ISSN : 2319-7323




INTERNATIONAL JOURNAL OF COMPUTER SCIENCE ENGINEERING


Open Access

ABSTRACT

Title : Recognizing emotions of Marathi isolated speech from energy and formants using LDA
Authors : Shaikh Nilofer Rais Ahmed, Ratnadeep R. Deshmukh, Vishal B. Waghmare
Keywords : Database, Emotion Recognition, Formants, Feature extraction, Linier discriminant Analysis, Speech.
Issue Date : July 2015
Abstract : Many attempts have been made for developing a system which can recognize emotions from speech signals effectively. The research shows that various features namely prosodic and spectral have been used for emotion recognition from speech. This paper is one search approach towards same. The database used for recognition purpose was developed on Marathi language using 100 speakers. Here we have extracted the prosodic features i.e. energy and formants from speech signals. We have also applied linier discriminates analysis as the classification technique. Further we have compare the results gain on the basis of extracted features and came to know that formant gives quit good results compared to that of energy.
Page(s) : 188-191
ISSN : 2319-7323
Source : Vol. 4, No.4