Emotion Recognition based on Third-Order Circular Suprasegmental Hidden Markov Model

TL;DR

This paper introduces the CSPHMM3, a novel third-order circular suprasegmental hidden Markov model, which improves emotion recognition accuracy from speech data compared to existing models, demonstrating its effectiveness on the EPST database.

Contribution

The work presents CSPHMM3, a new model that outperforms traditional HMM, GMM, SVM, and VQ in emotion recognition accuracy from speech signals.

Findings

CSPHMM3 achieves 77.8% accuracy in emotion recognition.

CSPHMM3 outperforms HMM3, GMM, SVM, and VQ by 6.0%, 4.9%, 3.5%, and 5.4%.

Recognition accuracy is comparable to human subjective assessment.

Abstract

This work focuses on recognizing the unknown emotion based on the Third-Order Circular Suprasegmental Hidden Markov Model (CSPHMM3) as a classifier. Our work has been tested on Emotional Prosody Speech and Transcripts (EPST) database. The extracted features of EPST database are Mel-Frequency Cepstral Coefficients (MFCCs). Our results give average emotion recognition accuracy of 77.8% based on the CSPHMM3. The results of this work demonstrate that CSPHMM3 is superior to the Third-Order Hidden Markov Model (HMM3), Gaussian Mixture Model (GMM), Support Vector Machine (SVM), and Vector Quantization (VQ) by 6.0%, 4.9%, 3.5%, and 5.4%, respectively, for emotion recognition. The average emotion recognition accuracy achieved based on the CSPHMM3 is comparable to that found using subjective assessment by human judges.