Localization of Languages for eGovernance and RTIA


Text-to-Speech and Automatic Speech Recognition in Indian Languages (Matrubhasha)

Text-to-Speech and Automatic Speech Recognition in Indian Languages (Matrubhasha)


In the present era of human computer interaction, the educationally under privileged and the rural communities of India are being deprived of technologies that pervade the growing interconnected web of computers and communications. One good solution for this problem would be computers talking to the common man in the language he is comfortable to communicate in. Indian population has a significant percentage of people who are educationally under-privileged. There are still quite a large number of areas where people do not have the capabilities of 3R’s. The digital divide under such circumstances is constantly on a rise, where on one hand we claim that India is leading in IT and on the other hand, the advances we make are totally inaccessible by a large number of countrymen. Under such circumstances, we cannot expect rural/educationally under-privileged countrymen to use computers and IT products unless we remove the need of being literate, which exists as a barrier between them and computers.

Major Issues

In this information age, storage and retrieval of information in a convenient manner has gained importance. Because of the near-universal adoption of World Wide Web as a repository of information for unconstrained and wide dissemination, information is now broadly available on the Internet and is accessible from remote sites. However, the interaction between the computer and the user is largely through keyboard and screen-oriented systems. In the current Indian context, this restricts the usage to a miniscule fraction of the population, who are both computer-literate and conversant with written English. In order to enable a wider proportion of population to benefit from Information technology, there is a dire need for an interface other than keyboard and screen-interface that is widely in use at present. Speech, being a natural means of communication among human beings, can also provide a consummate platform for man-machine interaction. It is also desirable that human-machine interface permits one’s native language of communication. In the context of a multi-lingual country like India, this can be of immense value to our country where literacy rate is considerably low. Certain efforts are currently been undertaken to develop OS and applications, which support the local languages. Localization efforts have been undertaken by most of the leading OS vendors and promoters, which include Microsoft (Windows), Red Hat (Linux), NCST (Indix), IIT Madras (IndLinux) etc. These OS’s support some of the leading Indian languages by using international coding standards (Unicode). Speech technologies promise to be the next generation user interface. Software application having speech and voice recognition abilities have a better chance to communicate with a large percentage of population which include educationally under-privileged, visually challenged and computer illiterates, if these applications can speak and understand the native language. Hence we put forward the API (Application Programming Interface) Model based on Unicode for Text to Speech Synthesis and Automatic Speech Recognition in Indian languages.

Why Unicode?

Unicode is the international standard that encodes characters in 16 bits as opposed to the ASCII standard encoding 8 bits. The Unicode Standard is the universal character-encoding standard used for representation of text for computer processing. Unicode provides a consistent way of encoding multilingual plain text. The design of Unicode is based on the simplicity and consistency of ASCII but goes far beyond ASCII’s limited ability to encode only the Latin alphabet. The Unicode Standard provides the capacity to encode all of the characters used for the written languages of the world. To keep character coding simple and efficient, the Unicode standard assigns each character a unique numeric value and name. It has laid out provisions for encoding all scripts in the world, and has been agreed upon by all major software providers, as well as international governments, as the most suitable character representation for all major character sets. The advantage of using Unicode as character set will enable the TTS engine to recognize different Indian languages in the same document or character string, where as using a separate encoding format for each of the languages would not support the same. All the content development applications such as Office Suite’s, Star-Office, and Open-Office etc. are already being localized using Unicode. Unicode is already playing a significant part with respect to localization and internationalisation. Since it handles the characters for all languages in a uniform way, it avoids the complexities of different character code architectures. All of the modern operating systems, from PCs to mainframes, support Unicode now or are actively developing support for it. The same is true of databases, as well. In this scenario, Unicode would be the best option to go with, in the context of the current problem being discussed about!

Why API Model?

While we talk about IT being completely in-reach of the common countrymen, it is not just enough to have an operating system, or one specific application that supports local language speech synthesis or speech recognition. The point is that in the current juncture where in the growth and impact of technology is day by day rising exponentially; any software application is a candidate for localization. Hence, we put forward this API model so that any software developer can incorporate speech capabilities into one’s application, thus extending the reach of the product even to the masses.

Mr. Raman and the Matrubhasha Team


October 23, 2006 - Posted by | Govt. of INDIA

No comments yet.

Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: