数据采集与处理2017，Vol.32Issue(5)：921-930,10.DOI:10.16337/j.1004-9037.2017.05.009
基于非负矩阵分解的语音深层低维特征提取方法
Nonnegative Matrix Factorization Based Deep Low-Dimensional Feature Extraction Approach for Speech Recognition
摘要
Abstract
As a type of deep neural network (DNN) based low-dimensional feature,bottleneck feature (BNF) has achieved great success in continuous speech recognition.However,the existing of bottleneck layer reduces the frame accuracy of output layer when training a bottleneck deep neural network (BNDNN),which in return has a bad impact on the performance of bottleneck feature.To solve this problem,a nonnegative matrix factorization based low-dimensional feature extraction approach using DNN without bottleneck layer is proposed in this paper.Specifically,semi-nonnegative matrix factorization and convex-nonnegative matrix factorization algorithms are applied to hidden-layer weights matrix to obtain a basis matrix as the new feature-layer weights matrix,and a new type of feature is extracted by forward passing input data without setting a bias vector in the new feature-layer.Experiments show that the feature has a relatively stable pattern around different tasks and network structures.For corpus with enough training data,the proposed features have almost the same recognition performance with conventional bottleneck feature.Under low-resource environment,the recognition accuracy of the new feature-tandem system outperforms both DNN hybrid system and bottleneck-tandem system obviously.关键词
连续语音识别/深层神经网络/半非负矩阵分解/凸非负矩阵分解/低维特征Key words
continuous speech recognition/deep neural network/semi-nonnegative matrix factorization/convex-nonnegative matrix factorization/low-dimensional features分类
信息技术与安全科学引用本文复制引用
秦楚雄,张连海..基于非负矩阵分解的语音深层低维特征提取方法[J].数据采集与处理,2017,32(5):921-930,10.基金项目
国家自然科学基金(61175017,61403415)资助项目. （61175017,61403415）
