Under TDIL Programme of DeitY, Technology Development for Indian Languages has the objective of developing Information Processing Tools and Techniques to facilitate human-machine interaction without language barrier. Presently TDIL Programme is working  on following research areas with the aim of enabling masses to build a knowledge society and ensuring communication without language barrier. These technologies are disseminated through tdil-dc.in.

Machine Translation (MT)

The alpha versions of Machine Translation systems for some of the language pairs (English-Hindi, English-Bangla, English-Malayalam, English-Punjabi, English-Urdu, English-Marathi, English-Oriya, English-Tamil, Urdu-Hindi, Punjabi-Hindi, Hindi-Punjabi, Telugu-Tamil) in tourism domain have been developed and simultaneously work in other languages is in progress. To access the system click here.

Anuvadaksh (English to Indian Language Machine Translation System)
AnglaBharati (English to Indian Languages Machine Translation)
Indian Language to Indian Language Machine Translation.

Speech Based Access For Agricultural Commodity Prices (ASR)

It is a telephony application to provide real-time local prices of commodities with the support of voice query for the ease of farmers.Currently it is available in Marathi , Telugu, Assamese, Bengali,Hindi.

Text to Speech System (TTS)

Text to Speech (TTS) system which is integrated with a screen reader, has been developed in six Indian languages namely Hindi, Bangla, Marathi, Tamil, Telugu and Malayalam. This will help the visually challenged section of the society to have information access in Indian languages.

To request the TTS software DVD click here.

Optical Character Recognition (OCR)

Optical Character Recognition (OCR) is a utility tool for digitizing the content and is essential for development of knowledge networks such as digital libraries. Currently OCR is hosted in Bangla, Devanagari, Gurumukhi, Kannada, Malayalam and Telugu.

To know more about the system click here.

On-line handwriting recognition system (OHWR)

OHWR is a useful tool that converts the written strokes of an individual into editable text thus bypassing the need of a keyboard for text entry. This system is very useful in the field data collection ,currently supported languages are Bangla,Malayalam,Kannada,Hindi, Tamil and Telugu.

Sandhan

Sandhan is a monolingual search system for tourism domain in five Indian languages viz., Bengali, Hindi, Marathi, Tamil and Telugu.

To know more click here.

TDIL Programme of DeitY has been looking forward for more industrial involvement & association for the productization of these research outcomes. The aim of this initiative is to take the work forward and benefit the masses to a large extend. To accomplish this, the government has formed a Technology Evangelization Committee for Language Technologies which will do the Assessment/Evaluation of the developed technologies for possible technology transfer. The committee will assess the potential industry partners and will monitor the commercialization of these research outcomes.

TDIL Pragramme welcome industry for their valuable feedback/interest on the above listed technologies for possible commercialization. We are looking forward for more and more association with IT Industry to proliferate the awareness & availability of Indian language products & technologies  to benefit the masses. Expectation from industry is to take forward these technologies with a commitment to come out with the product or service which will make the world-wide knowledge accessible to the common man.