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
Glyphosate and AMPA in drinking water
Carcinogenic or not? The broad-spectrum herbicide glyphosate is used all over the world in agriculture. Alongside farming, the chemical is also used for weed-killing in domestic gardens and in public and private spaces kept free from «vegetal invasion», such as railway tracks. Glyphosate has been used since the 1970s in pesticides and was hitherto thought to be harmless at typical levels of exposure. However, since the International Agency for Research on Cancer (IARC) – the specialized cancer-re...
Find out why Minestis domain modeling meets the support of resource geologists
Minestis provides geostatistics-based application for estimation domain modeling including automatic sample clustering into domains and implicit modeling of envelopes. It has never been so quick to achieve reliable domain modeling. The modeling of coherent estimation domains is a major area of integrated Mineral Resource Estimation. The description of variable behavior associated with mineralization processes helps delineating spatial envelopes, which facilitate grade interpolation, and fully defines mineralize...
New Automation Guide for Improved Titration Workflows
Find valuable tips and tricks on how to optimize your titration workflows in the new METTLER TOLEDO Automation Guide. Download the Titration Automation Guide today and learn how titration processes can be automated for highest efficiency and security in the laboratory. Modern laboratories look into automation to address the demands for high throughput and variety of samples and workflows. Automation is not only concerned with aspects of efficiency. It also supports the user in terms of quality and data security...
Case study - Low-flow groundwater sampling on a nuclear site
Nuclear licensed site use of low-flow groundwater sampling shows: Reduced time, reduced quantity of purge water – both thus reducing cost - and reduced risk of operator contact especially with potentially radioactive-contaminated purge water thanks to a self-contained enclosed system. One of the biggest headaches on site is the purge water and the expense of getting rid of it – after it has itself been analysed for radioactivity. Low flow sampling is helping contain and reduce the problems.On site...
Case study - LFG engine protection for Viridor
Rapid changes in landfill gas quality can damage the engines it powers. To keep watch, Viridor has installed static automatic gas analysis and reporting equipment supplied by Geotech at its Whitehead landfill site near Manchester. Every ten secondsthe equipment measures concentrations of CH4, CO2 and O2 and outputs the data in three, 4-20 mA channel signals. Control circuits receive the analyser signals and are set to shut down the landfill gas (LFG) engine before damage by a fast-changing gas mix. Gas thresholds...