CFP last date
20 January 2025
Reseach Article

Marathi Isolated Digit Recognition System using HTK

Published on January 2018 by Devyani S. Kulkarni, Ratnadeep R. Deshmukh, Vandana L. Jadhav Patil, Pukhraj P. Shrishrimal, Swapnil D. Waghmare, Aaron M. Oirere
International Conference on Cognitive Knowledge Engineering
Foundation of Computer Science USA
ICKE2016 - Number 2
January 2018
Authors: Devyani S. Kulkarni, Ratnadeep R. Deshmukh, Vandana L. Jadhav Patil, Pukhraj P. Shrishrimal, Swapnil D. Waghmare, Aaron M. Oirere
d033541c-bb8b-4bb4-9206-62d3a5f05c6e

Devyani S. Kulkarni, Ratnadeep R. Deshmukh, Vandana L. Jadhav Patil, Pukhraj P. Shrishrimal, Swapnil D. Waghmare, Aaron M. Oirere . Marathi Isolated Digit Recognition System using HTK. International Conference on Cognitive Knowledge Engineering. ICKE2016, 2 (January 2018), 42-45.

@article{
author = { Devyani S. Kulkarni, Ratnadeep R. Deshmukh, Vandana L. Jadhav Patil, Pukhraj P. Shrishrimal, Swapnil D. Waghmare, Aaron M. Oirere },
title = { Marathi Isolated Digit Recognition System using HTK },
journal = { International Conference on Cognitive Knowledge Engineering },
issue_date = { January 2018 },
volume = { ICKE2016 },
number = { 2 },
month = { January },
year = { 2018 },
issn = 0975-8887,
pages = { 42-45 },
numpages = 4,
url = { /proceedings/icke2016/number2/28955-6094/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Proceeding Article
%1 International Conference on Cognitive Knowledge Engineering
%A Devyani S. Kulkarni
%A Ratnadeep R. Deshmukh
%A Vandana L. Jadhav Patil
%A Pukhraj P. Shrishrimal
%A Swapnil D. Waghmare
%A Aaron M. Oirere
%T Marathi Isolated Digit Recognition System using HTK
%J International Conference on Cognitive Knowledge Engineering
%@ 0975-8887
%V ICKE2016
%N 2
%P 42-45
%D 2018
%I International Journal of Computer Applications
Abstract

This paper proposes a system of isolated digit recognition for Marathi language using HTK approach. The database used contains 800 utterances of 40 individuals. Among them 20 are female and 20 are male. For training the acoustic features of the database powerful MFCC i. e. Mel frequency cepstral coefficients technique is used. We have used word level model to recognize the Marathi isolated digits. The result analysis of the system shows 99. 75% recognition with 48. 75% accuracy.

References
  1. V. B. Waghmare, R. R. Deshmukh, P. P. Shrishrimal and G. B. Janvale "Development of Isolated Marathi Words Emotional Speech Database" International Journal of Computer Applications 94(4):19-22, May 2014.
  2. Devyani S. Kulkarni, Ratnadeep R. Deshmukh, and Pukhraj P. Shrishrimal. "A Review of Speech Signal Enhancement Techniques. " International Journal of Computer Applications 139. 14 (2016).
  3. Pukhraj P. Shrishrimal, Ratnadeep R. Deshmukh and Vishal B. Waghmare "Indian Language Speech Database: A Review" . International Journal of Computer Applications 47(5):17-21, June 2012.
  4. Devyani S. Kulkarni, "HTK Based Speech Recognition Systems for Indian Regional languages: A Review", International Research Journal of Engineering and Technology (IRJET), Volume 03 Issue 06, June-2016.
  5. P. C. Woodland et al "Large Vocabulary Continuous Speech Recognition Using HTK", Acoustics, Speech and Signal Processing, 1994 ICASSP-1994.
  6. D. Jurafsky and J. H. Martin, "HMMs and Speech Recognition," in Speech and Language Processing, S. Russell and P. Norving, Dorling Kindersley Pvt. Ltd. , India, 2000, pp. 261-309.
  7. The HTK Book. By Steve Young, Gunnar Evermann, Mark Gales, Thomas Hain, Dan Kershaw, Gareth Moore, Julian Odell, Dave Ollason, Dan Povey, Valtcho Valtchev and Phil Woodland.
Index Terms

Computer Science
Information Sciences

Keywords

Htk Hmm Acoustic Model Digit Recognition Grammar Mfcc