COMBINED FEATURE EXTRACTION TECHNIQUES AND NAIVE BAYES CLASSIFIER FOR SPEECH RECOGNITION

Speech processing and consequent recognition are important areas of Digital Signal Processing since speech allows people to communicate more natu-rally and efficiently. In this work, a speech recognition system is developed for re-cognizing digits in Malayalam. For recognizing speech, features are to be ex-tracted from speech and hence feature extraction method plays an important role in speech recognition. Here, front end processing for extracting the features is per-formed using two wavelet based methods namely Discrete Wavelet Transforms (DWT) and Wavelet Packet Decomposition (WPD). Naive Bayes classifier is used for classification purpose. After classification using Naive Bayes classifier, DWT produced a recognition accuracy of 83.5% and WPD produced an accuracy of 80.7%. This paper is intended to devise a new feature extraction method which produces improvements in the recognition accuracy. So, a new method called Dis-crete Wavelet Packet Decomposition (DWPD) is introduced which utilizes the hy-brid features of both DWT and WPD. The performance of this new approach is evaluated and it produced an improved recognition accuracy of 86.2% along with Naive Bayes classifier.

A marine bacterium, Micrococcus MCCB 104, antagonistic to vibrios in prawn larval rearing systems

marine bacterium, Micrococcus MCCB 104, isolated from hatchery water, demonstrated extracellular antagonistic properties against Vibrio alginolyticus, V. parahaemolyticus, V. vulnificus, V. fluviallis, V. nereis, V. proteolyticus, V. mediterranei, V. cholerae and Aeromonas sp., bacteria associated with Macrobrachium rosenbergii larval rearing systems. The isolate inhibited the growth of V. alginolyticus during co-culture. The antagonistic component of the extracellular product was heat-stable and insensitive to proteases, lipase, catalase and α-amylase. Micrococcus MCCB 104 was demonstrated to be non-pathogenic to M. rosenbergii larvae

Synechocystis MCCB 114 and 115 as putative probionts for Penaeus monodon post-larvae

Synechocystis MCCB 114 and 115 were segregated as putative probionts for shrimp larvae from a collection of 54 cyanobacterial cultures enriched from seawater. On feeding Penaeus monodon post-larvae with the cyanobacteria, the generic diversity of the intestinal bacterial flora could be enhanced with substantial reduction or total absence of Vibrio spp. A significant difference (p < 0.001) in the percent survival of batches of post-larvae fed on the cyanobacterial cultures was observed and, on repeated challenge with V. harveyi, the relative percent survival of those batches of larvae fed on Synechocystis MCCB 114 and 115 was significantly higher. The Synechocystis MCCB 114 and 115 cultures were found to contain high levels of protein (34 to 43%), in addition to carotenoids

Antimicrobial activity of chitosan against vibrios from freshwater prawn Macrobrachium rosenbergii larval rearing systems

Chitosan is a biocompatible and biodegradable natural polymer with established antimicrobial properties against specific microorganisms. The present study demonstrates its antibacterial activity against 48 isolates of Vibrio species from prawn larval rearing systems. The antibacterial activity had a positive correlation with the concentration of chitosan. This work opens up avenues for using chitosan as a prophylactic biopolymer for protecting prawn larvae from vibriosis.