Title :
Developing Tamil emotional speech corpus and evaluating using SVM
Author_Institution :
IT Dept., Karpagam Coll. of Eng., Coimbatore, India
Abstract :
Finding the user´s emotion it can be used for business development and psychological analysis. The motivation of this paper is to build the Tamil emotional corpus for being base for the emotional analysis based on the acoustic variations present and to make Tamil emotional corpus available in public domain. Tamil Play will be used as main resource for building the emotional corpus. Basically, emotions like Happy, Neural, Sad, Fear and Anger are taken for this analysis purpose. And also for the accuracy purpose from the play both Male and Female Speakers emotional speech have been considered. The observer´s perception test result will be used to evaluate annotation of emotion. Tamil emotional speech corpus have been built and Emotion Recognition engine has been constructed using Support Vector Machine (SVM) classifier with the features like MFCC and Energy.
Keywords :
emotion recognition; natural language processing; speech recognition; support vector machines; SVM; Tamil emotional speech corpus; acoustic variation; emotion recognition; support vector machine classifier; Emotion recognition; Feature extraction; Mel frequency cepstral coefficient; Speech; Speech recognition; Support vector machines; Emotional Recognition Model; Mel Frequency Cepstral Coefficient (MFCC); Support Vector Machine (SVM); Tamil;
Conference_Titel :
Science Engineering and Management Research (ICSEMR), 2014 International Conference on
Print_ISBN :
978-1-4799-7614-0
DOI :
10.1109/ICSEMR.2014.7043627
