28 citations · 46 across the 11 of their papers we have counts for
5 papers · 1 filter
Generating Novel and Realistic Speakers for Voice Conversion
Meiying Melissa Chen, Zhenyu Wang, Zhiyao Duan
Voice conversion models modify timbre while preserving paralinguistic features, enabling applications like dubbing and identity protection. However, most VC systems require access…
Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword Spotting
Zhenyu Wang, Li Wan, Biqiao Zhang +5
A keyword spotting (KWS) engine that is continuously running on device is exposed to various speech signals that are usually unseen before. It is a challenging problem to build a s…
Toward Improving Synthetic Audio Spoofing Detection Robustness via Meta-Learning and Disentangled Training With Adversarial Examples
Zhenyu Wang, John H. L. Hansen
Advances in automatic speaker verification (ASV) promote research into the formulation of spoofing detection systems for real-world applications. The performance of ASV systems can…
Multi-source Domain Adaptation for Text-independent Forensic Speaker Recognition
Zhenyu Wang, John H. L. Hansen
Adapting speaker recognition systems to new environments is a widely-used technique to improve a well-performing model learned from large-scale data towards a task-specific small-s…
Audio Anti-spoofing Using a Simple Attention Module and Joint Optimization Based on Additive Angular Margin Loss and Meta-learning
Zhenyu Wang, John H. L. Hansen
Automatic speaker verification systems are vulnerable to a variety of access threats, prompting research into the formulation of effective spoofing detection systems to act as a ga…