{"title":"EMOTION RECOGNITION AND EMOTION SPOTTING IMPROVEMENT USING FORMANT-RELATED FEATURES","authors":"D. Gharavian, M. Sheikhan","doi":"10.1234/MJEE.V4I4.266","DOIUrl":null,"url":null,"abstract":"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 69% 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.","PeriodicalId":37804,"journal":{"name":"Majlesi Journal of Electrical Engineering","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2010-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Majlesi Journal of Electrical Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1234/MJEE.V4I4.266","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Engineering","Score":null,"Total":0}
引用次数: 6
Abstract
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 69% 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.
期刊介绍：
The scope of Majlesi Journal of Electrcial Engineering (MJEE) is ranging from mathematical foundation to practical engineering design in all areas of electrical engineering. The editorial board is international and original unpublished papers are welcome from throughout the world. The journal is devoted primarily to research papers, but very high quality survey and tutorial papers are also published. There is no publication charge for the authors.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
