Open AccessEmotion recognition from syllabic units using k-nearest-neighbor classification and energy distribution
Author(s) -
Abdellah Agrima,
Ilham Mounir,
Abdelmajid Farchi,
Laila Elmaazouzi,
Badia Mounir
Publication year - 2021
Publication title -
international journal of power electronics and drive systems/international journal of electrical and computer engineering
Language(s) - English
Resource type - Journals
eISSN - 2722-2578
pISSN - 2722-256X
DOI - 10.11591/ijece.v11i6.pp5438-5449
Subject(s) - formant , computer science , speech recognition , k nearest neighbors algorithm , support vector machine , emotion classification , vowel , classifier (uml) , pattern recognition (psychology) , artificial intelligence , sadness , anger , syllabic verse , psychology , psychiatry
In this article, we present an automatic technique for recognizing emotional states from speech signals. The main focus of this paper is to present an efficient and reduced set of acoustic features that allows us to recognize the four basic human emotions (anger, sadness, joy, and neutral). The proposed features vector is composed by twenty-eight measurements corresponding to standard acoustic features such as formants, fundamental frequency (obtained by Praat software) as well as introducing new features based on the calculation of the energies in some specific frequency bands and their distributions (thanks to MATLAB codes). The extracted measurements are obtained from syllabic units’ consonant/vowel (CV) derived from Moroccan Arabic dialect emotional database (MADED) corpus. Thereafter, the data which has been collected is then trained by a k-nearest-neighbor (KNN) classifier to perform the automated recognition phase. The results reach 64.65% in the multi-class classification and 94.95% for classification between positive and negative emotions.