[1]刘俊坤,李燕萍,凌云志.基于AutoEncoder DBN－VQ 的说话人识别系统[J].计算机技术与发展,2018,28(02):45-49.[doi:10.3969/j.issn.1673－629X.2018.02.]
　LIU Junkun,LI Yanping,LING Yunzhi.Speaker Ｒecognition System Based on AutoEncoder Deep Belief Network and Vector Quantization[J].,2018,28(02):45-49.[doi:10.3969/j.issn.1673－629X.2018.02.]
点击复制

基于AutoEncoder DBN－VQ 的说话人识别系统()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年02期
页码:
45-49
栏目:
智能、算法、系统工程
出版日期:
2018-02-10

文章信息/Info

Title:
Speaker Ｒecognition System Based on AutoEncoder Deep Belief Network and Vector Quantization
文章编号:
1673－629X(2018)02－0045－05
作者:
刘俊坤; 李燕萍; 凌云志
南京邮电大学 通信与信息工程学院，江苏 南京 210003
Author(s):
LIU Jun－kun; LI Yan－ping; LING Yun－zhi
School of Communications ＆ Information Engineering，Nanjing University of Posts and Telecommunications，Nanjing 210003，China
关键词:
说话人识别; 深度置信网络; 自动编码器; 矢量量化
Keywords:
speaker recognition; deep belief network; AutoEncoder; vector quantization
分类号:
TP302
DOI:
10.3969/j.issn.1673－629X.2018.02.
文献标志码:
A
摘要:
基于矢量量化的说话人识别算法，通过描述说话人语音特征的不同分布进行说话人识别。在说话人数量较多，训练语音时长较短时，系统识别率不高。模型训练一般在纯净语音条件下进行，在实际有噪声环境下进行识别时，系统性能会急剧恶化。为改善系统识别性能，提出一种基于自动编码深度置信网络与矢量量化结合的说话人识别方法。该方法采用深度置信网络对说话人语音数据进行学习和挖掘，在语音时长较短时可以更好地捕获说话人的个性特征;同时采用自动编码器有去噪声的特点，构造自动编码深度置信网络，使网络模型可以对有噪语音数据进行有效地噪声过滤。实验结果证明，该方法在说话人训练语音时长有限时，以及对说话人有噪语音进行识别时，系统识别率都有很大提升。
Abstract:
The speaker recognition system using vector quantization works by describing the different characteristics of the speaker’s speech features．When the number of speakers are large and training speech length is short，the recognition rate of the system is not high．For the model is usually trained under the condition of pure speech，the performance of the system will be poor when it is used in the actual environment．In order to improve the recognition performance of the system，we propose a method of speech recognition based on the combination of Au-
toEncoder deep belief network and vector quantization．It adopts the deep belief network to model and learn for speech data，so speaker’s personality characteristics in speech can be better captured when the speech length is short．In the meantime，it structures AutoEncoder deep belief network，which is effective on noise filtering for noisy speech data．The experiment show that the proposed method can improve the recognition rate greatly when there is only a small amount of speaker training data and speech is noisy．

相似文献/References:

[1]吴庆棋 林江云.基于聚类优化GMM提高说话人识别性能的研究[J].计算机技术与发展,2009,(04):35.
　WU Qing-qi,LIN Jiang-yun.A Study on GMM Optimization with Clustering for Improving Speaker Recognition[J].,2009,(02):35.
[2]但志平 郑胜.最小二乘向量机在说话人识别中的应用[J].计算机技术与发展,2007,(05):30.
　DAN Zhi-ping,ZHENG Sheng.Application of LS - SVM in Speaker Recognition[J].,2007,(02):30.
[3]张华 裘雪红.说话人识别中LPCCEP倒谱分量的相对重要性[J].计算机技术与发展,2006,(04):67.
　ZHANG Hua,QIU Xue-hong.On the Importance of Components of LPCCEP in Speaker Recognition[J].,2006,(02):67.
[4]于云,周伟栋. 基于稀疏表示的鲁棒性说话人识别系统[J].计算机技术与发展,2015,25(12):41.
　YU Yun,ZHOU Wei-dong. Robust Speaker Recognition System Based on Sparse Representation[J].,2015,25(02):41.
[5]李燕,陶定元,林乐. 基于DTW模型补偿的伪装语音说话人识别研究[J].计算机技术与发展,2017,27(01):93.
　LI Yan-ping,TAO Ding-yuan,LIN Le. Study on Electronic Disguised Voice Speaker Recognition Based on DTW Model Compensation[J].,2017,27(02):93.
[6]李姗,徐珑婷. 基于语谱图提取瓶颈特征的情感识别算法研究[J].计算机技术与发展,2017,27(05):82.
　LI Shan,XU Long-ting. Research on Emotion Recognition Algorithm Based on Spectrogram Feature Extraction of Bottleneck Feature[J].,2017,27(02):82.
[7]林舒都,邵曦.基于i-vector和深度学习的说话人识别[J].计算机技术与发展,2017,27(06):66.
　LIN Shu-du,SHAO Xi. Speaker Recognition with i-vector and Deep Learning[J].,2017,27(02):66.
[8]邱东,刘德雨.基于模糊深度学习网络的行人检测方法[J].计算机技术与发展,2018,28(10):22.[doi:10.3969/ j. issn.1673-629X.2018.10.005]
　QIU Dong,LIU De-yu.A Pedestrian Detection Method Based on Fuzzy Depth Learning Network[J].,2018,28(02):22.[doi:10.3969/ j. issn.1673-629X.2018.10.005]
[9]强 晗,郭亚兰,田礼明.基于深度置信网络的恶意代码检测方法研究[J].计算机技术与发展,2019,29(07):93.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 019]
　QIANG Han,GUO Ya-lan,TIAN Li-ming.Research on Malicious Code Detection Based on Deep Belief Networks[J].,2019,29(02):93.[doi:10. 3969 / j. issn. 1673-629X. 2019. 07. 019]
[10]单新文,李 萌,陶晔波,等.基于深度置信网络的用电量预测方法研究[J].计算机技术与发展,2021,31(增刊):177.[doi:10. 3969 / j. issn. 1673-629X. 2021. S. 036]
　SHAN Xin-wen,LI Meng,TAO Ye-bo,et al.Research on Electricity Consumption Forecasting Method Based on Deep Belief Network[J].,2021,31(02):177.[doi:10. 3969 / j. issn. 1673-629X. 2021. S. 036]

更新日期/Last Update: 2018-03-26