Abstract: In the past decade a lot of research has gone into Automatic Speech Emotion Recognition (SER). The primary objective of SER is to improve man-machine interface. It can also be used to monitor the psycho physiological state of a person in lie detectors. In recent time, speech emotion recognition also finds its applications in medicine and forensics. In this paper 7 emotions are recognized using pitch and prosody features. Majority of the speech features used in this work are in time domain. Support Vector Machine (SVM) classifier has been used for classifying the emotions. Berlin emotional database is chosen for the task. A good recognition rate of 81% was obtained. The paper that was considered as the reference for our work recognized 4 emotions and obtained a recognition rate of 94.2%. The reference paper also used hybrid classifier thus increasing complexity but can only recognize 4 emotions.

Keywords :Artificial Intelligence, Machine Learning, Voice Recognition, Speech Recognition, Speech Emotion Recognition.

PDF | DOI: 10.17148/IJARCCE.2022.11456

Open chat
Chat with IJARCCE