[1]张 舒,王成强,李 想,等.生产环境下声纹识别系统的设计与实现[J].南京师范大学学报(工程技术版),2018,18(04):086.[doi:10.3969/j.issn.1672-1292.2018.04.013]
　Zhang Shu,Wang Chengqiang,Li Xiang,et al.The Design and Implement of Voiceprint Recognition Systemin the Production Environment[J].Journal of Nanjing Normal University(Engineering and Technology),2018,18(04):086.[doi:10.3969/j.issn.1672-1292.2018.04.013]
点击复制

生产环境下声纹识别系统的设计与实现
分享到：

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
18卷
期数:
2018年04期
页码:
086
栏目:
计算机工程
出版日期:
2018-12-30

文章信息/Info

Title:
The Design and Implement of Voiceprint Recognition Systemin the Production Environment
文章编号:
1672-1292(2018)04-0086-07
作者:
张 舒1; 王成强1; 李 想2; 李 慧2
(1.淮海工学院商学院,江苏 连云港 222005)(2.淮海工学院计算机工程学院,江苏 连云港 222005)
Author(s):
Zhang Shu1; Wang Chengqiang1; Li Xiang2; Li Hui2
(1.Business School,Huaihai Institute of Technology,Lianyungang 222005,China)(2.School of Computer Science,Huaihai Institute of Technology,Lianyungang 222005,China)
关键词:
声纹识别; 原理; 产品; 架构设计
Keywords:
voiceprint recognition; principle; product; architecture design
分类号:
TP391
DOI:
10.3969/j.issn.1672-1292.2018.04.013
文献标志码:
A
摘要:
声纹识别是一种能根据待识别语音的声纹特征识别说话人的技术. 本文阐述了声纹识别系统的原理知识,介绍了声纹识别系统的体系架构,本系统采取分层结构,核心业务分解为业务层和实现层,多个层的多个功能模块被设计成独立的服务,从而提升了声纹识别系统的识别准确率,最后给出了系统在实际生产环境下的产品设计方案.
Abstract:
The voiceprint recognition is a kind of technology that can recognize the speaker according to the voiceprint characteristics of the voice to be recognized. The paper illustrates the principal knowledge of voiceprint recognition system,and introduces its system architecture. This system adopts a hierarchical structure and the core business layer is also divided into a business layer and implementation layer. Several functional modules of multiple layers are designed as independent services,thus improving the recognition efficiency of the voiceprint system. Finally,the product design scheme of the system under the actual production environment is given.

参考文献/References:

[1] 郑凯鹏,周萍,张上鑫,等. 基于倒谱分量的融合参数应用于声纹识别[J]. 微电子学与计算机,2017,34(8):29-32.ZHENG K P,ZHOU P,ZHANG S X,et al. Base on the fusion parameters of cepstrum components used in speaker recognition[J]. Microelectronics & computer,2017,34(8):29-32.(in Chinese)
[2]OMER A E. Joint MFCC-and-vector quantization based text-independent speaker recognition system[C]//International Conference on Communication,Control,Computing and Electronics Engineering. IEEE,2017:1-6.
[3]BOUSSAID L,HASSINE M. Arabic isolated word recognition system using hybrid feature extraction techniques and neural network[J]. International journal of speech technology,2018,21(1):29-37.
[4]DIXIT A,VIDWANS A,SHARMA P. Improved MFCC and LPC algorithm for bundelkhandi isolated digit speech recognition[C]//International Conference on Electrical,Electronics,and Optimization Techniques. IEEE,2016:3755-3759.
[5]AL-THAHAB O Q J. Speech recognition based Radon-Discrete Cosine Transforms by Delta Neural Network learning rule[C]//International Symposium on Fundamentals of Electrical Engineering. IEEE,2017:1-6.
[6]BANERJEE A,DUBEY A,MENON A,et al. Speaker recognition using deep belief networks[EB/OL]. [2018-11-23]. https://arxiv.org/ftp/arxiv/papers/1805/1805.08865.pdf.

备注/Memo

备注/Memo:
收稿日期:2018-04-18.
基金项目:连云港市科技计划项目(JC1608、CG1611)、江苏省“青蓝工程”培养对象、江苏省第五期“333高层次人才培养工程”、淮海工学院教学改革项目(XJG2017-2-5)、教育部协同育人项目(201702134005、201701028110)、连云港市“521高层次人才培养工程”(ZKK201604).
通讯联系人:张舒,讲师,研究方向:智能信息处理,数据采集与数据挖掘. E-mail:shufanzs@126.com
更新日期/Last Update: 2018-12-30