Jiangyan Yi

机构：Tsinghua University · ORCID：0000-0003-2422-4618

发表论文 212 篇 · 总被引 2338 次 · h-index 28

代表论文

• Seeing helps hearing: A multi-modal dataset and a mamba-based dual branch parallel network for auditory attention decoding (2025 · Information Fusion · 被引 30)
• Cross-Modal Knowledge Distillation With Multi-Stage Adaptive Feature Fusion for Speech Separation (2025 · IEEE Transactions on Audio Speech and Language Processing · 被引 18)
• Region-Based Optimization in Continual Learning for Audio Deepfake Detection (2025 · Proceedings of the AAAI Conference on Artificial Intelligence · 被引 6)
• ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection (2025 · 被引 4)
• Adversarial Training and Gradient Optimization for Partially Deepfake Audio Localization (2025 · 被引 4)
• WMCodec: End-to-End Neural Speech Codec with Deep Watermarking for Authenticity Verification (2025 · 被引 3)