[1]张潇丹,包永强,奚吉,等.基于MD-CM-SFLA神经网络的耳语音情感识别[J].东南大学学报(自然科学版),2012,42(5):848-853.[doi:10.3969/j.issn.1001-0505.2012.05.010]
 Zhang Xiaodan,Bao Yongqiang,Xi Ji,et al.Whispered speech emotion recognition based on MD-CM-SFLA neural network[J].Journal of Southeast University (Natural Science Edition),2012,42(5):848-853.[doi:10.3969/j.issn.1001-0505.2012.05.010]
点击复制

基于MD-CM-SFLA神经网络的耳语音情感识别()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
42
期数:
2012年第5期
页码:
848-853
栏目:
信息与通信工程
出版日期:
2012-09-20

文章信息/Info

Title:
Whispered speech emotion recognition based on MD-CM-SFLA neural network
作者:
张潇丹1 包永强2 奚吉1 赵力1 邹采荣1
1 东南大学水声信号处理教育部重点实验室, 南京 210096; 2 南京工程学院通信工程学院, 南京 211167
Author(s):
Zhang Xiaodan1 Bao Yongqiang2 Xi Ji1 Zhao Li1 Zou Cairong1
1 Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education, Southeast University, Nanjing 210096, China
2 School of Communication Engineering, Nanjing Institute Technology, Nanjing 211167, China
关键词:
混合蛙跳算法 分子动力学 云模型 Velocity-Verlet算法 BP神经网络 耳语音情感识别
Keywords:
shuffled frog leaping algorithm molecular dynamics cloud model Velocity-Verlet algorithm back propagation(BP)neural network whispered speech emotion recognition
分类号:
TN912
DOI:
10.3969/j.issn.1001-0505.2012.05.010
摘要:
提出了一种基于分子动力学模拟与云模型理论的改进混合蛙跳算法(MD-CM-SFLA).该算法将青蛙个体等效成分子,仅考虑最差个体和全局最优个体之间的吸引力,采用一种新的分子间作用力来代替两体间经典的Lennard-Jones作用力,并利用Velocity-Verlet算法和正态云发生器代替混合蛙跳算法的更新策略,有效平衡了种群的多样性和搜索的高效性.然后,将MD-CM-SFLA算法与BP神经网络相结合,设计出一种MD-CM-SFLA神经网络,并将其应用于耳语音情感识别中.耳语音情感识别结果表明,MD-CM-SFLA神经网络相对于BP神经网络具有明显的优势,在相同的测试条件下,其平均识别率较BP神经网络提高5.2%.由此表明,利用MD-CM-SFLA算法优化BP神经网络的参数,可以实现BP神经网络的快速收敛,获得较好的学习能力,从而为耳语音情感识别提供一种新思路.
Abstract:
A molecular dynamics simulation and cloud model theory based shuffled frog leaping algorithm(MD-CM-SFLA)is proposed. In this algorithm, an individual frog is equivalent to a molecular and only the attractive force between the worst individual and the global best individual is considered. A new intermolecular force instead of the classic two-body Lennard-Jones force is adopted, and the Velocity-Verlet algorithm and a normal cloud generator are substitued for the update strategy of the shuffled frog leaping algorithm(SFLA). The population diversity and the search efficiency are effectively balanced. Then, a MD-CM-SFLA neural network is proposed through combining the MD-CM-SFLA with back propagation(BP)neural network, and it is applied to the whispered speech emotion recognition. The experimental results of whispered speech emotion recognition indicate that compared with BP neural network, the MD-CM-SFLA neural network has obvious advantages. Under the same test conditions, the average recognition rate of the MD-CM-SFLA neural network is 5.2% higher than that of BP neural network. Therefore, utilizing MD-CM-SFLA algorithm to optimize the parameters of BP neural network can obtain fast convergence velocity and good learning ability, thus providing a new idea for whispered speech emotion recognition.

参考文献/References:

[1] Tao Zhi,Zhao Heming,Wu Di,et al.Speech enhancement based on modified mel masking model and speech absence probability in whispers [J].Acta Acustica,2009,34(4):370-377.
[2] 王敏,赵鹤鸣,张庆芳.基于瞬时频率估计和特征映射的汉语耳语音话者识别[J].数据采集与处理,2011,26(6):686-690
  Wang Min,Zhao Heming,Zhang Qingfang.Speaker identification with Chinese whispered speech based on instantaneous frequency estimation and feature mapping [J].Journal of Data Acquisition & Processing,2011,26(6):686-690.
[3] Wang Min,Zhao Heming.Whispered speaker identification based on multiband demodulation analysis and instantaneous frequency estimation [J].Acta Acustica,2010,35(4):471-476.
[4] 余华,黄程韦,张潇丹,等.混合蛙跳算法神经网络及其在语音情感识别中的应用[J].南京理工大学学报,2011,35(5):659-663.
  Yu Hua,Huang Chengwei,Zhang Xiaodan,et al.Shuffled frog-leaping algorithm based neural network and its application in speech emotion recognition [J].Journal of Nanjing University of Science and Technology,2011,35(5):659-663.(in Chinese)
[5] Alireza R V,Ali H M.Solving a bi-criteria permutation flow-shop problem using shuffled frog-leaping algorithm [J].Soft Computing,2008,12(5):435-452.
[6] Eusuff M M,Lansey K E.Shuffled frog-leaping algorithm:a mimetic meta-heuristic for discrete optimization [J].Engineering Optimization,2006,38(2):129-154.
[7] Alireza R V,Ali H M.A hybrid multi-objective shuffled frog-leaping algorithm for a mixed-model assembly line sequencing problem [J].Computers & Industrial Engineering,2007,53(4):642-666.
[8] Swope W C,Andersen H C,Berens P H,et al.A computer simulation method for the calculation of equilibrium constants for the formation of physical clusters of molecules:application to small water clusters [J].Journal of Chemical Physics,1982,76(1):637-649.
[9] 戴朝华,朱云芳,陈维荣,等.云遗传算法及其应用[J].电子学报,2007,35(7):1419-1424.
  Dai Chaohua,Zhu Yunfang,Chen Weirong,et al.Cloud model based genetic algorithm and its application [J].Acta Electronica Sinica,2007,35(7):1419-1424.(in Chinese)
[10] 徐星,李元香,姜大志,等.一种基于分子动理论的改进粒子群优化算法[J].系统仿真学报,2009,21(7):1904-1907.
  Xu Xing,Li Yuanxiang,Jiang Dazhi,et al.Improved particle swarm optimization algorithm based on theory of molecular motion [J].Journal of System Simulation,2009,21(7):1904-1907.(in Chinese)

相似文献/References:

[1]魏志勇,毕可东,陈云飞.石墨烯纳米带热导率的分子动力学模拟[J].东南大学学报(自然科学版),2010,40(2):306.[doi:10.3969/j.issn.1001-0505.2010.02.017]
 Wei Zhiyong,Bi Kedong,Chen Yunfei.Thermal conductivity of graphene nanoribbons simulated by molecular dynamics[J].Journal of Southeast University (Natural Science Edition),2010,40(5):306.[doi:10.3969/j.issn.1001-0505.2010.02.017]
[2]杨决宽,唐明兵,钱瑞明,等.晶格失配对超晶格法向导热系数影响的分子动力学模拟[J].东南大学学报(自然科学版),2006,36(3):427.[doi:10.3969/j.issn.1001-0505.2006.03.020]
 Yang Juekuan,Tang Mingbing,Qian Ruiming,et al.Molecular dynamics simulation of the influence of lattice mismatch on cross-plane superlattice thermal conductivity[J].Journal of Southeast University (Natural Science Edition),2006,36(5):427.[doi:10.3969/j.issn.1001-0505.2006.03.020]
[3]靳一,王继武,吴乐南.混合蛙跳算法优化的支持向量机EBPSK检测器[J].东南大学学报(自然科学版),2011,41(3):509.[doi:10.3969/j.issn.1001-0505.2011.03.015]
 Jin Yi,Wang Jiwu,Wu Lenan.EBPSK demodulator based on shuffled frog leaping optimized SVM[J].Journal of Southeast University (Natural Science Edition),2011,41(5):509.[doi:10.3969/j.issn.1001-0505.2011.03.015]
[4]毕可东,陈云飞,王玉娟,等.金刚石导热系数的各向同性分子动力学模拟[J].东南大学学报(自然科学版),2010,40(4):746.[doi:10.3969/j.issn.1001-0505.2010.04.016]
 Bi Kedong,Chen Yunfei,Wang Yujuan,et al.Homogeneous molecular dynamics simulation of thermal conductivity of diamond[J].Journal of Southeast University (Natural Science Edition),2010,40(5):746.[doi:10.3969/j.issn.1001-0505.2010.04.016]
[5]陈慧,陈云飞,陈敏华,等.填充氩后单壁碳纳米管的导热系数[J].东南大学学报(自然科学版),2006,36(3):416.[doi:10.3969/j.issn.1001-0505.2006.03.017]
 Chen Hui,Chen Yunfei,Chen Minhua,et al.Thermal conductivity of single-wall carbon nanotubes filled with argon[J].Journal of Southeast University (Natural Science Edition),2006,36(5):416.[doi:10.3969/j.issn.1001-0505.2006.03.017]
[6]毕可东,陈云飞,杨决宽,等.不同结构单壁碳纳米管热传导的分子动力学模拟[J].东南大学学报(自然科学版),2006,36(3):420.[doi:10.3969/j.issn.1001-0505.2006.03.018]
 Bi Kedong,Chen Yunfei,Yang Juekuan,et al.Molecular dynamics simulation of thermal conductivity of single-wall carbon nanotubes with different structures[J].Journal of Southeast University (Natural Science Edition),2006,36(5):420.[doi:10.3969/j.issn.1001-0505.2006.03.018]
[7]杨决宽,陈云飞,颜景平.超薄氩膜热传导的分子动力学模拟[J].东南大学学报(自然科学版),2003,33(3):303.[doi:10.3969/j.issn.1001-0505.2003.03.014]
 Yang Juekuan,Chen Yunfei,Yan Jingping.Molecular dynamics simulation of thermal conductivity of argon thin film[J].Journal of Southeast University (Natural Science Edition),2003,33(5):303.[doi:10.3969/j.issn.1001-0505.2003.03.014]
[8]陈慧,魏志勇,陈伟宇,等.掺杂硅纳米薄膜法向热导率的分子动力学模拟[J].东南大学学报(自然科学版),2017,47(3):490.[doi:10.3969/j.issn.1001-0505.2017.03.013]
 Chen Hui,Wei Zhiyong,et al.Molecular dynamics simulation of out-of-plane thermal conductivity of doped silicon nanofilms[J].Journal of Southeast University (Natural Science Edition),2017,47(5):490.[doi:10.3969/j.issn.1001-0505.2017.03.013]
[9]陈俊,殷小晶,张倩倩,等.沥青内金属离子的水污特征及组分扩散的分子动力学模拟[J].东南大学学报(自然科学版),2017,47(4):799.[doi:10.3969/j.issn.1001-0505.2017.04.026]
 Chen Jun,Yin Xiaojing,Zhang Qianqian,et al.Water quality degradation due to metal in asphalt and molecular dynamics simulation on SARA fraction diffusion[J].Journal of Southeast University (Natural Science Edition),2017,47(5):799.[doi:10.3969/j.issn.1001-0505.2017.04.026]

备注/Memo

备注/Memo:
作者简介: 张潇丹(1988—),女,博士生; 赵力(联系人),男,博士,教授,博士生导师,zhaoli@seu.edu.cn.
基金项目: 国家自然科学基金资助项目(60872073, 60975017,51075068)、教育部博士点基金资助项目(20110092130004)、江苏省高校自然科学基金资助项目(10KJB510005).
引文格式: 张潇丹,包永强,奚吉,等.基于MD-CM-SFLA神经网络的耳语音情感识别[J].东南大学学报:自然科学版,2012,42(5):848-853. [doi:10.3969/j.issn.1001-0505.2012.05.010]
更新日期/Last Update: 2012-09-20