Models & Optimisation and Mathematical Analysis Journal
Volume 7, Numéro 1, Pages 20-25
2019-12-24

Use Of Differents Classifiers For Recognition Of Fear Emotions In Speech



Authors : Horkous Houari .

Abstract

This work consists on the automatic recognition of the emotions in the speech, because it plays a very significant role in the communication. The automatic recognition of the emotions potentially had a broad application in the Human Machine Interaction. In this work emotional speech corpus in Algerian Dialect was created for parameters extraction. The selected parameters in our study are the prosodic (pitch, intensity and duration), the unvoiced frames, jitter, shimmer and cepstral parameters MFCCs (Mel-Frequency Cepstral Coefficients) to analyze the emotions of fear and neutral. These parameters will be used in the automatic recognition of the emotions. The system of recognition is based on the methods of classification KNN (K-Nearest Neighbor), SVM (Support Vector Machine) and ANN (Artificial Neural Network). The obtained results lead us to observe that the use of MFCCs parameters gives a very acceptable rate of emotion recognition.

Keywords

Speech emotion ; Algerian Dialect ; prosodic ; MFCC ; KNN ; SVM ; ANN

Les articles similaires

Recognition Of Fear And Anger Emotions In The Algerian Dialect Speech

Horkous Houari . 
pages 6-10.

Kernel Svm Classifiers Based On Fractal Analysis For Estimation Of Hearing Loss

Djemai Mohamed .  Guerti Mhania . 
pages 45-50.

Personal Appearance And The Use Of Euphemism In The Speech Of Algerian Adolescents: The Case Of The Constantine Speech Community

Arabet Mohamed Akram . 
pages 1349-1360.

Speech Emotions Recognition Of Joy And Sadness Based On Prosodic And Mfccs Parameters

Horkous Houari . 
pages 15-18.

Multi-dialectical Languages Effect On Speech Recognition Too Much Choice Can Hurt

G. Elfeky Mohamed .  Moreno Pedro .  Soto Victor . 
pages 1-5.

Formats de citation