +1
The current privacy evaluation for speaker anonymization often overestimates privacy when a same-gender target selection algorithm (TSA) is used, although this TSA leaks the speake…
Two Views, One Truth: Spectral and Self-Supervised Features Fusion for Robust Speech Deepfake Detection
Yassine El Kheir, Arnab Das, Enes Erdem Erdogan +3
Recent advances in synthetic speech have made audio deepfakes increasingly realistic, posing significant security risks. Existing detection methods that rely on a single modality,…
Private kNN-VC: Interpretable Anonymization of Converted Speech
Carlos Franzreb, Arnab Das, Tim Polzehl +1
Speaker anonymization seeks to conceal a speaker's identity while preserving the utility of their speech. The achieved privacy is commonly evaluated with a speaker recognition mode…
Anonymising Elderly and Pathological Speech: Voice Conversion Using DDSP and Query-by-Example
Suhita Ghosh, Melanie Jouaiti, Arnab Das +4
Speech anonymisation aims to protect speaker identity by changing personal identifiers in speech while retaining linguistic content. Current methods fail to retain prosody and uniq…
PI-RADS v2 Compliant Automated Segmentation of Prostate Zones Using co-training Motivated Multi-task Dual-Path CNN
Arnab Das, Suhita Ghosh, Sebastian Stober
The detailed images produced by Magnetic Resonance Imaging (MRI) provide life-critical information for the diagnosis and treatment of prostate cancer. To provide standardized acqui…
StarGAN-VC++: Towards Emotion Preserving Voice Conversion Using Deep Embeddings
Arnab Das, Suhita Ghosh, Tim Polzehl +1
Voice conversion (VC) transforms an utterance to sound like another person without changing the linguistic content. A recently proposed generative adversarial network-based VC meth…
Emo-StarGAN: A Semi-Supervised Any-to-Many Non-Parallel Emotion-Preserving Voice Conversion
Suhita Ghosh, Arnab Das, Yamini Sinha +3
Speech anonymisation prevents misuse of spoken data by removing any personal identifier while preserving at least linguistic content. However, emotion preservation is crucial for n…