Machine Learning Based Speech Emotion Recognition System

Machine Learning Based Speech Emotion Recognition System

B    Chakradhar1     D Bhavana2    G  Rakesh3    M Chandrashekar4       A Sandeep5

   Assistant  Professor, Department of CSE, Raghu Engg. College, Visakhapatnam, AP, India.1

B.Tech   Students, Department of CSE, Raghu Engg. College, Visakhapatnam, AP, India.2,3,4,5

Abstract- In the last decade, there has been significant research into Automatic Speech Emotion Recognition (SER). The primary goal of SER is to improve human-machine interfaces. It can also monitor someone's psychological state for lie detection applications. Recently, speech emotion recognition has found uses in medicine and forensics. This paper recognizes 7 emotions using pitch and prosody features. The majority of speech features used here are in the time domain. A Support Vector Machine (SVM) classifier categorizes the emotions. The Berlin emotional database was used for this task. A good recognition rate of 81% was achieved. The reference paper for this work recognized 4 emotions and obtained a 94.2% recognition rate. However, the reference paper used a more complex hybrid classifier, while this work focuses on recognizing more emotions with a simpler model.

.

KeyWords: Blindness, Smart Stick, BlinDar, GPS, ESP8266, Internet of Things, RF Tx/Rx, MQ2.