We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Time-domain non-linear feature parameter for consonant classification.
- Authors
Thasleema, T.; Prajith, P.; Narayanan, N.
- Abstract
This paper introduces an accurate time-domain approach to model and classify the Malayalam consonant-Vowel (CV) speech unit waveforms. The technique is based on statistical models of Reconstructed State Space (RSS). A feature extraction method using RSS based State Space Point Distribution (SSPD) parameters are studied. The results of the simulation experiment performed on the Malayalam CV speech databases using Artificial Neural Network (ANN) and k-Nearest Neighborhood ( k-NN) classifiers are also presented. The results indicate that the efficiency of the RSS approach is capable of increasing speaker independent consonant speech recognition accuracy.
- Subjects
AUTOMATIC speech recognition; MALAYALAM language; TIME-domain analysis; LINEAR systems; PARAMETER estimation; CONSONANTS; FEATURE extraction; STATISTICS; ARTIFICIAL neural networks
- Publication
International Journal of Speech Technology, 2012, Vol 15, Issue 2, p227
- ISSN
1381-2416
- Publication type
Article
- DOI
10.1007/s10772-012-9136-6