维普中文期刊产品整合服务

Performance analysis of ASR system in hybrid DNN-HMM framework using a PWL euclidean activation function

查看全文 作　　者：Anirban [1]DUTTA;Gudmalwar [1]ASHISHKUMAR;Ch V Rama [1]RAO 高影响力作者 机构地区：[1]Department of Electronics and Communication Engineering,National Institute of Technology Meghalaya,Shillong 793003,India高影响力机构 出　　处：《Frontiers of Computer Science》索引2021年第15卷第4期,共11页高影响力期刊 基　　金：This work was an outcome of the R&D work undertaken project under the Visvesvaraya PhD Scheme of Ministry of Electronics&Information Technology;Government of India,being implemented by Digital India Corporation. 摘　　要：Automatic Speech Recognition(ASR)is the process of mapping an acoustic speech signal into a human readable text format.Traditional systems exploit the Acoustic Component of ASR using the Gaussian Mixture Model-Hidden Markov Model(GMM-HMM)approach.Deep NeuralNetwork(DNN)opens up new possibilities to overcome the shortcomings of conventional statistical algorithms.Recent studies modeled the acoustic component of ASR system using DNN in the so called hybrid DNN-HMM approach.In the context of activation functions used to model the non-linearity in DNN,Rectified Linear Units(ReLU)and maxout units are mostly used in ASR systems.This paper concentrates on the acoustic component of a hybrid DNN-HMM system by proposing an efficient activation function for the DNN network.Inspired by previous works,euclidean norm activation function is proposed to model the non-linearity of the DNN network.Such non-linearity is shown to belong to the family of Piecewise Linear(PWL)functions having distinct features.These functions can capture deep hierarchical features of the pattern.The relevance of the proposal is examined in depth both theoretically and experimentally.The performance of the developed ASR system is evaluated in terms of Phone Error Rate(PER)using TIMIT database.Experimental results achieve a relative increase in performance by using the proposed function over conventional activation functions. 关 键 词：deep learning euclidean piecewise linear speech recognition activation function
相关文献

参考文献(55)

耦合文献(27)

网站首页 | 关于我们 | 联系我们 | 产品服务 | 客服中心 | 广告服务 | 版权声明 | 网站联盟 | 友情链接 | 售卡网点

版权所有© 渝B2-20050021-1　渝公网安备 50019002500403号　违法和不良信息举报中心

互联网出版许可证 新出网证(渝)字10号 全国400电话 - 免长途话费