删除或更新信息，请邮件至freekaoyan#163.com(#换成@)

连续音素的改进深信度网络的识别算法*

本站小编 Free考研考试/2022-01-02
-->
阴法明,赵 焱,赵力.连续音素的改进深信度网络的识别算法*[J].,2019,38(1):39-44
连续音素的改进深信度网络的识别算法*
Phoneme recognition based on deep belief network
投稿时间：2018-04-25修订日期：2018-12-29
中文摘要:
为提高连续语音识别中的音素识别率，提出一种基于改进并行回火训练的受限波尔兹曼机的音素识别算法。首先，算法利用经过等能量划分后的改进并行回火来训练受限玻尔兹曼机，接着将受限玻尔兹曼机堆叠组成一个深信度网络，从而作为深度神经网络预训练的基础模型，然后通过软最大化层输出，得到用于音素状态后验概率检测的深度神经网络。接着利用少量的标签数据，根据反向传播算法对网络权重进行微调。最后将所得后验概率作为隐马尔科夫的发射概率，然后利用Viterbi解码器实现音素识别。在TIMIT语料库上的实验表明，相比于传统的对比散度类算法提高了约4.5%。在不增加计算量的情况下比原始并行回火算法提高约1%。
英文摘要:
In order to improve the accuracy of phoneme recognition in continuous speech recognition, in this paper, a modified parallel tempering (PT)algorithm applied totrain the Restricted Boltzmann Machine is proposed. Firstly, Restricted Boltzmann Machine(RBM) is trained in light of Metropolis-Hasting for parallel tempering sampling, then stacking up RBMs to form a deep belief network（DBN） as the basis for DNN pre-training ,then by adding an output layer called “softmax” to the network, a deep neural network detecting the posterior probability of phoneme can be created. Subsequently, Backward Propagation algorithm is applied to fine-tune the weights discriminatively with less label data. Finally the sequence of the predicted probability distribution is fed into a standard Viterbi decoder. The experiments show that the proposed method has a better performance on the TIMIT dataset than traditional ways.Its recognition rate is higher 4.5%than CD，and 1% than original PT without more computation.
DOI：10.11684/j.issn.1000-310X.2019.01.006
中文关键词:并行回火受限玻尔兹曼机深信度网络音素识别
英文关键词:Parallel temperingRestricted Boltzmann MachineDeep belief networkPhoneme recognition
基金项目:国家自然科学基金项目 (61571106)
作者单位E-mail
阴法明南京信息职业技术学院yinfm@njcit.cn
赵 焱东南大学xie.yue@seu.edu.cn
赵力东南大学zhaoli@seu.edu.cn
摘要点击次数:1081
全文下载次数:852
查看全文查看/发表评论下载PDF阅读器
相关附件：查重结果修改说明1修改说明1修改说明2
关闭








PDF全文下载地址:

http://yysx.cnjournals.cn/ch/reader/create_pdf.aspx?file_no=18059&flag=1&journal_id=yysx&year_id=2019
相关话题/网络 东南大学 概率 信息 中文

Free考研考试FreeKaoYan.Com
欢迎来到Free考研考试，"为实现人生的Free而奋斗"

© 2020 FreeKaoYan! . All rights reserved.