Comparison of Different Models and Refinement Techniques in Speech Emotion Recognition

  • Kowtha Sathwik, Korikana Snehith, Amarthaluru Nikhil Kumar, Kolla Bhanu Prakash

Abstract

In Speech Emotion Recognition, we receive raw speech from a person as input and refine the speech with some techniques and analyse the emotional state of the person. There are lot of models for SER, using these models we get different accuracies and we also have different datasets and databases to train them. We used features like MFCC, PLP, Pitch etc for better recognition.They are lot of refinement techniques so, comparing different combinations and analysing result is the main goal and judging on which parameters accuracies are depending.

Published
2020-05-28
How to Cite
Kowtha Sathwik, Korikana Snehith, Amarthaluru Nikhil Kumar, Kolla Bhanu Prakash. (2020). Comparison of Different Models and Refinement Techniques in Speech Emotion Recognition. International Journal of Control and Automation, 13(4), 831 - 840. Retrieved from http://sersc.org/journals/index.php/IJCA/article/view/18881
Section
Articles