首页> Neural networks : the official journal of the International Neural Network Society> CMDF-TTS: Text-to-speech method with limited target speaker corpus.

CMDF-TTS: Text-to-speech method with limited target speaker corpus.

导出 LinkOut

翻译打印收藏纠错

第一作者： Ye,Tao

第一单位： School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, PR China. Electronic address: ye.tao@qust.edu.cn.

作者： Ye,Tao ^[1] ; Jiawang,Liu ^[2] ; Chaofeng,Lu ^[3] ; Meng,Liu ^[4] ; Xiugong,Qin ^[5] ; Yunlong,Tian ^[6] ; Yongjie,Du ^[7]

作者单位： School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, PR China. Electronic address: ye.tao@qust.edu.cn. ^[1] School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, PR China. Electronic address: liujiawang@mails.qust.edu.cn. ^[2] School of Information Science and Technology, Qingdao University of Science and Technology, Qingdao 266061, PR China. Electronic address: 2579356425@qq.com. ^[3] School of Reliability and Systems Engineering, Beihang University, Beijing 100191, PR China. Electronic address: liumeng518@buaa.edu.cn. ^[4] Beijing Research Institute of Automation for Machinery Industry Co., Ltd., Beijing 100000, PR China. Electronic address: 13121990213@163.com. ^[5] National Engineering Research Center of Digital Home Networking, Qingdao 266000, PR China. Electronic address: tianyl@haier.com. ^[6] National Engineering Research Center of Digital Home Networking, Qingdao 266000, PR China. Electronic address: tcldu@163.com. ^[7]

关键词 Compress corpus Denoising diffusion probabilistic models Limited target speaker corpus Multi-level prosody modeling Text-to-speech

医学主题词人类(Humans);言语(Speech);算法(Algorithms)

DOI 10.1016/j.neunet.2025.107432

PMID 40249999

发布时间 2025-05-31

翻译满意度评价：

准确一般字义偏差语意偏离译文作用小提交