Speech Emotion Recognition using GTCC, NN and GA

  Khushboo Mittal,  Parvinder Kaur

Emotion identification from speech of a human being is a very important area in research, which represents the inhuman-computer interaction. Recently, increasing attention has been directed to the study of the emotional content of speech signals, and hence, many systems have been proposed to identify the emotional content of a spoken utterance. The recent literature on speech emotion recognition has been presented considering the issues related to emotional speech corpora, different types of speech features and models used for recognition of emotions from speech. In this work, three emotions JOY, SAD, and AGGRESSIVE, are used based on automatic speech emotion recognition system. A new system is proposed for the detection of emotion form speech of an individual, GTCC and GA are used for feature extraction and feature reduction purpose. And for classification neural network and support vector machine algorithm are used. Then after obtaining results from NN and SVM, they are compared using graph. This proves neural network does better classification.

Keywords- Emotion Recognition, Happy, Sad, Anger, Feature Extraction, Classification.

Unique Identification Number - IJEDR1504148
Page Number(s) - 830-836
Pubished in - Volume 3 | Issue 4 | December 2015
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  Khushboo Mittal,  Parvinder Kaur,   "Speech Emotion Recognition using GTCC, NN and GA", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.3, Issue 4, pp.830-836, December 2015, Available at :http://www.ijedr.org/papers/IJEDR1504148.pdf