Speech & Natural Language Processing

C-DAC has been a pioneer institute in developing and proliferating the use of Indian languages on computers. This technology is now extended to include multimedia and multilingual computing solutions covering a wide range of applications such as publishing and printing, word processing, office application suites with language interfaces for popular third party softwares on various operating platforms, E-mail, MT, and multimedia content in Indian languages. These have been successfully commercialized. Many a times all these activities are intermingled with each other. Therefore, often developing a system in NLP means to either start working from scratch or use the utilities/subprograms from open source with appropriate modifications. Because of this limitation, the speed of development is slow. To overcome these problems two types of goals were worked out by DIT, Short Term and Long Term. In short term goal, smaller applications such as Desktop publishing were to be developed for all 22 ILs and make them available to common masses free of charge. In Long term Goals 5 mission mode projects were proposed in EILMT, IL-ILMT,OCR/OHR, CLIA and Human resource development in Language Technology. CDAC Noida in participating in all five projects and successfully completed tasks defined in 1st phase. CDAC is also taking up projects in Speech Processing and Digital Library.