Wavelet Packet Entropy in Speaker-Independent Emotional State Detection from Speech Signal

Journal Title: روش های هوشمند در صنعت برق - Year 2014, Vol 5, Issue 20

Abstract

In this paper, wavelet packet entropy is proposed for speaker-independent emotion detection from speech. After pre-processing, wavelet packet decomposition using wavelet type db3 at level 4 is calculated and Shannon entropy in its nodes is calculated to be used as feature. In addition, prosodic features such as first four formants, jitter or pitch deviation amplitude, and shimmer or energy variation amplitude besides MFCC features are applied to complete the feature vector. Then, Support Vector Machine (SVM) is used to classify the vectors in multi-class (all emotions) or two-class (each emotion versus normal state) format. 46 different utterances of a single sentence from Berlin Emotional Speech Dataset are selected. These are uttered by 10 speakers in sadness, happiness, fear, boredom, anger, and normal emotional state. Experimental results show that proposed features can improve emotional state detection accuracy in multi-class situation. Furthermore, adding to other features wavelet entropy coefficients increase the accuracy of two-class detection for anger, fear, and happiness.

Authors and Affiliations

Mina Kadkhodaei Elyaderani, Hamid Mahmoodian, Ghazaal Sheikhi

Keywords

Related Articles

A Novel Approach in Text-Independent Speaker Recognition in Noisy Environment

In this paper, robust text-independent speaker recognition is taken into consideration. The proposed method performs on manual silence-removed utterances that are segmented into smaller speech units containing few phones...

Overheating Recognition in Power Systems using Thermochromic Materials and Image Processing

According to the diagnosis of defects in electrical equipment to prevent accidents, damage and losses, it is necessary to work effectively in identifying defects so that we can predict and prevent errors. Nowadays, therm...

Rotor Design and Analysis of 4/2 SRMs to Produce Continuous Torque using Finite Element Method

Electrical and mechanical benefits, simple manufacturing and maintenance of switched reluctance motor make it suitable in industrial and home applications, but the most important drawbacks of switched reluctance motor ar...

Improved Fiber Bragg Grating Bending-Sensor Using TE/TM Modes

After the advent of optical fibers and cheap respective parts, using fiber optic sensors flourished. Bending is one of the significant parameters by measuring which, using optical fiber sensors, mechanical system mode ca...

Design of a Sliding Mode Controller for Two-Wheeled Balancing Robot

Nowadays, the control of mechanical systems with fewer inputs than outputs (Under-actuated systems) has become a challenging problem for control engineers. Two-wheeled balancing robots is one of the appealing examples of...

Download PDF file
  • EP ID EP328450
  • DOI -
  • Views 108
  • Downloads 0

How To Cite

Mina Kadkhodaei Elyaderani, Hamid Mahmoodian, Ghazaal Sheikhi (2014). Wavelet Packet Entropy in Speaker-Independent Emotional State Detection from Speech Signal. روش های هوشمند در صنعت برق, 5(20), 67-74. https://europub.co.uk/articles/-A-328450