Emotion recognition in Romanian language using LPC features

Author

Feraru, Silvia Monica ; Zbancioc, Marius Dan

Author_Institution

Inst. of Comput. Sci., Iaşi, Romania

fYear

2013

fDate

21-23 Nov. 2013

Firstpage

1

Lastpage

4

Abstract

In this study we compare the recognition accuracy of the emotions when in the feature vectors are introduced the LPC coefficients, with previous results obtained with prosodic features (F0-fundamental frequency, F1-F4-formants), respectively MFCC (Mel frequency) cepstral coefficients. From the extended sets of parameters that we introduced LPCC ((linear prediction cepstral coefficients)+LPC+PARCOR (partial correlation coefficient)+LAR (log area ratio) coefficients +AC (autocorrelation coefficients), best results was obtained for PARCOR coefficients when the emotion recognition rate was around 81%.

Keywords

Gaussian processes; emotion recognition; natural language processing; support vector machines; AC; GMM; LAR; LDA; LPC features; MFCC; Mel frequency cepstral coefficients; PARCOR; Romanian language; SROL database; SVM; autocorrelation coefficients; emotion recognition; feature vectors; linear prediction cepstral coefficients; log area ratio coefficients; partial correlation coefficient; Accuracy; Databases; Emotion recognition; Mel frequency cepstral coefficient; Speech; Speech recognition; Vectors; LPCC; PARCOR; Weighted-KNN; emotion recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

E-Health and Bioengineering Conference (EHB), 2013

Conference_Location

Iasi

Print_ISBN

978-1-4799-2372-4

Type

conf

DOI

10.1109/EHB.2013.6707314

Filename

6707314