.
 Objectives

 
The major objectives of the Resource Centre for Indian Language Technology Solutions, Indian Institute Technology Guwahati, are  to make available knowledge tools for North-Eastern languages, with particular emphasis on Assamese and Manipuri,  and the development of technologies and products that would enable computer processing of the Assamese and Manipuri languages. Detailed information about the objectives, and achievements made so far follows.

  To act as a repository of  knowledge tools  for Assamese and Manipuri.

A
website for North–Eastern languages has been developed, which features classification of 60 out of 150 existing languages of the North–Eastern states. Geographic and demographic information is also available. A Linguistic map of  North–Eastern India, where the size of the text is indicative of density of speakers has also been put up. Additionally , phonology and grammar of about 20 languages, with special emphasis on Assamese, online Assamese dictionary, Assamese fonts are also featured. Work on Manipuri dictionary is currently going on.

  To develop the  methodologies and tools for seamless integration of  language  processing tools with existing and evolving software development environment.

MS-Word support for Assamese has been developed. This technology uses the Inscript keyboard ,which is widely used., and can be used with Resource Centre for Indian Language Technology Solutions, Indian Institute Technology Guwahati custom Assamese fonts. The use of the Inscript keyboard layout will allow smooth migration from C-DAC to Microsoft technologies. Furthermore with all features of MS-Word available for use the overall editor becomes much more versatile. The same technology is to be used in conjunction with the Applet based dictionary search engine. The resource center intends  to develop the same support for Manipuri, and if required, other Indian languages.

To network with other Resource Centres  concerned with computer processing  of Indian languages, organizations  which can provide specialized knowledge, potential user agencies, and other interested educational  institutions.

Currently the resource center has tie-ups with the
Dept. of Assamese, Gauhati University  and Indian Statistical Institute, Kolkata. Assamese OCR Technology Transfer from Indian Statistical Institute, Kolkata has been negotiated  with the objective of investigating into refinement of  the OCR technology to suit Assamese and Manipuri

 To develop a wide range of technologies and products  that would facilitate computer processing of the Assamese and Manipuri languages.

Some of the products  developed are Dictionaries, Assamese fonts, Assamese language support for MS-Word, Assamese Morphological Analyzer ,Online Search engine for the dictionary .  Spell Checkers for both Assamese and  Manipuri, and a Chat Server having simple English to Assamese translation facility, and vice versa are under development. The spellchecker and morphological analyzer will be used in conjunction with the web-based dictionary to provide additional support for the MS-Word Assamese  enabled  editor.

  To create awareness and organize training programmes for agencies and personnel concerned with the deployment of Indian language processing systems.

In this context, a training program on Web Page Design & Office Automation using Assamese was held from 15
th to –16th March, 2002 . It’s major objective was to orient and  encourage participants to use Assamese  for E-governance.

 
To facilitate language technology research in Machine Aided Translation, Optical Character Recognition, Text-to-Speech, and Speech Recognition  for Assamese and Manipuri.

Research has been conducted in the field of  Speech Recognition for Assamese, and simple Voice Commands for drawing geometrical figures have been developed. These commands can be used for Drawing, Resizing, and Colouring of shapes. Microsoft Speech   API technology has been used , and XML  has been used for representing the (command) grammar. Investigations into using Assamese  for simple editor commands  are currently being made. Assamese Speech Codebooks for commonly used words are being developed. These will be used for speech modelling and recognition
.

 To organize IT localization  clinics  for  small businesses  to provide  consultancy on  use of Indian language tools in developing IT solutions and to take up development of requisite niche technologies.
 


-