8 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…
Domain-Adaptive Dual-Gating Mixture of Experts for Generalizable Speech Deepfake Detection
Siqing Qin, Zhe Li, Kong Aik Lee +1
Recent advances in speech deepfake detection (SDD) have leveraged the Mixture of Experts (MoE) to enhance generalization capacity. However, existing gating networks often overlook…
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…
TrInk: Ink Generation with Transformer Network
Zezhong Jin, Shubhang Desai, Xu Chen +8
In this paper, we propose TrInk, a Transformer-based model for ink generation, which effectively captures global dependencies. To better facilitate the alignment between the input…
Naturalistic Language-related Movie-Watching fMRI Task for Detecting Neurocognitive Decline and Disorder
Yuejiao Wang, Xianmin Gong, Xixin Wu +4
Early detection is crucial for timely intervention aimed at preventing and slowing the progression of neurocognitive disorder (NCD), a common and significant health problem among t…
Spectral-Aware Low-Rank Adaptation for Speaker Verification
Zhe Li, Man-wai Mak, Mert Pilanci +2
Previous research has shown that the principal singular vectors of a pre-trained model's weight matrices capture critical knowledge. In contrast, those associated with small singul…
Detecting Neurocognitive Disorders through Analyses of Topic Evolution and Cross-modal Consistency in Visual-Stimulated Narratives
Jinchao Li, Yuejiao Wang, Junan Li +14
Early detection of neurocognitive disorders (NCDs) is crucial for timely intervention and disease management. Given that language impairments manifest early in NCD progression, vis…
MoMuSE: Momentum Multi-modal Target Speaker Extraction for Real-time Scenarios with Impaired Visual Cues
Junjie Li, Ke Zhang, Shuai Wang +3
Audio-visual Target Speaker Extraction (AV-TSE) aims to isolate the speech of a specific target speaker from an audio mixture using time-synchronized visual cues. In real-world sce…