Xuechen Liu

Biography

Xuechen Liu is a Project Postdoctoral Researcher at the National Institute of Informatics in Tokyo, Japan. He holds a PhD in Computer Science from the University of Eastern Finland and has industrial experience at Emotech LTD. His research focuses on audio deepfake detection, speaker recognition, and multi-modal information retrieval. He has published extensively in speech and audio conference venues and journals and has been an organizing committee member of ASVspoof Challenges since 2021.

Career

Awards

• 2015 COMAP Mathematics Contest in Modeling Meritorious winner

Academic Activities

• Member of IEEE and ISCA

Recent Research

• Post-training for Deepfake Speech Detection
• Target Speaker Extractor Training with Diverse Speaker Conditions and Synthetic Data
• LENS-DF: Deepfake Detection and Temporal Localization for Long-Form Noisy Speech
• From Sharpness to Better Generalization for Speech Deepfake Detection
• AfriHuBERT: A self-supervised speech representation model for African languages
• ASVspoof 5: Design, collection and validation of resources for spoofing, deepfake, and adversarial attack detection using crowdsourced speech
• Explaining Speaker and Spoof Embeddings via Probing
• Improving curriculum learning for target speaker extraction with synthetic speakers
• Disentangling the Prosody and Semantic Information with Pre-trained Model for In-Context Learning based Zero-Shot Voice Conversion
• A Preliminary Study on Long-Form In-the-Wild Audio Spoofing Detection
• Quantifying Source Speaker Leakage in One-to-One Voice Conversion
• Generating Speakers by Prompting Listener Impressions for Pre-trained Multi-Speaker Text-to-Speech Systems
• Target Speaker Extraction with Curriculum Learning
• ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale
• Open-Source Conversational AI with SpeechBrain 1.0
• [Arxiv] Speaker-Text Retrieval via Contrastive Learning
• Towards single integrated spoofing-aware speaker verification embeddings
• ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild
• Benchmarking and Challenges in Security and Privacy for Voice Biometrics
• ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection