International Journal of Electrical and Computer Engineering (IJECE) Vol. 10, No. 5, October 2020, pp. 4752~4758 ISSN: 2088-8708, DOI: 10.11591/ijece.v10i5.pp4752-4758  4752 Journal homepage: http://ijece.iaescore.com/index.php/IJECE Creation of speech corpus for emotion analysis in Gujarati language and its evaluation by various speech parameters Vishal P. Tank 1 , S. K. Hadia 2 1 V T Patel Department of Electronics and Communication Engineering, Chandubhai S Patel Institute of Technology (CSPIT), Charotar University of Science and Technology (CHARUSAT), India 2 Gujarat Technological University, India Article Info ABSTRACT Article history: Received Nov 18, 2019 Revised Mar 23, 2020 Accepted Apr 3, 2020 In the last couple of years emotion recognition has proven its significance in the area of artificial intelligence and man machine communication. Emotion recognition can be done using speech and image (facial expression), this paper deals with SER (speech emotion recognition) only. For emotion recognition emotional speech database is essential. In this paper we have proposed emotional database which is developed in Gujarati language, one of the official’s language of India. The proposed speech corpus bifurcate six emotional states as: sadness, surprise, anger, disgust, fear, happiness. To observe effect of different emotions, analysis of proposed Gujarati speech database is carried out using efficient speech parameters like pitch, energy and MFCC using MATLAB Software. Keywords: Emotion detection from speech Energy Gujarati language MATLAB software MFCC Pitch Copyright © 2020 Institute of Advanced Engineering and Science. All rights reserved. Corresponding Author: Vishal P. Tank, V T Patel Department of Electronics and Communication Engineering, Chandubhai S Patel Institute of Technology (CSPIT), Charotar University of Science and Technology (CHARUSAT), Changa-388421, Anand, Gujarat, India. Email: vishaltank.ec@charusat.ac.in 1. INTRODUCTION Speech and facial expression mainy two mode by which people interact and communicate to each other, betwixt speech is best mode for information exchange. Speech is a compund signal which contains the sharp details of language, speaker, emotion, and message [1]. It is importance to understand role of different emotions in speech because presecnce of emotions make speech more natural. Word “OKAY” spoken with different emotions have different meanings and inerpretation. Human robot interaction can be possible in better, effective and natural way if valid emotion gets involved in a speech.Finally this helps in to area of artificial intellience. As mention earlier emotions can be perceived either from speech or facial expression (image processing), but dignosticate from the speech is complicated task. By recognitioning emotions of users add values in day to day life. Emotion recognition task is useful in day to day life in several ways like, lie detection system [2], audio/video retrieval [3, 4], artificial intelligence and robotics, assign priority to customers in various call-centers, improved diagnostic tool, intelligent teaching/tutoring system, language conversion, improved computer games, smart car board system and sorting of voicemail/ messages. Such utilisations make emotion recognition from speech as best research topic in the field of speech processing. To have a speech database is essential in process of speech emotion recognition as shown in Figure 1 [5]. Researchers and scientists have developed speech corpora invarious languages like English, German, Chinese, Spanish, Japanese, Russian, Swedish, and Italian etc [6]. There are few speech databases available for official Indian languages like Hindi, Telugua andMalyalam [7]. As per author perception,