28 citations · 46 across the 13 of their papers we have counts for
14 papers
NouveauVoice: Generating Novel Pseudo Speakers for Voice Anonymization
Meiying Melissa Chen, Anastasia Kuznetsova, Zhenyu Wang +1
Advanced neural technologies in speech synthesis and voice conversion (VC) have introduced severe risks to personal privacy, necessitating robust Speaker Anonymization Systems (SAS…
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…
Towards 3D Objectness Learning in an Open World
Taichi Liu, Zhenyu Wang, Ruofeng Liu +2
Recent advancements in 3D object detection and novel category detection have made significant progress, yet research on learning generalized 3D objectness remains insufficient. In…
A Fusion Model for Artwork Identification Based on Convolutional Neural Networks and Transformers
Zhenyu Wang, Heng Song
The identification of artwork is crucial in areas like cultural heritage protection, art market analysis, and historical research. With the advancement of deep learning, Convolutio…
LogitLens4LLMs: Extending Logit Lens Analysis to Modern Large Language Models
Zhenyu Wang
This paper introduces LogitLens4LLMs, a toolkit that extends the Logit Lens technique to modern large language models. While Logit Lens has been a crucial method for understanding…
Query-by-Example Keyword Spotting Using Spectral-Temporal Graph Attentive Pooling and Multi-Task Learning
Zhenyu Wang, Shuyu Kong, Li Wan +6
Existing keyword spotting (KWS) systems primarily rely on predefined keyword phrases. However, the ability to recognize customized keywords is crucial for tailoring interactions wi…
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…
SATBA: An Invisible Backdoor Attack Based On Spatial Attention
Huasong Zhou, Xiaowei Xu, Xiaodong Wang +1
Backdoor attack has emerged as a novel and concerning threat to AI security. These attacks involve the training of Deep Neural Network (DNN) on datasets that contain hidden trigger…
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…
Impact of Naturalistic Field Acoustic Environments on Forensic Text-independent Speaker Verification System
Zhenyu Wang, John H. L. Hansen
Audio analysis for forensic speaker verification offers unique challenges in system performance due in part to data collected in naturalistic field acoustic environments where loca…
A multi-view approach for Mandarin non-native mispronunciation verification
Zhenyu Wang, John H. L. Hansen, Yanlu Xie
Traditionally, the performance of non-native mispronunciation verification systems relied on effective phone-level labelling of non-native corpora. In this study, a multi-view appr…
Cross-domain Adaptation with Discrepancy Minimization for Text-independent Forensic Speaker Verification
Zhenyu Wang, Wei Xia, John H. L. Hansen
Forensic audio analysis for speaker verification offers unique challenges due to location/scenario uncertainty and diversity mismatch between reference and naturalistic field recor…