中国科学院大学学报2017，Vol.34Issue(5)：633-639,7.DOI:10.7523/j.issn.2095-6134.2017.05.014
深度神经网络自适应中基于身份认证向量的归一化方法
Investigation of normalization methods in speaker adaptation of deep neural network using i-vector
摘要
Abstract
The deep neural network (DNN) was a remarkable modeling technology for speech recognition in recent years and its performance was significantly better than that of the Gaussian mixture model,which was the mainstream modeling technology in speech recognition before.However,commendable adaptation of DNN has not been solved yet.In this work,we use the identity vector (i-vector) to adapt a deep neural network by putting i-vector and the regular speech features together as the input of DNN for both training and testing.Then we focus on the normalization method of i-vector using a new max-min linear normalization method.We get a 5.10％ relative decrease in word error rate over the traditional length normalization method.关键词
身份认证向量/深度神经网络/说话人自适应/归一化Key words
identity vector/deep neural network/speaker adaptation/normalization分类
信息技术与安全科学引用本文复制引用
杨建斌,张卫强,刘加..深度神经网络自适应中基于身份认证向量的归一化方法[J].中国科学院大学学报,2017,34(5):633-639,7.基金项目
国家自然科学基金(61370034,61403224)资助 （61370034,61403224）
