Improved Accuracy of Automatic Speech Recognition System using Software and Hardware Co design

Journal Title: International Journal of Modern Engineering Research (IJMER) - Year 2013, Vol 3, Issue 2

Abstract

 Abstract: We Present Automatic Speech Recognition System For Human Machine Interaction By Using Hardware and Software Co design, The Entire Speech Signal Is Segmented Into a sequence Shorter Signal Is done By Future Extraction, This System Improves the Timing Performance by using Hardware Accelerator GMM (Gaussian mixture model), This hardware accelerator is performed by emission probability Calculation, In order to avoid large memory requirement and this accelerator adopts a double buffering scheme for accessing the acoustic parameters, The weighted finite state transducer (WFST) in Viterbi search model gives Word Sequence from Emission probability calculation. The word accuracy rate is preserved at 93.33%, as a part of recognizer is very suitable for Embedded Real time Application By Using New Adaptive Beam Pruning algorithm. Which is about four times faster than pure Software based system.

Authors and Affiliations

P Jayaseelan

Keywords

Related Articles

 Comparative Losses and Economic Feasibility of the Improved Onion Storage with Low Cost of Onion Storage Structure

 Onion produced in Kharif and Late Kharif season is not suitable for storage while onion produced in summer season can be stored upto 5-6 months and it can be brought in the during market rainy season i.e., from Jun...

 Enhancement in viscosity of diesel by adding vegetable oil

 Some time due to improper blending of different refinery distillate stream and variation in distillation range as well as cause of using different crude we are getting resulting diesel having various range of vis...

Novel Direct Switching Power Control Method of UPFC by Using Matrix Converter Based On SVPWM Techniques

This paper presents a direct Switching power control for three-phase matrix converters operating as unified power flow controllers (UPFCs). Matrix converters (MCs) allow the direct ac/ac power conversion without dc energ...

 A Detailed Modelingof a Five Parameters Model for Photovoltaic Modules

 In the present paper we interested at the parametric characterization of the five parameters model. However, we reductive the system of the three characteristic points under STC in one equation called fRsand one...

 Studies on effect of various operating parameters & foaming agents- Drying of fruits and vegetables

 Abstract: The foam mat drying is a good way of dehydrating liquids foods in short times. Due to the porous structure of the foamed materials, mass transfer is enhanced leading to shorter dehydration times. This tec...

Download PDF file
  • EP ID EP140978
  • DOI -
  • Views 84
  • Downloads 0

How To Cite

P Jayaseelan (2013).  Improved Accuracy of Automatic Speech Recognition System using Software and Hardware Co design. International Journal of Modern Engineering Research (IJMER), 3(2), 980-984. https://europub.co.uk/articles/-A-140978