Recognition Of Fear And Anger Emotions In The Algerian Dialect Speech

Résumé: Recognition emotion in speech signal has attracted much attention and plays an important role in affect computing, artificial intelligence and signal processing areas. The aim of speech emotion recognition system is to extract the information from the speech signal and identify the emotional state of a human being. In this work emotional speech corpus in Algerian Dialect is used for parameters extraction to analyze the emotions of fear, anger and neutral. 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). The system of recognition is based on the method of classification KNN (K-Nearest Neighbor). The obtained results lead us to observe that combined prosodies, jitter, shimmer, unvoiced frames and MFCCs parameters give recognition rate important (84.02%)

Publié dans la revue: Models & Optimisation and Mathematical Analysis Journal