The Automatic Recognition of Sepedi Speech Emotions Based on Machine Learning Algorithms

Over the past years, speech emotion recognition (SER) studies have been gaining much interest in the fields of affective computing and human-computer interaction (HCI). The idea was to improve the interaction between human beings and machines. In this paper, an SER system that classifies and recognise six basic emotions (anger, sadness, disgust, fear, happiness, and neutral) from speech spoken in Sepedi language (one of South Africa's official languages) is discussed. Speech recordings were collected from the Sepedi language speakers and TV drama broadcast to create emotional speech corpora. 34 speech features were then extracted from the speech corpora, using the pyAudioAnalysis tool, to train and compare different algorithms using 10 folds cross-validation. The experiments were conducted using WEKA data-mining software. The results showed that Auto-WEKA outperforms all the standard algorithms (SVM. KNN and MLP). Recorded speech corpus yielded good recognition accuracy compare to TV broadcast speech corpus.