Abstract: In the past decade plenty of analysis has gone into Automatic Speech feeling Recognition (SER). The first objective of SER is to boost man-machine interface. It also can be accustomed monitor the psychotic state of an individual in lie detectors. In recent time, speech feeling recognition conjointly finds its applications in drugs and forensics. During this paper seven emotions square measure recognized mistreatment pitch and prosody options. Majority of the speech options utilized in this work square measure in time domain. Support Vector Machine (SVM) classifier has been used for classifying the emotions. Berlin emotional info is chosen for the task. A decent recognition rate of 81 was obtained. The paper that was thought of because the reference for our work recognized four emotions and obtained a recognition rate of 94.2%. The reference paper conjointly used hybrid classifier so increasing complexes however will solely acknowledge four emotions.
Keywords : Speech Emotion Recognition, Machine Learning, IoT Automation, Graphical User Interface
| DOI: 10.17148/IJARCCE.2021.101212