|Table of Contents|

Shuffled Frog-leaping Algorithm Based Neural Network and Its Application in Speech Emotion Recognition

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2011年05期
Page:
659-663
Research Field:
Publishing date:

Info

Title:
Shuffled Frog-leaping Algorithm Based Neural Network and Its Application in Speech Emotion Recognition
Author(s):
YU Hua12 HUANG Cheng-wei1ZHANG Xiao-dan1 JIN Yun1ZHAO Li1
1. Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education,Southeast University, Nanjing 210096,China; 2. School of Electronics and Information Engineering,Nanjing College of Information Technology,Nanjing 210013,China
Keywords:
shuffled frog-leaping algorithm neural networks speech emotion recognition recognition ratio
PACS:
391. 42
DOI:
-
Abstract:
The shuffled frog-leaping algorithm( SFLA) is applied to the speech emotion recognition in neural network training. The freatures of the six speech emotions are extracted and recognized. The changes of harmonics-to-noise ratio( HNR) features with different emotions are studied. The random initial data trained by the SFLA is used to optimize the connection weights and thresholds of the neural network,and the network can converge fast. The recognition capability of the BP,RBF and SFLA neural networks are compared experimentally. The results show that the recognition ratio of the SFLA neural network is 4. 7% better than that of BP neural network and 4. 3% better than that of the RBF neural network.

References:

[1] Picard R W. Affective Computing[M]. Cambridge: MIT Press, 1997.
[2] Picard R W. Toward computers that recognize and respond to user emotion[J]. IBM Technical Journal, 2000, 38( 2) : 705-719.
[3] 赵力,将春辉,邹采荣,等. 语音信号中的情感特征 分析和识别的研究[J]. 通信学报, 2000, 21( 10) : 18 -25.
[4] 金赟,赵艳,黄程韦,等. 耳语音情感数据库的设计 与建立[J]. 声学技术, 2010, 29( 1) : 63-68.
[5] 袁家斌,浦海晨. 基于遗传算法优化的神经网络电 子邮件信息分类器的研究[J]. 南京理工大学学报, 2008, 32( 1) : 78-82.
[6] 秦华旺,戴跃伟,王执铨. 一种基于改进神经网络的 入侵容忍系统模型[J]. 南京理工大学学报, 2008, 32( 5) : 628-631.
[7] 赵英,催福义,郭亮,等. 基于BP 神经网络的天津于 桥水库CODMn 预测研究[J]. 南京理工大学学报, 2008, 32( 3) : 376-380.
[8] 陈得宝,赵春霞. 基于改进GA 的WRBF 神经网络 设计与应用[J]. 南京理工大学学报,2007,31( 3) : 370-374.
[9] 朱红,陈清华,刘国岁. 高速神经网络HS-K-WTA-2 的研究[J]. 南京理工大学学报2007,31 ( 1 ) : 89 -91.
[10] 何春梅,叶有培,徐蔚鸿. 训练模式对的摄动对单体 模糊神经网络的影响[J]. 南京理工大学学报, 2009, 33( 1) : 12-15.
[11] Eusuff M M,Lansey K E. Shuffled frog-leaping algorithm: A memetic meta-heuristic for discrete optimization[J]. Engineering Optimization,2006,38 ( 2) : 129-154.
[12] Yang Junan,Zhuang Zhenquan. Research of quantum genetic algorithm and its application in blind source separation[J]. Journal of Electronics ( China) ,2003, 20( 1) : 62-68.
[13] 黄程韦,金赟,赵力,等. 基于特征空间分解与融合 的语音情感识别[J]. 信号处理,2010,26 ( 6) : 835 -842.
[14] 黄程韦,金赟,赵艳,等. 实用语音情感数据库的设 计与研究[J]. 声学技术, 2010, 29( 1) : 63-68.
[15] Huang Chengwei, Jin Yun,Zhao Yan, et al. Recognition of practical emotion from elicited speech[A]. Proceedings of ICISE[C]. Nanjing,China: IEEE,2009: 639 -642.
[16] Huang Chengwei, Jin Yun,Zhao Yan,et al. Speech emotion recognition based on re-composition of two-class classifiers[A]. Proceedings of ACII[C]. Amsterdam, Netherland: IEEE, 2009: 1-3.
[17] Tato R,Santos R,Kompe R,et al. Emotion space improves emotion recognition[A]. Proc of ICSLP[C]. Denver,Colorado IEEE, 2009: 2029-2032.
[18] Eiji Yumoto,Wilbur J G. Harmonics-to-noise ratio as an index of the degree of hoarseness[J]. Journal of Acoustic Society of America, 1982, 71( 6) : 1544-1550.

Memo

Memo:
-
Last Update: 2012-10-24