ASVspoof Workshop 2024 Program
All sessions will be held in the Asklipios meeting room.
| Session Name | Chair | Start | End | Title | Presenter(s) |
|---|---|---|---|---|---|
| Opening | 09:45 | 10:00 | Welcome Message | ASVspoof 5 Organiser | |
| ASVspoof 5 Challenge Summary | John Hansen | 10:00 | 10:45 | ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale | Xin Wang & Héctor Delgado |
| ASVspoof 5 Site Presentation 1 | Elie Khoury | 10:45 | 10:55 | ParallelChain Lab's Anti-spoofing Systems for ASVspoof 5 | Panagiotis Simatis |
| ASVspoof 5 Site Presentation 1 | Elie Khoury | 10:55 | 11:05 | Data augmentations for audio deepfake detection for the ASVspoof5 closed condition | Pierre Champion |
| ASVspoof 5 Site Presentation 1 | Elie Khoury | 11:05 | 11:15 | BUT Systems and Analyses for the ASVspoof 5 Challenge | Oldřich Plchot |
| ASVspoof 5 Site Presentation 1 | Elie Khoury | 11:15 | 11:25 | Whispeak Speech Deepfake Detection Systems for the ASVspoof5 Challenge | Pierre Falez |
| ASVspoof 5 Site Presentation 1 | Elie Khoury | 11:25 | 11:35 | The SHADOW Team Submission to the ASVSpoof 2024 Challenge | Tiantian Feng |
| ASVspoof 5 Site Presentation 1 | Elie Khoury | 11:35 | 11:45 | IDVoice team System Description for ASVSpoof5 Challenge | Rostislav Makarov |
| ASVspoof 5 Site Presentation 1 | Elie Khoury | 11:45 | 11:55 | AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge | Dmitrii Korzh |
| ASVspoof 5 Site Presentation 1 | Elie Khoury | 11:55 | 12:05 | Robust Audio Deepfake Detection: Exploring Front-/Back-End Combinations and Data Augmentation Strategies for the ASVspoof5 Challenge | Karla Schäfer |
| ASVspoof 5 Site Presentation 1 | Elie Khoury | 12:05 | 12:15 | SZU-AFS Antispoofing System for the ASVspoof 5 Challenge | Bin Li |
| ASVspoof 5 Site Presentation 1 | Elie Khoury | 12:15 | 12:25 | Exploring WavLM Back-ends for Speech Spoofing and Deepfake Detection | Reda Dehak (via Zoom) |
| Lunch (1 hour 10 minutes) | 12:25 | 13:35 | Free lunch at Kipriotis Panorama Main Restaurant (12:30-14:30) | ||
| ASVspoof 5 and beyond | Antonio Peinado | 13:35 | 13:50 | Analyzing the Impact of Splicing Artifacts in Partially Fake Speech Signals | Viola Negroni |
| ASVspoof 5 and beyond | Antonio Peinado | 13:50 | 14:05 | Exploring Generalization To Unseen Audio Data For Spoofing: Insights From SSL Models | Ajinkya Kulkarni |
| ASVspoof 5 and beyond | Antonio Peinado | 14:05 | 14:20 | Malacopula: adversarial automatic speaker verification attacks using a neural-based generalised Hammerstein model | Massimiliano Todisco |
| ASVspoof 5 and beyond | Antonio Peinado | 14:20 | 14:30 | Temporal Variability and Multi-scaled Self-Supervised Representations to Tackle the ASVspoof5 Deepfake Challenge | yuankun xie (via Zoom) |
| ASVspoof 5 and beyond | Antonio Peinado | 14:30 | 14:40 | USTC-KXDIGIT System Description for ASVspoof5 Challenge | Yihao Chen (via Zoom) |
| ASVspoof 5 and beyond | Antonio Peinado | 14:40 | 14:50 | Learn from Real: Reality Defender's Submission to ASVspoof5 Challenge | Yi Zhu (via Zoom) |
| ASVspoof 5 and beyond | Antonio Peinado | 14:50 | 15:00 | A Single End-to-end Voice Anti-spoofing Model with Graph Attention and Feature Aggregation for ASVspoof 5 Challenge | Weijiang Xia (via Zoom) |
| ASVspoof 5 and beyond | Antonio Peinado | 15:00 | 15:10 | A universal deception speech detection based on an innovative progressive training method with improved virtual softmax and data balance | Jian Guo (via Zoom) |
| Coffee break (30 minutes) | 15:10 | 15:40 | KPCC / Level 1 / lobby area | ||
| ASVspoof 5 Site Presentation 2 | Themos Stafylakis | 15:40 | 15:50 | Spoofing-Robust Speaker Verification Using Parallel Embedding Fusion: BTU Speech Group’s Approach for ASVspoof5 Challenge | Jagabandhu Mishra |
| ASVspoof 5 Site Presentation 2 | Themos Stafylakis | 15:50 | 16:00 | ASASVIcomtech: The Vicomtech-UGR Speech Deepfake Detection and SASV Systems for the ASVspoof5 Challenge | Iván López-Espejo |
| ASVspoof 5 Site Presentation 2 | Themos Stafylakis | 16:00 | 16:10 | Intema System Description for the ASVspoof5 Challenge: Power Weighted Score Fusion | Alexander Kondratev |
| ASVspoof 5 Site Presentation 2 | Themos Stafylakis | 16:10 | 16:20 | Enhancing Spoofing Detection in ASVspoof 5 Workshop 2024: Fusion of WavLM-ResNet18-SA for Optimal Performance Against Speech Deepfakes | Po-Cheng Chan |
| ASVspoof 5 Site Presentation 2 | Themos Stafylakis | 16:20 | 16:30 | ASVspoof 5 Challenge: Advanced ResNet Architectures for Robust Voice Spoofing Detection | Anh-Tuan Dao |
| ASVspoof 5 Site Presentation 2 | Themos Stafylakis | 16:30 | 16:40 | WavLM model ensemble for audio deepfake detection | Adriana Stan |
| ASVspoof 5 Site Presentation 2 | Themos Stafylakis | 16:40 | 16:50 | A Study of Guided Masking Data Augmentation for Deepfake Speech Detection | Duc-Tuan Truong |
| ASVspoof 5 Site Presentation 3 | Themos Stafylakis | 16:50 | 17:00 | Augmentation through Laundering Attacks for Audio Spoof Detection | Hafiz Malik (via Zoom) |
| ASVspoof 5 Forum | 17:00 | 18:00 | Forum and discussion | All participants |