Emotion Recognition and Emotion Spotting Improvement Using Formant-Related Features
عنوان مقاله: Emotion Recognition and Emotion Spotting Improvement Using Formant-Related Features
شناسه ملی مقاله: JR_MJEE-4-4_001
منتشر شده در در سال 1389
شناسه ملی مقاله: JR_MJEE-4-4_001
منتشر شده در در سال 1389
مشخصات نویسندگان مقاله:
Davood Gharavian - Assistant Professor
Mansour Sheikhan
خلاصه مقاله:
Davood Gharavian - Assistant Professor
Mansour Sheikhan
Emotion has an important role in naturalness of man-machine communication. So, computerized emotion recognition from speech is investigated by many researchers in the recent decades. In this paper, the effect of formant-related features on improving the performance of emotion detection systems is experimented. To do this, various forms and combinations of the first three formants are concatenated to a popular feature vector and Gaussian mixture models are used as classifiers. Experimental results show average recognition rate of ۶۹% in four emotional states and noticeable performance improvement by adding only one formant-related parameter to feature vector. The architecture of hybrid emotion recognition/spotting is also proposed based on the developed models.
کلمات کلیدی: emotion recognition, en, formants, Gaussian Mixture Model
صفحه اختصاصی مقاله و دریافت فایل کامل: https://civilica.com/doc/1795431/