Jingran Xie
3 indexed papers
Recent (6 mo)
3With code
0Influential cites
0Benchmarked
0Publications per year
326
Top categories
Sound×3AI×2ML×1Crypto×1Multimedia×1
Frequent co-authors
Research Timeline
2026
Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions
The paper proposes a feature-aligned watermarking method to improve the robustness of audio watermarks while preserving imperceptibility.
Self-Guidance: Enhancing Neural Codecs via Decoder Manifold Alignment
The paper proposes a method called self-guidance to improve the reconstruction fidelity of neural speech codecs based on Vector-Quantized VAEs.
UniAE-MoE: A Unified Audio Encoder via Mixture of Experts
This paper introduces UniAE-MoE, a unified audio encoder that achieves state-of-the-art performance in audio understanding tasks.
Highlighted terms show continued research focus across papers
Papers
cs.SDcs.AIEmpiricalRecentSep 30, 2026
UniAE-MoE: A Unified Audio Encoder via Mixture of Experts
Shengbo Cai, Zhisheng Zhang, Zichao Nie, Jing Peng +2 more
This paper introduces UniAE-MoE, a unified audio encoder that achieves state-of-the-art performance in audio understanding tasks.
View →
cs.SDcs.LGEmpiricalRecent