BUILDING ROBOT VOICE CONTROL TRAINING METHODOLOGY USING ARTIFICIAL NEURAL NET
Journal: International Journal of Civil Engineering and Technology (IJCIET) (Vol.8, No. 10)Publication Date: 2017-10-18
Authors : RAMI MATARNEH SVITLANA MAKSYMOVA ZHANNA DEINEKO; VYACHESLAV LYASHENKO;
Page : 523-532
Keywords : Building Robot; Voice Control; Motion Commands; Artificial Neural Net;
Abstract
The article describes using artificial neural net for speech recognition. This is necessary for the automation of construction work. We selected multi-layer perceptron for separate words recognition tasks. We researched different forms of hidden layer. And we made a conclusion that for voice commands analysis tasks solution it is expedient to use multi-layer perceptron with linearized functions (the best result was achieved using model with hidden layer with linearized hyperbolic tangent function). We use this experience to train robots in civil engineering.
Other Latest Articles
- Polymerase chain reaction versus culture in the diagnosis of extrapulmonary tuberculosis-A comparative study
- A STUDY ON THE EFFECT OF BAGASSE ASH TERNARY CONCRETE ON DRYING SHRINKAGE OF CONCRETE
- CONTROL OF MULTI DRUG RESISTANT TUBERCULOSIS: PRINCIPLES AND PRACTICES
- PUS culture isolates and their antibiotic sensitivity at a Tertiary Care Hospital in Hyderabad Karnataka Region
- RECENT ADVANCES IN HISTOPATHOLOGY: 23
Last modified: 2018-04-20 15:25:08