CLAP: Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation2025-02-07 深度学习 EVA-GAN: Enhanced Various Audio Generation via Scalable Generative Adversarial Networks2025-01-17 深度学习 Whisper: Robust Speech Recognition via Large-Scale Weak Supervision2025-01-14 DaNing HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis2025-01-03 深度学习