基于ADSABC算法优化WNN的语音识别研究

王民; 许娟; 要趁红; 赵渊

doi:10.3788/YJYXS20183307.0615

您当前的位置：

首页 >

文章列表页 >

基于ADSABC算法优化WNN的语音识别研究

图像处理 | 更新时间：2020-07-06

- 基于ADSABC算法优化WNN的语音识别研究
- WNN speech recognition based on ADSABC algorithm
- 液晶与显示 2018年33卷第7期页码：615-623
- 作者机构：
  
  西安建筑科技大学信息与控制工程学院, 陕西西安 710055
- 作者简介：
  
  [ "王民(1959-), 男, 江苏常州人, 教授, 硕士生导师, 西安建筑科技大学通信与信息工程系主任, 电子信息工程教研室主任, 长期从事智能信息处理方面的研究工作。E-mail:wangmin1329@163.com" ]
  [ "许娟(1991-), 女, 陕西渭南人, 硕士研究生, 主要研究智能信息处理相关技术。E-mail:649011325@qq.com" ]
- 基金信息：
  
  住房城乡建设部科学技术项目计划(2016-R2-045);陕西省教育厅专项基金(2013JK1081);陕西省科学技术研究发展计划项目(No.CXY1122（2）);陕西省自然科学基金青年基金(2013JQ8003);Housing and Urbsn Ministry of Science project(2016-R2-045);Shaanxi Provincial Department of Education special fund(2013JK1081);Shaanxi Province Science and Technology Research and Development Project(CXY1122(2));Shaanxi Provincial Natural Science Foundation Youth Fund(2013JQ8003)
- DOI：10.3788/YJYXS20183307.0615
  中图分类号： TN912.3
- 收稿日期：2018-03-08，
  
  录用日期：2018-4-11，
  
  纸质出版日期：2018-07
- 稿件说明：
移动端阅览
王民, 许娟, 要趁红, 等. 基于ADSABC算法优化WNN的语音识别研究[J]. 液晶与显示, 2018,33(7):615-623.

Min WANG, Juan XU, Chen-hong YAO, et al. WNN speech recognition based on ADSABC algorithm[J]. Chinese journal of liquid crystals and displays, 2018, 33(7): 615-623.
王民, 许娟, 要趁红, 等. 基于ADSABC算法优化WNN的语音识别研究[J]. 液晶与显示, 2018,33(7):615-623. DOI： 10.3788/YJYXS20183307.0615.

Min WANG, Juan XU, Chen-hong YAO, et al. WNN speech recognition based on ADSABC algorithm[J]. Chinese journal of liquid crystals and displays, 2018, 33(7): 615-623. DOI： 10.3788/YJYXS20183307.0615.

摘要

小波神经网络（WNN）具有高度的非线性映射功能及强大的自适应能力，但是WNN算法存在易陷入局部极小值，收敛速度慢。而人工蜂群算法（ABC）具有很强的全局搜索能力及较快的收敛速度。两者优势互补，已结合应用于语音识别中。本文对ABC算法做出改进，在采蜜蜂和观察蜂阶段各提出一个新的解搜索方程，采取自适应的双搜索方式（Adaptive Double Search）求解，从而提高算法的收敛速度和收敛精度。并将其和WNN算法进行结合，组成一种训练神经网络的新算法ADSABC-WNN，该算法既能克服WNN算法的缺点，又能保存双方的优点。实验结果表明，与传统ABC算法优化小波神经网络相比，识别率提高均有所提高，其中在词汇量为50时识别率提高了4.51%。将实验结果与其他方法优化的小波神经网络模型进行比较，在噪声环境下，该混合模型可以有效地减少识别时间，而且可以明显提高网络的训练速度和语音识别的识别率。

Abstract

Wavelet neural network(WNN) has a highly nonlinear mapping function and a strong adaptive ability

but the WNN algorithm tends to fall into local minimum and converges slowly. The artificial bee colony algorithm (ABC) has a strong global search ability and faster convergence rate. The two algorithms complement each other and have been applied to voice recognition. In this paper

ABC algorithm is improved. A new solution search equation is proposed in the bee mining and the observation bee. Adaptive Double Search is used to solve the problem

so as to improve the convergence speed and convergence accuracy. And we combined with WNN algorithm to form a new algorithm ADSABC-WNN which can not only overcome the shortcomings of WNN algorithm but also save the advantages of both. The experimental results show that compared with the traditional ABC algorithm

the recognition rate improves

and the recognition rate increases by 4.51% when the vocabulary size is 50. Compared with the wavelet neural network model optimized by other methods

this hybrid model can effectively reduce the recognition time under the noise environment

and can obviously improve the training speed of network and the recognition rate of speech recognition.

关键词

Keywords

references

赵力.语音信号处理[M].北京:机械工业出版社, 2003.

ZHAO L. Speech Signal Processing[M]. Beijing:China Machine Press, 2003. (in Chinese)

JUANGB H, CHEN T. The past, present, and future of speech processing[J]. IEEE Signal Processing Magazine, 1998, 15(3):24-48.

UHRIGR E. Application of artificial neural networks in industrial technology[C]// Proceedings of the IEEE International Conference on Industrial Technology . Guangzhou, China: IEEE, 1994: 73-77.

ZHOUZ H, CHEN S F, CHEN Z Q. A statistics based approach for extracting priority rules from trained neural networks[C] // Proceeding of The IEEE-INNS-ENNS International Joint Conference on Neural Networks . Como, Italy: IEEE, 2000, 3: 401-406.

宋弘.小波神经网络在语音识别系统中的应用[J].微电子学与计算机, 2010, 27(4):121-124, 128.

SONG H. Application of wavelet neural network in speech recognition system[J]. Microelectronics & Computer, 2010, 27(4):121-124, 128. (in Chinese)

江铭炎, 袁东风.人工蜂群算法及其应用[M].北京:科学出版社, 2014:58.

JIANGM Y, YUAN D F. Artificial Bee Colony Algorithm and its Application[M]. Beijing:Science Press, 2014:58. (in Chinese)

MEISSNER M, SCHMUKER M, SCHNEIDER G. Optimized particle swarm optimization (OPSO) and its application to artificial neural network training[J]. BMC Bioinformatics, 2006, 7:125.

ABU-MOUTI F S, EL-HAWARY M E. Optimal distributed generation allocation and sizing in distribution systems via artificial bee colony algorithm[J]. IEEE Transactions on Power Delivery, 2011, 26(4):2090-2101.

EPSONB. The arcitecture of BCU[C]// IEEE Communications Magazine . 2009.

李卫华, 徐涛, 李小梨.基于人工蜂群的BP神经网络算法[J].计算机系统应用, 2012, 21(5):195-198.

LI W H, XU T, LI X L. BP neural network based on artificial bee colony algorithm[J]. Computer Systems & Applications, 2012, 21(5):195-198. (in Chinese)

黄玲玲, 刘三阳, 高卫峰.具有人工蜂群搜索策略的差分进化算法[J].控制与决策, 2012, 27(11):1644-1648.

HUANG L L, LIU S Y, GAO W F. Differential evolution with the search strategy of artificial bee colony algorithm[J]. Control and Decision, 2012, 27(11):1644-1648. (in Chinese)

高卫峰, 刘三阳, 焦合华, 等.引入人工蜂群搜索算子的粒子群算法[J].控制与决策, 2012, 27(6):833-838.

GAO W F, LIU S Y, JIAO H H, et al. Particle swarm optimization with search operator of artificial bee colony algorithm[J]. Control and Decision, 2012, 27(6):833-838. (in Chinese)

ALAMM S, KABIR M W U, ISLAM M M. Self-adaptation of mutation step size in artificial bee colony algorithm for continuous function optimization[C]// Proceedings of 13th International Conference on Computer and Information Technology . Dhaka, Bangladesh: IEEE, 2010: 69-74.

韩志艳, 王健, 伦淑娴.基于遗传小波神经网络的语音识别分类器设计[J].计算机科学, 2010, 37(11):243-246.

HAN Z Y, WANG J, LUN S X. Design of speech recognition classifier based on genetic wavelet neural network[J]. Computer Science, 2010, 37(11):243-246. (in Chinese)

张冬至, 胡国清.基于遗传优化小波神经网络逆模型的油水测量[J].光学精密工程, 2011, 19(7):1588-1595.

ZHANGD Z, HU G Q. Measurement of oil-water flow based on inverse model of wavelet neural network with genetic optimization[J]. Optics and Precision Engineering, 2011, 19(7):1588-1595. (in Chinese)

黄文明, 徐双双, 邓珍荣, 等.改进人工蜂群算法优化RBF神经网络的短时交通流预测[J].计算机工程与科学, 2016, 38(4):713-719.

HUANG W M, XU S S, DENG Z R, et al. Short-term traffic flow prediction of optimized RBF neural networks based on the modified ABC algorithm[J]. Computer Engineering and Science, 2016, 38(4):713-719. (in Chinese)

张新艳.人工蜂群算法的改进及应用[J].宜宾学院学报, 2016, 16(6):41-45.

ZHANG X Y. The improvement and application of artificial bee colony algorithm[J]. Journal of Yibin University, 2016, 16(6):41-45. (in Chinese)

单泽彪, 石要武, 刘小松, 等.应用人工蜂群算法的动态波达方向跟踪[J].光学精密工程, 2015, 23(3):838-845.

SHANZ B, SHI Y W, LIU X S, et al. DOA tracking of moving targets by artificial bee colony algorithm[J]. Optics and Precision Engineering, 2015, 23(3):838-845. (in Chinese)

赵群.基于ACO优化小波神经网络的语音识别[J].大庆师范学院学报, 2014, 34(6):1-4.

ZHAO Q. Study on speech recognition based on ACO optimized wavelet neural network[J]. Journal of Daqing Normal University, 2014, 34(6):1-4. (in Chinese)

斯芸芸, 徐道连, 周卓然.基于遗传算法和小波神经网络的语音识别研究[J].微型机与应用, 2011, 30(16):68-71.

SI Y Y, XU D L, ZHOU Z R. Research of speech recognition based on genetic algorithm and wavelet neural network[J]. Microcomputer & its Applications, 2011, 30(16):68-71. (in Chinese)

MIAOY J, METZE F. Improving low-resource CD-DNN-HMM using dropout and multilingual DNN training[C]// Proceedings of the 14th Annual Conference of the International Speech Communication Association (INTERSPEECH) . Lyon, France: INTERSPEECH, 2013: 2237-2241.

MIAOY J, METZE F, RAWAT S. Deep maxout networks for low-resource speech recognition[C]// Proceedings of 2013 IEEE Workshop on Automatic Speech Recognition and Understanding ( ASRU ). Olomouc, Czech Republic: IEEE, 2013: 398-403.

张舸, 张鹏远, 潘接林, 等.基于递归神经网络的语音识别快速解码算法[J].电子与信息学报, 2017, 39(4):930-937.

ZHANG G, ZHANG P Y, PAN J L, et al. Fast decoding algorithm for automatic speech recognition based on recurrent neural networks[J]. Journal of Electronics & Information Technology, 2017, 39(4):930-937. (in Chinese)

秦楚雄, 张连海.基于DNN的低资源语音识别特征提取技术[J].自动化学报, 2017, 43(7):1208-1219.

QIN C X, ZHANG L H. Deep neural network based feature extraction for low-resource speech recognition[J]. Acta Automatica Sinica, 2017, 43(7):1208-1219. (in Chinese)

张晴晴, 刘勇, 潘接林, 等.基于卷积神经网络的连续语音识别[J].工程科学学报, 2015, 37(9):1212-1217.

ZHANG Q Q, LIU Y, PAN J L, et al. Continuous speech recognition by convolutional neural networks[J]. Chinese Journal of Engineering, 2015, 37(9):1212-1217. (in Chinese)

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据