Detecting Human Emotion via Speech Recognition by Using Speech Spectrogram

被引：0
作者：
Prasomphan, Sathit [1 ]
机构：
[1] King Mongkuts Univ Technol North Bangkok, Dept Comp & Informat Sci, Fac Sci Appl, Bangkok 10800, Thailand
来源：
PROCEEDINGS OF THE 2015 IEEE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS (IEEE DSAA 2015) | 2015年
关键词：
Speech Emotion Recognition; Neural Network; Spectrogram; Feature extraction;
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：
This research presents a novel algorithm for detecting human emotion via speech recognition by using speech spectrogram. The proposed algorithm aims to detect the emotional by using information inside the spectrogram. Neural network was used for being the classifier. A new approach to feature extraction based on analysis of two dimensions time-frequency representation of a speech signal have been presented. The algorithm was tested with Berlin emotion database and Audiovisual Thai Emotion Database. The experimental results show that the proposed framework can efficiently find the correct speech emotion compared to by using the comparing method.
引用
收藏
页码：113 / 122
页数：10
相关论文
共 24 条
  • [1] [Anonymous], INT J SIGNAL PROCESS
  • [2] Attabi Y., 2013, IEEE T AFFECTIVE COM, V4
  • [3] Demircan S., 2014, J ADV COMPUTER NETWO, V2
  • [4] AN ARGUMENT FOR BASIC EMOTIONS
    EKMAN, P
    [J]. COGNITION & EMOTION, 1992, 6 (3-4) : 169 - 200
  • [5] Survey on speech emotion recognition: Features, classification schemes, and databases
    El Ayadi, Moataz
    Kamel, Mohamed S.
    Karray, Fakhri
    [J]. PATTERN RECOGNITION, 2011, 44 (03) : 572 - 587
  • [6] Harimii A., 2014, J AI DATA MINING, V2, P53
  • [7] He L., 2009, 7 INT C COMM SIGN PR, P1
  • [8] Holzinger A., 2013, International Conference on Availability, Reliability, and Security, P469, DOI [10.1007/978, DOI 10.1007/978]
  • [9] Hyun K.H., 2005, 2005 IEEE INT WORKSH
  • [10] Ingale AB., 2012, Int J Adv Eng Res Stud, V1, P316
123