Big Data Technologies and Applications. 8th International Conference, BDTA 2017, Gwangju, South Korea, November 23–24, 2017, Proceedings

Research Article

Detecting Human Emotion via Speech Recognition by Using Ensemble Classification Model

Download77 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-98752-1_8,
        author={Sathit Prasomphan and Surinee Doungwichain},
        title={Detecting Human Emotion via Speech Recognition by Using Ensemble Classification Model},
        proceedings={Big Data Technologies and Applications. 8th International Conference, BDTA 2017, Gwangju, South Korea, November 23--24, 2017, Proceedings},
        proceedings_a={BDTA},
        year={2018},
        month={11},
        keywords={Speech emotion recognition Feature extraction Ensemble classification Weight majority vote k-nearest neighbor Neural Network Support Vector Machines},
        doi={10.1007/978-3-319-98752-1_8}
    }
    
  • Sathit Prasomphan
    Surinee Doungwichain
    Year: 2018
    Detecting Human Emotion via Speech Recognition by Using Ensemble Classification Model
    BDTA
    Springer
    DOI: 10.1007/978-3-319-98752-1_8
Sathit Prasomphan1,*, Surinee Doungwichain1
  • 1: King Mongkut’s University of Technology North Bangkok
*Contact email: ssp.kmutnb@gmail.com

Abstract

Speech Emotion Recognition is one of the most challenging researches in the field of Human-Computer Interaction (HCI). The accuracy of detecting emotion depends on several factors for example, type of emotion and number of emotion which is classified, quality of speech. In this research, we introduced the process of detecting 4 different emotion types (anger, happy, natural, and sad) from Thai speech which was recorded from Thai drama show which was most similar with daily life speech. The proposed algorithms used the combination of Support Vector Machine, Neural Network and k-Nearest Neighbors for emotion classification by using the ensemble classification method with majority weight voting. The experimental results show that emotion classification by using the ensemble classification method by using the majority weight voting can efficiency give the better accuracy results than the single model. The proposed method has better results when using with fundamental frequency (F0) and Mel-frequency cepstral coefficients (MFCC) of speech which give the accuracy results at 70.69%.