Isolated and continuous bangla speech recognition: implementation, performance and application perspective

Includes bibliographical references (page 6).

Библиографические подробности
Главные авторы: Hasnat, Md. Abul, Mowla, Jabir, Khan, Mumit
Другие авторы: Center for Research on Bangla Language Processing (CRBLP), BRAC University
Формат: Статья
Язык:English
Опубликовано: BRAC University 2010
Предметы:
Online-ссылка:http://hdl.handle.net/10361/331
id 10361-331
record_format dspace
spelling 10361-3312019-09-29T05:27:15Z Isolated and continuous bangla speech recognition: implementation, performance and application perspective Hasnat, Md. Abul Mowla, Jabir Khan, Mumit Center for Research on Bangla Language Processing (CRBLP), BRAC University Bangla speech recognition Bangla language processing Includes bibliographical references (page 6). Research on automatic speech recognition has been approach progressively since 1930 and the major advances are since 1980 with the introduction of the statistical modeling of speech with the key technology Hidden Markov Model (HMM) and the stochastic language model (B. H. Juang, 2005). However, the existing reported research works on Bangla speech recognition didn’t yet incorporate the HMM technique and language model. This paper presents two different type of Bangla speech recognition from the implementation, performance and application perspective. We used HMM technique for pattern classification and also incorporate stochastic language model with the system. At the signal preprocessing level we perform adaptive noise elimination and end point detection. Spectral feature vectors such as Mel Frequency Cepstral Coefficients(MFCC) with the addition of first and second order coefficients are extracted from each speech wave signal. HMM is used for pattern classification. The system is implemented using the Cambridge Hidden Markov Modeling Toolkit (HTK) (S. Young, 2001-2005). Md. Abul Hasnat Jabir Mowla Mumit Khan 2010-10-05T05:11:02Z 2010-10-05T05:11:02Z 2007 2007 Article http://hdl.handle.net/10361/331 en 6 pages application/pdf BRAC University
institution Brac University
collection Institutional Repository
language English
topic Bangla speech recognition
Bangla language processing
spellingShingle Bangla speech recognition
Bangla language processing
Hasnat, Md. Abul
Mowla, Jabir
Khan, Mumit
Isolated and continuous bangla speech recognition: implementation, performance and application perspective
description Includes bibliographical references (page 6).
author2 Center for Research on Bangla Language Processing (CRBLP), BRAC University
author_facet Center for Research on Bangla Language Processing (CRBLP), BRAC University
Hasnat, Md. Abul
Mowla, Jabir
Khan, Mumit
format Article
author Hasnat, Md. Abul
Mowla, Jabir
Khan, Mumit
author_sort Hasnat, Md. Abul
title Isolated and continuous bangla speech recognition: implementation, performance and application perspective
title_short Isolated and continuous bangla speech recognition: implementation, performance and application perspective
title_full Isolated and continuous bangla speech recognition: implementation, performance and application perspective
title_fullStr Isolated and continuous bangla speech recognition: implementation, performance and application perspective
title_full_unstemmed Isolated and continuous bangla speech recognition: implementation, performance and application perspective
title_sort isolated and continuous bangla speech recognition: implementation, performance and application perspective
publisher BRAC University
publishDate 2010
url http://hdl.handle.net/10361/331
work_keys_str_mv AT hasnatmdabul isolatedandcontinuousbanglaspeechrecognitionimplementationperformanceandapplicationperspective
AT mowlajabir isolatedandcontinuousbanglaspeechrecognitionimplementationperformanceandapplicationperspective
AT khanmumit isolatedandcontinuousbanglaspeechrecognitionimplementationperformanceandapplicationperspective
_version_ 1814309825657438208