Speech Recognition in Marathi Language on Android O.S.

Abstract

Speech is the basic mode of communication among human beings. For about four decades human beings have been dreaming of an ”intelligent machine” which can master the natural speech. Speech recognition is the process of recognizing the spoken word to perform particular task. It is expected to have a human computer dialogue in local languages like Marathi, Hindi, Telugu etc. In this paper we are going to study different methods for feature extraction and comparison techniques for ASR systems and select the most appropriate technique for improving the accuracy of the system. An experimental database of phonemes(some vowels and consonants) is collected for speaker dependent system. MFCC are extracted from speech signal of the spoken words. DTW algorithm is used for measuring similarity between two word sequences, which may vary in time or speed to construct the minimum distance warp path.

Authors and Affiliations

Saroj B. Jadhav, Jayshree Ghorphade and Rishikesh Yeolekar

Keywords

Related Articles

QOS ORIENTED VERTICAL HANDOFF FOR WIMAX/WLAN IN ADHOC WIRELESS NETWORK

Vertical Handoff (VHO) scheme is designed based on the interworking architecture of WLAN/WIMAX which aims to provide always the best Quality of Service (Qos) for users. The performance of applications and network co...

Implementation of Parallel MAC Unit in 8*8 PreEncoded NR4SD Multipliers

This paper describes a merged multiplyaccumulate (MAC) hardware along with the pre-encoded non redundant radix-4 signed digit encoding (NR4SD) multiplier. New designs of pre-encoded multipliers are explored by off-lin...

Issues and Dependencies on Affect Data Models For Assessment of Disorders- A Survey

Analysis of free-form data has always been a challenge. In that, data depicting affects in hidden form and/or in various modes complicates the task of mining to identify and analyze relevant affects from the input. A...

Fuzzy Decision Tree Classification Based On The Peano Count Tree Representation

Image classification is one of the important tasks in remote sensing image interpretation in which the image pixels are classified. Many organizations have large quantities of spatial data collected in various applic...

Automatic Grinding Control using Adaptive Minimum Variance Control Theory with Temperature Fuzzy Controlling

The paper displays the inference of a new multivariable adaptive controller, which minimizes an expense function, incorporating input framework, yielding more set points. It gives an adaptive system which ensures mi...

Download PDF file
  • EP ID EP27965
  • DOI -
  • Views 268
  • Downloads 0

How To Cite

Saroj B. Jadhav, Jayshree Ghorphade and Rishikesh Yeolekar (2014). Speech Recognition in Marathi Language on Android O.S.. International Journal of Research in Computer and Communication Technology, 3(8), -. https://europub.co.uk/articles/-A-27965