Abstract: Automatic speech emotion recognition is an active research area in the field of Human Computer Interaction (HCI) with wide range of applications. The proposed work is Speech Emotion Recognition for Malayalam language by using gradient boosted tree classifiers in python. Speech Emotion Recognition is extraction of the emotional state of the speaker from his or her speech signal. In this first we collect different speeches from individuals in Malayalam language. The emotion in one input audio will be found out by extracting features in that audio by MFCC (Mel Frequency Cepstral Co-efficient) and then classified by Gradient boosted tree classifiers. Four types of emotions such as Angry, Happy, Neutral and Sad are identified by this approach. Applications of SER are in the field of Medicine, Counselling, Autism patients, Music therapy, Law and  Entertainment – Recognize mood & emotions of user.

Keywords: Speech Emotion Recognition, MFCC, Gradient Boosted Tree Classifiers

PDF | DOI: 10.17148/IJARCCE.2020.9123

Open chat
Chat with IJARCCE