CFP last date
21 October 2024
Reseach Article

Speech Recognition System Architecture for Gujarati Language

by Jinal H. Tailor, Dipti B. Shah
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 138 - Number 12
Year of Publication: 2016
Authors: Jinal H. Tailor, Dipti B. Shah
10.5120/ijca2016909049

Jinal H. Tailor, Dipti B. Shah . Speech Recognition System Architecture for Gujarati Language. International Journal of Computer Applications. 138, 12 ( March 2016), 28-31. DOI=10.5120/ijca2016909049

@article{ 10.5120/ijca2016909049,
author = { Jinal H. Tailor, Dipti B. Shah },
title = { Speech Recognition System Architecture for Gujarati Language },
journal = { International Journal of Computer Applications },
issue_date = { March 2016 },
volume = { 138 },
number = { 12 },
month = { March },
year = { 2016 },
issn = { 0975-8887 },
pages = { 28-31 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume138/number12/24433-2016909049/ },
doi = { 10.5120/ijca2016909049 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T23:39:31.301789+05:30
%A Jinal H. Tailor
%A Dipti B. Shah
%T Speech Recognition System Architecture for Gujarati Language
%J International Journal of Computer Applications
%@ 0975-8887
%V 138
%N 12
%P 28-31
%D 2016
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Speech recognition is an area of Natural Language Processing and Artificial Intelligence. To achieve good accuracy and efficiency of Automatic Speech Recognition (ASR) system for Indian Gujarati language is challenging task due to its morphology, language barriers, different dialects, and unavailability of resources. This paper presents proposed architecture of ASR for Gujarati language. Raw input data have been collected from 4 male and 2 female who belongs from age between 18 to 36 years to prepare dataset for training purpose. The goal of Speech recognition system is to make machines capable enough to operate in natural languages. ASR is a system to convert vocalized form to visualized form using different computational devices. This convincing approach is useful to the people having disabilities deaf or inability to use input device. In this paper we have used Hidden Markov Model Toolkit HTK Tool to measure performance and error parameters. The system implementation analyzed WR (Word Recognition Rate) 95.9% and WER (Word Error Rate) as 5.85 % in Lab environment. For the open noisy environment calculated WR was 95.1% and WER found 7.40%.

References
  1. Akila A.,E. Chandra. , - “Isolated Tamil Word Speech Recognition System Using HTK”, International Journal of Computer Science Research and Application, Vol. 3, Issue 2,Pages 30-38
  2. C.Vimala, M.Krishnaveni , 2012, Continuous Speech Recognition system for Tamil language using monophone-based Hidden Markov Model , Proceedings of the Second International Conference on computational science, Engineering and Information Technology CCSEIT’12 pp 227-231.
  3. Chowdhury, S., ―”Implementation of Speech Recognition System for Bangla”, BRAC University, DHAKA, Bangladesh, August 2010.
  4. Daines D., - “An Architecture for Scalable, Universal Speech Recognition”. PhD Thesis, School of Computer science, Carnegie Mellon University, USA, 2011
  5. Durbin M., & Cardona G., (1968) “A Gujarati Reference Grammar Language”, 44(2), 411
  6. Hasnat, M., Molwa, J.,Khan, M., ―”Isolated and Continuous Bangla Speech Recognition: Implementation, Performance and application perspective”,2007.
  7. Hidden Markov Model Toolkit [HTK] downloaded from http://htk.eng.cam.ac.uk/
  8. Kumar, K.,Aggarwal R., ―”Hindi Speech Recognition System Using HTK”, International Journal of Computing and Business Research, ISSN (Online): 2229-6166, Volume 2 Issue 2, May 2011.
  9. Kumar R., Singh C., Kaushik S., ―”Isolated and Connected Word Recognition for Punjabi Language using Acoustic Template Matching Technique‖, 2004.
  10. Laxmi A. and Hema A Murthy,2006 A Syllable Based Continuous Speech Recognition for Tamil, INTERSPEECH – ICSLP, Pennsylvania,pp 1878-1881
  11. M. R. Hassan, B. Nath and M. Ala Uddin Bhuiyan, “Bengali Phoneme Recognition: A New Approach”, Proc. 6th ICCIT, Dhaka, 2003.
  12. Nadungodage T., Weerasinghe, R., ―Continuous Sinhala Speech Recognizer‖, Conference on Human Language Technology for Development, Alexandria, Egypt, May 2011.
  13. Pandit P., Bhatt S., - “Automatic Speech Recognition of Gujarati Digits using Dynamic Time Warping”, International Journal of Engineering and Innovative Technology, Vol. 3, Issue 12, June 2014
  14. Sarfraz H., Hussain S., Bokhari R., Raza A, Ullah I., Sarfraz Z., Pervez S., Mustafa A., Javed I., Parveen R., ―”Large Vocabulary Continuous Speech Recognition for Urdu”, International Conference on Frontiers of Information Technology, Islamabad, 2010.
  15. Syama R, Suma Mary Idikkula (2008) “HMM Based Speech Recognition System for Malayalam”, ICAI’08 – The 2008 International Conference on Artificial Intelligence, Monte Carlo Resort, Las Vegas, Nevada, USA (July 14-17, 2008)
Index Terms

Computer Science
Information Sciences

Keywords

Acoustic Model Hidden Markov Model Gujarati Speech-To-Text