Automatic speech recognition has been a subject of active research interest since last few decades. In the present paper, spoken Hindi (Indian national language) Paired Word Recognition (HPWR) has been examined with the help of intelligent hybrid computing scheme based on wavelet transform and Probabilistic Neural Network (PNN). This type of network is a combination of radial basis layer and a competitive transfer function layer, which picks up the maximum probabilities as a final result. For the experimental purpose, six hundred and fifty Hindi paired word samples from individuals with different gender and age groups have been recorded. Pre-processing procedure has been performed on the samples using accurate endpoint detection algorithm. For feature extraction of samples, wavelet transform has been used. PNN algorithm is used as a classifier. The proposed intelligent hybrid computing scheme based on wavelet-probabilistic neural network has produced practically good recognition rate.
- Inderscience Publishers
- Hindi paired word recognition using probabilistic neural network
Selecting the Right Air Quality Monitor
There are many types of air quality monitors available, but which one is the best choice for measuring gaseous air pollutant concentrations? There are two classes of such air quality monitors: sampling monitors and in-situ monitors (“in-situ” = “in the original position”). Sampling monitors utilises a manifold through which the air to be analysed is pumped. A small air sample is then enclosed in a cell where its molecular content can be analysed. The analysis method varies depending on...
Estimation of dead or live bacteria using online Bacteria Activity monitoring - Case Study
The BACTcontrol, a microLAN instrument, measures on-line bacterial enzyme activity in food and aquatic samples. Besides ß-DGlucuronidase, ß-Galactosidase and ß-Glucosidase to measure E.coli, Coliform and Enterococci activity respectively also alkaline phosphatase (ALP) activity is measured to determine Total Activity. The BACTcontrol TA test measures the metabolism activity of ALP enzyme that is produced in most of the well known aquatic microbial cells using the (MUP) fluorescent substrate. In...
World Oil: Holistic optimization approach improves coring efficiency, sample quality
To acquire a high-quality core in as few runs as possible, and reduce operational costs, a provider must maximize ROP while ensuring efficient, safe surface handling of the rock sample and coring assembly. To satisfy these requirements, HT30 Max, a full-gauge core barrel system with jam mitigation technology, has been introduced.To improve initial production and ultimate recovery, we must first fully understand the reservoir rock. Full-gauge coring is the first line-of-sight into a reservoir. The actual formation...
Automated Oil Particle Analysis Helps Prevent Gearbox Failures
The major issue for premature failure in wind turbine gearboxes is bearing failure, which leads to gearbox failure. A wind turbine gearbox will not survive if the oil is not clean and especially if the hard ferrous particles are not removed from around the bearings. The LaserNet 230 particle counter and ferrous debris monitor has been shown to be an excellent analytical tool for end users to be able to diagnose wear faults in various machine applications such as gear boxes, engines and transmissions. The wear...
Minestis - automatic domaining - has proven to be efficient with big datasets
Minestis offers a unique feature called Automatic Domaining which quickly groups borehole samples into domains in an automatic way. Those who have seen the tool run qualifies it as impressive. The classification of samples into geological domains is a fastidious and fairly subjective step in geological modeling. Geovariances and Mines Paris Tech have developed a combination of Geostatistical Hierarchical Clustering (‘GHC’) and Support Vector Machine (‘SVM’) in Minestis in order to...