An effective automatic speech emotion recognition for Tamil language based on DWT and MFCC using Stability-plasticity dilemma Neural network

Author

Ram, C. Sunitha ; Ponnusamy, R.

Author_Institution

Dept. of CSE, SCSVMV Univ., Kanchipuram, India

fYear

2014

fDate

27-28 Feb. 2014

Firstpage

1

Lastpage

6

Abstract

In this paper we put effort on Effective Automatic Speech emotion recognition on Human computer Interaction for Tamil speech. Due to the unavailability of Tamil language database for emotion recognition, we built a database of emotional speech in Tamil. This database consists of 19 wave clips modulated with anger, joy, fear, neutral, and sad. Then we extract cepstral based features like MFCC and Discrete Wavelet Transform (DWT). A German Corpus - Berlin Database of Emotional Speech and our self built Tamil emotional databases are used for training purpose. The Neural network is trained using Stability-plasticity dilemma. Finally results are compared and explained.

Keywords

audio databases; discrete wavelet transforms; emotion recognition; feature extraction; human computer interaction; learning (artificial intelligence); natural language processing; speech recognition; Berlin database emotional speech; DWT; German corpus; MFCC; Tamil emotional databases; Tamil language; Tamil speech; anger; automatic speech emotion recognition; cepstral based feature extraction; discrete wavelet transform; emotional speech database; fear; human computer interaction; joy; neutral; sad; stability-plasticity dilemma neural network training; wave clips; Databases; Discrete wavelet transforms; Emotion recognition; Feature extraction; Mel frequency cepstral coefficient; Speech; Speech recognition; DWT; EASER; MFCC; Stability-Plasticity dilemma;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Communication and Embedded Systems (ICICES), 2014 International Conference on

Conference_Location

Chennai

Print_ISBN

978-1-4799-3835-3

Type

conf

DOI

10.1109/ICICES.2014.7034102

Filename

7034102