现代电子技术2017，Vol.40Issue(17)：60-63,4.DOI:10.16652/j.issn.1004-373x.2017.17.015
基于广义回归神经网络的面罩语音矫正研究
Research on mask speech correction based on generalized regression neural network
摘要
Abstract
In order to improve the clarity and intelligibility of mask speech, a mask speech correction method based on generalized regression neural network(GRNN)for nonlinear modeling of line spectrum pair(LSP)parameters is pro-posed. The LSP parameters of normal speech and mask speech are extracted respectively,and then used to train GRNN to obtain the correction model. The LSP parameters of mask speech are modified based on the correction model,and its results are used as parameters for new speech synthesis. The experimental results show that the correction model trained by GRNN can adjust the LSP parameters of the mask speech effectively,and recover the spectral distribution of the mask speech to a certain extent.关键词
面罩语音/线谱对/广义回归神经网络/语音合成Key words
mask speech/LSP/GRNN/speech synthesis分类
信息技术与安全科学引用本文复制引用
王霞,刘婕,王光艳,王蒙军..基于广义回归神经网络的面罩语音矫正研究[J].现代电子技术,2017,40(17):60-63,4.基金项目
天津市自然科学基金重点项目(14JCZDJC32600) （14JCZDJC32600）
