Prototype-Based Disentanglement for Controllable Dysarthric Speech Synthesis
基于原型的解耦方法用于可控性口吃语音合成
机构 * Department of Language Science and Technology, The Hong Kong Polytechnic University(语言科学与技术系,香港理工大学) ; College of Rehabilitation Medicine, Fujian University of Traditional Chinese Medicine(康复医学学院,福建中医药大学) ; Department of Imaging, Rehabilitation Hospital affiliated to Fujian University of Traditional Chinese Medicine(影像科,福建中医药大学附属康复医院)
专题命中 病理影像 :pathology(abstract)
AI总结 本文提出ProtoDisent-TTS框架,通过原型解耦技术实现健康与口吃语音的可控转换,提升语音合成的可控性和鲁棒性。