Extract features from Persian speech signal for emotion recognition

Establishing verbal communication between man and machine, as well as understanding the human emotions by the machine and providing an appropriate response to it requires understanding the speech and emotions of the speaker, in this regard, research in the field of emotion recognition in speech signal is necessary. In this paper, an attempt is made to design and implement a system to determine and detect emotions of anger and happiness in the Persian speech signal. Research on recognizing some emotions has been done in most languages, but due to the difficulty of creating a speech database, so far little research has been done to identify emotions in Persian speech. In this article, due to the lack of a suitable database in Persian to detect emotions, at first, a database for moods of happiness and anger and neutral (without any emotion) in Persian, consisting of ۷۲۰ sentences was created. Then the frequency characteristics of speech signals obtained from Fourier transform such as maximum, minimum, median and mean as well as LPC coefficients were extracted. Then, the MLP neural network was used to detect emotions of happiness and anger with an average accuracy of ۸۷.۷۴%.

Keywords:

Emotion Recognition , Speech Processing , Happiness and Anger Diagnosis , LPC Coefficients , Neural Network