A Study of Support Vector Machines for Emotional Speech Recognition

被引：0
|
作者：
Kurpukdee, Nattapong [1 ,2 ]
Kasuriya, Sawit [2 ]
Chunwijitra, Vataya [2 ]
Wutiwiwatchai, Chai [2 ]
Lamsrichan, Poonlap [1 ]
机构：
[1] Kasetsart Univ, ICTES Program, TAIST Tokyo Tech, Bangkok, Thailand
[2] NSTDA, NECTEC, 112 Pahonyothin Rd, Pathum Thani 12120, Thailand
来源：
2017 8TH INTERNATIONAL CONFERENCE OF INFORMATION AND COMMUNICATION TECHNOLOGY FOR EMBEDDED SYSTEMS (IC-ICTES) | 2017年
关键词：
Emotional Speech Recognition (ESR) and Classification; Utterance features; SVM (Support Vector Machines); Binary Support Vector Machines (BSVM); FEATURES; SVM;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper, efficiency comparison of Support Vector Machines (SVM) and Binary Support Vector Machines (BSVM) techniques in utterance-based emotion recognition is studied. Acoustic features including energy, Mel-frequency cepstral coefficients (MFCC), Perceptual linear predictive (PLP), Filter bank (FBANK), pitch, their first and second derivatives are used as frame-based features. Four basic emotions including anger, happiness, neutral and sadness in Interactive Emotional Dyadic Motion Capture (IEMOCAP) database are selected for training and evaluating in our experiments. The best accuracy of emotional speech recognition is 58.40% in average from SVM with polynomial kernel. Energy features combination with FBANK, pitch and their first and second derivatives features are the most suitable for computing utterance feature. Binary Support Vector Machines (BSVM) techniques show accuracy improvement in some emotions, such as sadness and happiness emotion.
引用
收藏
页数：6
相关论文
共 50 条
  • [1] Support vector machines employing cross-correlation for emotional speech recognition
    Chandaka, Suryannarayana
    Chatterjee, Amitava
    Munshi, Sugata
    [J]. MEASUREMENT, 2009, 42 (04) : 611 - 618
  • [2] Speech Recognition using Support Vector Machines
    Aida-zade, Kamil
    Xocayev, Anar
    Rustamov, Samir
    [J]. 2016 IEEE 10TH INTERNATIONAL CONFERENCE ON APPLICATION OF INFORMATION AND COMMUNICATION TECHNOLOGIES (AICT), 2016, : 108 - 111
  • [3] Convolutional support vector machines for speech recognition
    Passricha, Vishal
    Aggarwal, Rajesh Kumar
    [J]. INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY, 2019, 22 (03) : 601 - 609
  • [4] RECURRENT SUPPORT VECTOR MACHINES FOR SPEECH RECOGNITION
    Zhang, Shi-Xiong
    Zhao, Rui
    Liu, Chaojun
    Li, Jinyu
    Gong, Yifan
    [J]. 2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, 2016, : 5885 - 5889
  • [5] Applications of support vector machines to speech recognition
    Ganapathiraju, A
    Hamaker, JE
    Picone, J
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2004, 52 (08) : 2348 - 2355
  • [6] Infinite Support Vector Machines in Speech Recognition
    Yang, Jingzhou
    van Dalen, Rogier C.
    Gales, Mark
    [J]. 14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 3302 - 3306
  • [7] An Application of Speech Recognition with Support Vector Machines
    Eray, Osman
    Tokat, Sezai
    Iplikci, Serdar
    [J]. 2018 6TH INTERNATIONAL SYMPOSIUM ON DIGITAL FORENSIC AND SECURITY (ISDFS), 2018, : 38 - 43
  • [8] Convolutional support vector machines for speech recognition
    Vishal Passricha
    Rajesh Kumar Aggarwal
    [J]. International Journal of Speech Technology, 2019, 22 : 601 - 609
  • [9] Speech Emotion Recognition Using Support Vector Machines
    Yu, Caiming
    Tian, Qingxi
    Cheng, Fang
    Zhang, Shiqing
    [J]. ADVANCED RESEARCH ON COMPUTER SCIENCE AND INFORMATION ENGINEERING, PT I, 2011, 152 : 215 - 220
  • [10] Visual speech recognition using support vector machines
    Gordan, M
    Kotropoulos, C
    Pitas, I
    [J]. DSP 2002: 14TH INTERNATIONAL CONFERENCE ON DIGITAL SIGNAL PROCESSING PROCEEDINGS, VOLS 1 AND 2, 2002, : 1093 - 1096
12345