COMPARISON BETWEEN GMM-SVM SEQUENCE KERNEL AND GMM: APPLICATION TO SPEECH EMOTION RECOGNITION

被引:0
|
作者
Trabelsi, I. [1 ]
Ben Ayed, D. [1 ]
Ellouze, N. [1 ]
机构
[1] Univ Tunis El Manar, ENIT, Lab Signal Image & Technol Informat LRSITI, Tunis 1002, Tunisia
来源
JOURNAL OF ENGINEERING SCIENCE AND TECHNOLOGY | 2016年 / 11卷 / 09期
关键词
Speech; Emotions; SVM; GMM; Kernel; Sequence;
D O I
暂无
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Speech emotion recognition aims at automatically identifying the emotional or physical state of a human being from his or her voice. The emotional state is an important factor in human communication, because it provides feedback information in many applications. This paper makes a comparison of two standard methods used for speaker recognition and verification: Gaussian Mixture Models (GMM) and Support Vector Machines (SVM) for emotion recognition. An extensive comparison of two methods: GMM and GMM/SVM sequence kernel is conducted. The main goal here is to analyze and compare influence of initial setting of parameters such as number of mixture components, used number of iterations and volume of training data for these two methods. Experimental studies are performed over the Berlin Emotional Database, expressing different emotions, in German language. The emotions used in this study are anger, fear, joy, boredom, neutral, disgust, and sadness. Experimental results show the effectiveness of the combination of GMM and SVM in order to classify sound data sequences when compared to systems based on GMM.
引用
收藏
页码:1221 / 1233
页数:13
相关论文
共 50 条
  • [21] Client dependent GMM-SVM models for speaker verification
    Le, Q
    Bengio, S
    ARTIFICIAL NEURAL NETWORKS AND NEURAL INFORMATION PROCESSING - ICAN/ICONIP 2003, 2003, 2714 : 443 - 451
  • [22] A STUDY ON GMM-SVM WITH ADAPTIVE RELEVANCE FACTOR AND ITS COMPARISON WITH I-VECTOR AND JFA FOR SPEAKER RECOGNITION
    You, Chang Huai
    Li, Haizhou
    Ma, Bin
    Lee, Kong Aik
    2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7683 - 7687
  • [23] Effect of Relevance Factor of Maximum a posteriori Adaptation for GMM-SVM in Speaker and Language Recognition
    You, Chang Huai
    Li, Haizhou
    Ma, Bin
    Lee, Kong Aik
    13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3, 2012, : 2063 - 2066
  • [24] Automatic Detection of Pathological Voices Using GMM-SVM Method
    Wang, Xiang
    Zhang, Jianping
    Yan, Yonghong
    PROCEEDINGS OF THE 2009 2ND INTERNATIONAL CONFERENCE ON BIOMEDICAL ENGINEERING AND INFORMATICS, VOLS 1-4, 2009, : 525 - 528
  • [25] A GMM SUPERVECTOR KERNEL WITH THE BHATTACHARYYA DISTANCE FOR SVM BASED SPEAKER RECOGNITION
    You, Chang Huai
    Lee, Kong Aik
    Li, Haizhou
    2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, 2009, : 4221 - 4224
  • [26] Combining Deep Speaker Specific Representations with GMM-SVM for Speaker Verification
    Price, Ryan
    Biswas, Sangeeta
    Shinoda, Koichi
    14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 2787 - 2791
  • [27] A COMPARISON OF SEVERAL VARIANTS OF GMM ON SPEECH RECOGNITION TASK
    Jakovljevic, Niksa M.
    Miskovic, Dragisa M.
    Pakoci, Edvin T.
    Grbic, Tatjana P.
    Delic, Vlado D.
    2013 21ST TELECOMMUNICATIONS FORUM (TELFOR), 2013, : 466 - +
  • [28] N-best tokenization in a GMM-SVM language identification system
    Yang, Xi
    Siu, Manhung
    2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 1005 - +
  • [29] Utterance partitioning with acoustic vector resampling for GMM-SVM speaker verification
    Mak, Man-Wai
    Rao, Wei
    SPEECH COMMUNICATION, 2011, 53 (01) : 119 - 130
  • [30] An SVM Kernel With GMM-Supervector Based on the Bhattacharyya Distance for Speaker Recognition
    You, Chang Huai
    Lee, Kong Aik
    Li, Haizhou
    IEEE SIGNAL PROCESSING LETTERS, 2009, 16 (1-3) : 49 - 52