ITRW on Non-Linear Speech Processing (NOLISP 05) Barcelona, Spain April 19-22, 2005

Spotting Multilingual Consonant-Vowel Units of Speech using Neural Network Models

Suryakanth V. Gangashetty, C. Chandra Sekhar, B. Yegnanarayana

Speech and Vision Laboratory, Department of Computer Science and Engineering, Indian Institute of Technology Madras, Chennai, India

In this paper, we consider an approach for multilingual speech recognition by spotting consonant-vowel (CV) units. The main issues in spotting multilingual CV units are the location of anchor points and la- belling the regions around these anchor points using suitable classifiers. The vowel onset points (VOPs) have been used as anchor points. The distribution capturing ability of autoassociative neural network (AANN) models is explored for detection of VOPs in continuous speech. We con- sider support vector machine (SVM) based classifiers due to their ability of generalisation from limited training data and also due to their inherent discriminative learning. We study the spotting approach for recognition of a large number of CV units in the broadcast news corpus of three Indian languages.

Full Paper

Bibliographic reference.  Gangashetty, Suryakanth V. / Chandra Sekhar, C. / Yegnanarayana, B. (2005): "Spotting multilingual consonant-vowel units of speech using neural network models", In NOLISP-2005, 287-297.