Hydrolysis of flatulence causing oligosaccharides by α-d-galactosidase of a probiotic Lactobacillus plantarum MTCC 5422 in selected legume flours and elaboration of probiotic attributes in soy-based fermented product

In the background of increasing research interest in food fermentations involving beneficial culture, the focus present study was to evaluate the ability of a single desirable bacterial culture to impart multiple benefits to the product being prepared therein. The intracellular α-d-galactosidase elaborated by Lactobacillus plantarum MTCC 5422 in formulated soy whey broth for Lactobacillus on partial purification exhibited an activity of 1.2 U/mL with specific activity of 12.0 U/mg and a threefold purification. The partially purified enzyme had a molecular mass of 84 kDa, pH and temperature optima of 5.8 and 45 °C, respectively, and enzyme stability of 30 min at 55 °C. Selected legume flours treated (2 h at 45 °C) with partially purified α-d-galactosidase resulted in lowering raffinose and stachyose levels in the range of 50–74 and 66–85 %, respectively. Soy-based fermented probiotic curd prepared with L. plantarum MTCC 5422 from α-d-galactosidase treated soy protein isolate showed almost 99 % decrease in levels of raffinose and stachyose. In the final product, the probiotic culture of L. plantarum MTCC 5422 reached viable population of 9.4 log₁₀ CFU/g and elaborated short chain fatty acids such as acetic, butyric and propionic acids in appreciable quantity. The product was devoid of any contaminating foodborne pathogenic bacterial species. At the same time, the product had appropriate levels of pH, acidity and antibacterial activity against Bacillus cereus. The innovative approach was the lowering of raffinose and stachyose by α-d-galactosidase of L. plantarum MTCC 5422 and elaboration of probiotic attributes by the same culture in the final product.     

Speaker recognition—general classifier approaches and data fusion methods

Speaker recognition refers to the concept of recognizing a speaker by his/her voice or speech samples. Some of the important applications of speaker recognition include customer verification for bank transactions, access to bank accounts through telephones, control on the use of credit cards, and for security purposes in the army, navy and airforce. This paper is purely a tutorial that presents a review of the classifier based methods used for speaker recognition. Both unsupervised and supervised classifiers are described. In addition, practical approaches that utilize diversity, redundancy and fusion strategies are discussed with the aim of improving performance.