DocumentCode :
165971
Title :
ROC Analysis of Class Dependent and Class Independent Linear Discriminant classifiers using frequency domain features
Author :
Kuchibhotla, Swarna ; Vankayalapati, H.D. ; Yalamanchili, B.S. ; Anne, K.R.
Author_Institution :
Acharya Nagarjuna Univ., Nagarjuna Nagar, India
fYear :
2014
fDate :
24-27 Sept. 2014
Firstpage :
1916
Lastpage :
1920
Abstract :
Emotional speech recognition aims at classifying the human emotional states viz. happy, neutral, anger and sad etc.,. To classify these emotions we need to extract reliable Acoustic features like prosody and spectral. The time domain features are much less accurate than frequency domain features. So in this paper Mel Frequency Cepstral Coefficients(MFCC) are extracted from Berlin emotional speech corpus and are classified using Class Dependent and Class Independent Linear Discriminant Analysis(CD-LDA and CI-LDA). The results obtained shows the performance variation of the classifiers with respect to the emotional states.
Keywords :
acoustic signal processing; cepstral analysis; emotion recognition; feature extraction; frequency-domain analysis; signal classification; speech recognition; time-domain analysis; Berlin emotional speech corpus; CD-LDA; CI-LDA; MFCC; ROC analysis; acoustic feature extraction; class dependent linear discriminant classifier; class independent linear discriminant classifier; emotion classification; emotional speech recognition; emotional states; frequency domain features; human emotional state classification; mel frequency cepstral coefficients; prosody; spectral; time domain features; Accuracy; Databases; Emotion recognition; Feature extraction; Mel frequency cepstral coefficient; Speech; Speech recognition;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Advances in Computing, Communications and Informatics (ICACCI, 2014 International Conference on
Conference_Location :
New Delhi
Print_ISBN :
978-1-4799-3078-4
Type :
conf
DOI :
10.1109/ICACCI.2014.6968289
Filename :
6968289
Link To Document :
بازگشت