CG
Chong-Xin Gan
cs.SDeess.AScs.AIcs.CLcs.MMcs.HCeess.SP
On Valency
published · living versionsW_uudr4xyg·v1 · currentpublished
Manifold-Constrained Residual Adaptation with Frame-Adaptive Layer Aggregation for Speaker Verification
with Zezhong Jin, Xiaoyu Wang, Zhe Li, Siqing Qin +2
1 version
Preprints & journals
7 papers in the corpus · 2023–2026Manifold-Constrained Residual Adaptation with Frame-Adaptive Layer Aggregation for Speaker Verification2610.25892v1 · Zezhong Jin, Xiaoyu Wang, Zhe Li et al.2026 · 0 citationsarXivon Valency
FlowGRPO for Vocal Separation: From Reward Analysis to Reward Design2610.15780v1 · Lishi Zuo, Chong-Xin Gan, Zezhong Jin et al.2026 · 0 citationsarXiv
Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning2608.05549v1 · Zezhong Jin, Xiaoyu Wang, Zhe Li et al.2026 · 0 citationsarXiv
EII-SCL: Harnessing Emotional Inertia for Multimodal Emotion Recognition in Conversation2607.17366v1 · Zilong Huang, Kong Aik Lee, Chong-Xin Gan et al.2026 · 0 citationsarXiv
UNet-Based Fusion and Exponential Moving Average Adaptation for Noise-Robust Speaker Recognition2604.25624v1 · Chong-Xin Gan, Peter Bell, Man-Wai Mak et al.2026 · 0 citationsarXiv
TrInk: Ink Generation with Transformer Network2508.21098v1 · Zezhong Jin, Shubhang Desai, Xu Chen et al.2025 · 1 citationarXiv
Asymmetric Clean Segments-Guided Self-Supervised Learning for Robust Speaker Verification2309.04265v2 · Chong-Xin Gan, Man-Wai Mak, Weiwei Lin et al.2023 · 6 citationsarXiv
Career total: 14 works. 7 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.