2 citations · 3 across the 4 of their papers we have counts for
10 papers
FlowGRPO for Vocal Separation: From Reward Analysis to Reward Design
Lishi Zuo, Chong-Xin Gan, Zezhong Jin +3
The Flow Matching objective supervises the velocity field at intermediate states, whereas waveform metrics are evaluated after decoding and may be non-differentiable. To align Flow…
DuRe-ST: Dual-Relation Spectro-Temporal Modeling for Speech Deepfake Detection
Shaole Li, Siqing Qin, Youzhi Tu +1
Previous speech deepfake detectors can adaptively capture spectro-temporal dependencies through graph attention, yet they largely overlook the co-variation between spectral and tem…
Source-Directed Trajectory Perturbation at First-Order Cost for Domain Generalization in Speech Deepfake Detection
Siqing Qin, Kong Aik Lee, Youzhi Tu
Speech deepfake detectors often lose accuracy when the distribution of the test data differs from that of the training data. Meta-learning for domain generalization (MLDG) shows pr…
DGS-MLDG: Domain Gradient Surgery Guided Meta-Learning for Domain Generalization in Speech Deepfake Detection
Siqing Qin, Kong Aik Lee, Youzhi Tu +2
Speech deepfake detection faces significant challenges due to domain shifts. Domain generalization (DG), particularly meta-learning for domain generalization (MLDG), offers a promi…
Cross-modal Translation via Conditional Latent Denoising for Video Deepfake Detection
Xinzhe Li, Youzhi Tu, Kong Aik Lee
The growing threat of video deepfakes necessitates multimodal detection. Beyond serving as independent indicators of authenticity, audio and visual signals have intrinsic dependenc…
Decoupled Latent Flow Matching for Few-Step Joint Vocal-Accompaniment Separation
Lishi Zuo, Youzhi Tu, Lu Yi +4
Generative modeling provides a flexible way to model mixture-conditioned source distributions, but iterative diffusion and flow matching models are costly for long music signals. T…
Class Unbiasing for Generalization in Medical Diagnosis
Lishi Zuo, Man-Wai Mak, Lu Yi +1
Medical diagnosis might fail due to bias. In this work, we identified class-feature bias, which refers to models' potential reliance on features that are strongly correlated with o…
Phonetic-aware speaker embedding for far-field speaker verification
Zezhong Jin, Youzhi Tu, Man-Wai Mak
When a speaker verification (SV) system operates far from the sound sourced, significant challenges arise due to the interference of noise and reverberation. Studies have shown tha…
Contrastive Speaker Embedding With Sequential Disentanglement
Youzhi Tu, Man-Wai Mak, Jen-Tzung Chien
Contrastive speaker embedding assumes that the contrast between the positive and negative pairs of speech segments is attributed to speaker identity only. However, this assumption…
Self-supervised Neural Factor Analysis for Disentangling Utterance-level Speech Representations
Weiwei Lin, Chenhang He, Man-Wai Mak +1
Self-supervised learning (SSL) speech models such as wav2vec and HuBERT have demonstrated state-of-the-art performance on automatic speech recognition (ASR) and proved to be extrem…