47
Niladri Sekhar Dash, Arpita Chakraborty
Research Cell : An International Journal of Engineering Sciences, Issue December 2016
ISSN: 2229-6913 (Print), ISSN: 2320-0332 (Online) -, Web Presence: http://www.ijoes.vidyapublications.com
© 2016 Vidya Publications. Authors are responsible for any plagiarism issues.
Digital Pronunciation Dictionary in Bangla for Computer
Assisted Language Teaching, E-Learning, and Speech Technology
Niladri Sekhar Dash
1
and Arpita Chakraborty
2
Linguistic Research Unit, Indian Statistical Institute, Kolkata
1
Intern at LRU, ISI, Kolkata, S/W Developer at R&D Lab, Kolkata
2
Email: ns_dash@yahoo.com
1
, c.arpita23@gmail.com
2
ABSTRACT
It will be a nice learning experience for the Bangla language learners if an on-line Bangla
education system is supported with a Digital Bangla Pronunciation Dictionary (DBPD),
which is accessed in classroom and at home, as the case may be, as one of the most useful
reference guides for learning standard and acceptable pronunciation of Bangla words.
Keeping this idea at background, in this paper, we have made an attempt to report the design
architecture of the proposed digital Bangla pronunciation dictionary, which is being
developed with a large lexical database of nearly hundred thousand words that are directly
obtained from a digital corpus of Bangla written texts as well as from other digital lexical
sources available in the language. This is perhaps the first attempt ever made for any of the
Indian languages with a mission for serving the Bangla speakers as well as Bangla language
learners with better learning resources and devices for the language across the world. The
immediate application of the resource is visualized as a tool for e-governance and on-line
language teaching where the learners can access this device to address various linguistic
purposes including spelling, pronunciation, part-of-speech, meaning, and usage of words.
Keywords: pronunciation, part-of-speech, transliteration, orthography, IPA, meaning
1. INTRODUCTION
The Digital Bangla Pronunciation Dictionary (DBPD) that we are engaged in developing is
capable of capturing the unique aspects of the pronunciation of the Bangla words with due
reference to their parts of speech, meaning, and usage. At the orthography level each and
every headword included in this dictionary is represented in two different scripts:
(a) The Unicode compatible standard Bangla script for the native Bangla speakers and the
others who know the language and its script.
(b) The Indic Roman script marked with diacritics for those people who do not know the
Bangla script but know the Indic Roman characters.
On the other hand, the pronunciation of the headwords, following the process adopted in the
Oxford English Dictionary, is represented in the following three ways: