NoreSpeech: Knowledge Distillation based Conditional Diffusion Model for Noise-robust Expressive TTS
Dongchao Yang, Songxiang Liu, Helin Wang, Jianwei Yu, Chao Weng, Yuexian Zou
Topics & Concepts
Computer scienceDistillationNoise (video)DiffusionArtificial intelligencePhysicsThermodynamicsChemistryOrganic chemistryImage (mathematics)Speech Recognition and Synthesis