[1]林巧民,齐柱柱.基于 HMM 和 ANN 混合模型的语音情感识别研究[J].计算机技术与发展,2018,28(10):74-78.[doi:10.3969/ j. issn.1673-629X.2018.10.015]
　LIN Qiao-min,QI Zhu-zhu.Research on Speech Emotion Recognition Based on HMM and ANN Mixed Model[J].,2018,28(10):74-78.[doi:10.3969/ j. issn.1673-629X.2018.10.015]
点击复制

基于 HMM 和 ANN 混合模型的语音情感识别研究()
分享到：

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

卷:
28
期数:
2018年10期
页码:
74-78
栏目:
智能、算法、系统工程
出版日期:
2018-10-10

文章信息/Info

Title:
Research on Speech Emotion Recognition Based on HMM and ANN Mixed Model
文章编号:
1673-629X(2018)10-0074-05
作者:
林巧民1; 2; 齐柱柱1
1. 南京邮电大学 计算机学院,江苏 南京 210023; 2. 南京邮电大学 教育科学与技术学院,江苏 南京 210003
Author(s):
LIN Qiao-min1; 2; QI Zhu-zhu1
1. School of Computer Science,Nanjing University of Posts &Telecommunications,Nanjing 210023,China; 2. School of Educational Science and Technology,Nanjing University of Posts & Telecommunications,Nanjing 210003,China
关键词:
情感计算; 人工智能; 隐马尔可夫模型; 神经网络; 语音情感识别
Keywords:
emotion calculation; artificial intelligence; hidden Markov model; neural network; speech emotion recognition
分类号:
TN912.34
DOI:
10.3969/ j. issn.1673-629X.2018.10.015
文献标志码:
A
摘要:
随着情感计算成为人工智能的一个重要方向,语音情感识别作为情感计算的一个重要部分,已经逐渐成为模式识别领域研究的热点之一。 随着研究的不断深入,单独使用某一种模式识别时效果并不理想。 为了提高识别率,提出了一种将隐马尔可夫模型(HMM)和径向基函数神经网络(RBF)相结合的方法。 这种方法对不同情感状态分别设计 HMM 模型,经过维特比(Viterbi)算法得到最优状态序列,然后对得到的状态序列进行时间规整,以便生成等维的特征矢量,将其作为 RBF 模型的输入进行语音情感识别,最后的识别结果由 RBF 模型给出。 实验结果表明,与孤立 HMM 相比,该方法在识别率上有较大的提高。
Abstract:
As emotion calculation becomes an important direction of artificial intelligence,speech emotion recognition,as an important part of emotional computing,has gradually become one of the hot spots in the field of pattern recognition. With the development of the research,the recognition effect is not very ideal when just used a single model to classify speech emotional status. In order to improve recognition rate,we propose a method in combination of Hidden Markov Model (HMM) and radial basis function neural network (RBF).This method designs HMM models for different emotional states,then gets the best sequence of emotional speech signal by Viterbi algorithm. Then,the feature parameters of the same state are structured as uniform dimension by the method of spatial orthogonal basis function expansion,which is used as the input of RBF for recognition of speech emotional states. Finally,the final results are given by RBF.The experiment shows that the proposed method has better recognition rate than isolated HMM.

相似文献/References:

[1]张春飞 李万龙 郑山红.Agent技术在智能教学系统中的应用与研究[J].计算机技术与发展,2009,(05):30.
　ZHANG Chun-fei,LI Wan-long,ZHENG Shan-hong.Application and Research of Agent Technology in Intelligent Tutoring System[J].,2009,(10):30.
[2]黄长专 王彪 杨忠.图像分割方法研究[J].计算机技术与发展,2009,(06):76.
　HUANG Chang-zhuan,WANG Biao,YANG Zhong.A Study on Image Segmentation Techniques[J].,2009,(10):76.
[3]张春飞 郑山红 李万龙.基于Agent技术的医疗信息整合研究[J].计算机技术与发展,2009,(10):250.
　ZHANG Chun-fei,ZHENG Shan-hong,LI Wan-long.Research on Integration of Healthcare Enterprise Based on Agent Technology[J].,2009,(10):250.
[4]杜秀全 程家兴.博弈算法在黑白棋中的应用[J].计算机技术与发展,2007,(01):216.
　DU Xiu-quan,CHENG Jia-xing.Game- Playing Algorithm in Black and White Chess Application[J].,2007,(10):216.
[5]孙锦 冯勤超.创造力支持系统[J].计算机技术与发展,2007,(03):138.
　SUN Jin,FENG Qin-chao.Creativity Support System[J].,2007,(10):138.
[6]吉张媛 何华灿.模糊Prolog系统[J].计算机技术与发展,2006,(02):123.
　JI Zhang-yuan,HE Hua-can.Fuzzy Prolog System[J].,2006,(10):123.
[7]赵鹏 何留进 孙凯 方薇[].基于情感计算的网络中文信息分析技术[J].计算机技术与发展,2010,(11):146.
　ZHAO Peng,HE Liu-jin,SUN Kai,et al.Analyzing Technologies of Internet Chinese Information Based on Affective Computing[J].,2010,(10):146.
[8]冯满堂 马青玉 王瑞杰[].基于人脸表情识别的智能网络教学系统研究[J].计算机技术与发展,2011,(06):193.
　FENG Man-tang,MA Qing-yu,WANG Rui-jie.Facial Expressing Recognition Based Research on Intelligent Network Teaching System[J].,2011,(10):193.
[9]丁莹.研究人工智能的一条新途径[J].计算机技术与发展,2012,(03):133.
　DING Ying.A New Avenue of Researching on AI[J].,2012,(10):133.
[10]张代远[].一类新型改进的广义蚁群优化算法[J].计算机技术与发展,2012,(06):39.
　ZHANG Dai-yuan.A New Improved Generalized Ant Colony Optimization Algorithm[J].,2012,(10):39.

更新日期/Last Update: 2018-10-10