Abstract
The recognition of emotion is becoming an increasingly important field for humancomputer interaction. This paper explores the detection of four basic classes of emotions, namely Anger, Sadness, Happiness and Neutral. Prosodic features such as mean, maximum, minimum, standard-deviation of pitch and energy, and audible durations are used for recognition purpose. A Fuzzy Min-Max Neural network is used as an emotion classifier which consists of fuzzy sets. Each fuzzy set is an aggregate(union) of fuzzy set hyperboxes. The use of a fuzzy set approach to pattern classifier inherently provides degree of membership information that is extremely useful in higher-level decision making. The data for classification is recorded with a sampling rate of 22.05 kHz. Each utterance is split into frame size of 440 samples (20 ms duration). The signal is passed through voice/un-voice classifier & prosody features are extracted from the signal. Data consists of utterances in English and Marathi languages, for four basic emotions . The average success rate is found to be 83.33%.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
