Work place: Department of Computer Science, Avinashilingam Institute for Home Science and HigherEducation for Women, Coimbatore, Tamil Nadu

E-mail: radharesearch@yahoo.com


Research Interests: Image and Sound Processing, Image Processing, Speech Recognition


Dr. V. Radha, Associate Professor, has more than 20 years of teaching experience. Her Area of Specialization is Image Processing, Optimization Techniques, Voice Recognition and Synthesis. She has 26 Publications at national and International level conferences.

Author Articles
Voice Pathology Identification: A Survey on Voice Disorder

By N.A. Sheela Selvakumari V.Radha

DOI: https://doi.org/10.5815/ijem.2017.02.04, Pub. Date: 8 Mar. 2017

Nowadays, Identification and Classification of voice pathology plays a major role in the field of speech processing. This paper explores and compares various things like input database, parameters, features extraction techniques, methodology and classification techniques used by the researchers in the problem of identifying the voice pathology. In this paper, we compared seven research works done in the field of voice pathology identification and classification. By analyzing the data's mentioned in these research papers and by considering these research papers as a base study, we wish to do the further research on voice pathology identification.

[...] Read more.
Efficient Acoustic Front-End Processing for Tamil Speech Recognition using Modified GFCC Features

By Vimala. C V.Radha

DOI: https://doi.org/10.5815/ijigsp.2016.07.03, Pub. Date: 8 Jul. 2016

Giving suitable input and features are always essential to obtain better accuracy in Automatic Speech Recognition (ASR). The type of signal and feature vectors given as an input is highly essential as the pattern matching algorithms strongly depends on these two components. The primary goal of this paper is to propose a suitable Pre-processing and feature extraction techniques for speaker independent speech recognition for Tamil language. The five pass Pre-processing and three types of modified feature extraction techniques are introduced using Gammatone Filtering and Cochleagram Coefficients (GFCC) to achieve better recognition performance. The modified GFCC features using multi taper Yule walker AR power spectrum, combinational features using Formant Frequencies (FF), combined frequency warping and feature normalization techniques using Linear Predictive Coding (LPC) and Cepstral Mean Normalization (CMN) are investigated. The experimental results prove that the proposed techniques have produced high recognition accuracy when compared with the conventional GFCC feature extraction technique. 

[...] Read more.
Other Articles