桂林电子科技大学学报2016，Vol.36Issue(2)：118-122,5.
深度信念网络的Bottleneck特征提取方法
A Bottleneck feature extraction method based on deep belief network
摘要
Abstract
In order to improve the speech recognition rate,a Bottleneck feature extraction method based on deep belief net-work is proposed.The unsupervised pre-training stacking restricted Boltzmann machine is used to obtain network initializa-tion parameters by using the contrastive divergence algorithm.And then the back propagation algorithm is adopted,the frame level cross entropy is maximized as the training criterion,the inverse iteration is used to fine tune the network parame-ters.The context dependent triphone model is adopted to get the better features.The phone error rate is used to evaluate the performance of the system.Experimental results show that the Bottleneck feature is better than the traditional features.关键词
连续语音识别/深度信念网络/Bottleneck特征/音素错误率Key words
continuous speech recognition/deep belief network/Bottleneck feature/PER分类
信息技术与安全科学引用本文复制引用
谈建慧,景新幸,杨海燕..深度信念网络的Bottleneck特征提取方法[J].桂林电子科技大学学报,2016,36(2):118-122,5.基金项目
广西自然科学基金(2012GXNSFAA053221) （2012GXNSFAA053221）
广西千亿元产业产学研用合作项目(信科院0618) （信科院0618）
