Browsing by Author "E, Chandra"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    STOP CONSONANT-SHORT VOWEL (SCSV) CLASSIFICATION FOR TAMIL SPEECH UTTERANCES
    (2016-02) S, Karpagavalli; E, Chandra
    Tamil Language is one of the ancient Dravidian languages spoken in south India. Most of the Indian languages are syllabic in nature and syllables are in the form of Consonant-Vowel (CV) units. In Tamil language, CV pattern occurs in the beginning, middle and end of a word. In this work, CV units formed with Stop Consonant – Short Vowel (SCSV) were considered for classification task. The work carried out in three stages, Vowel Onset Point (VOP) detection, CV segmentation and classification. VOP is an event at which the consonant part ends and vowel part begins. VOPs are identified using linear Prediction residuals which provide significant characteristics of the excitation source. To segment the CV units, fixed length spectral frames before and after VOPs are considered. Both production based features - Linear Predictive Cepstral Coefficients (LPCC) and perception based features - Mel Frequency Cepstral Coefficients (MFCC) are extracted and given as input to the classifiers designed with multilayer perceptron and support vector machine. A speech corpus of 200 Tamil words uttered by 15 native speakers was used, which covers all SCSV units formed with Tamil stop consonants (/k/,/ch/,/d/,/t/,/p/) and short vowels (/a/,/i/, /u/, /e/, /o/). The classifiers are trained and tested for its performance using various measures. The results indicate that the model built with MFCC using support vector machine RBF kernel outperforms.
  • No Thumbnail Available
    Item
    TAMIL SPEECH ENABLED INTERFACE USING ROBUST TAMIL CONSONANT-VOWEL MODEL
    (International Journal of Pure and Applied Mathematics, 2018) S, Karpagavalli; J, Viji Gripsy; E, Chandra
    There are a lot of assistive technology tools are available to help individuals with learning disabilities. Assistive technology tools improve the skills of the children such as listening, mathematical, organizing, memory, reading and writing. Speech recognition technologies are highly effective and beneficial for children with one or more challenges that include learning disabilities like dyslexia, discalculia and dysgraphia. In the proposed work, an application,”TamilEasyApp‟ has been developed for children with both reading and writing disability, with an objective to support the children to learn Tamil words effectively. It has been developed by using Robust Tamil Consonant-Vowel Model (RTCVM) which addresses both speech rate variability and environment variability. A list of 100 Tamil words is prepared according to their educational need as well as the educational theories involved in teaching disabled children. In the presence of trained teachers, nearly 25 children including male and female within the age group 7 to 15 are participated in recording and uttered each Tamil words 10 times during their regular learning time. The impact of the application is gathered from the teachers after the usage of the application for a period of two months. The performance of the children is assessed by conducting post-test after the introduction of the application and compared with their skill level in regular learning before the introduction of application. The pre-test and post-test details and observations are collected from the special trainers. The overall observation indicates that the motivation and independent learning among the children significantly progressed through the use of speech assistive tool.