期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2016
卷号：5
期号：6
页码：2105-2107
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Emotion recognition from Audio signal Recognition is a recent research topic in the Human Computer Interaction. The demand has risen for increasing communication interface between humans and digital media. Many researchers are working in order to improve their accuracy. But still there is lack of complete system which can recognize emotions from speech. In order to make the human and digital machine interaction more natural, the computer should able to recognize emotional states in the same way as human. The efficiency of emotion recognition system depends on type of features extracted and classifier used for detection of emotions. In this project emotion from Hindi speech is developed. The database used was collected from various speakers belonging to different genders and age group. This work basically focused on eight emotions which comprises of a combination of fundamental emotions with some advance emotions and are listed as: Happy, Angry, Sad, Depressed, Bored, Anxiety, Fear and Nervous. These signals were preprocessed and analyzed using various techniques like: cepstral, linear prediction coefficient etc. In feature extraction various parameters used to form a feature vector are: fundamental frequency, pitch contour, formants, duration (pause length ratio) etc. These features are classified by using K Nearest Neighbor (KNN) classifier and Neural Network based classifiers. The performance based on both classifiers is measured in terms of their accuracy.
