Our Vision

The primary goal of our Internet-Accessible Speech Recognition Technology project is to create a freely available, modular, state-of-the-art speech recognition system that can be easily modified to suit your research needs. The system is built on top of a vast hierarchy of general purpose C++ classes that implement generic math, data structure, and signal processing concepts. Click here for an official version of our public domain license statement.

In addition to the core recognition software, we distribute other tools that minimize the effort required to use our system to recreate important benchmarks:
Featured Photo
Production System Release r02_n00 Our long awaited and much anticipated new release of ISIP Production System is finally here! This release, titled r02_n00, solves compatbility problem with new GCC and is fully compatible with the latest GNU C++ compiler GCC4.1.1. (It has been tested in both GCC4.1.0 and GCC4.1.1.) Since 3.4 version, G++ is much closer to full conformance to the ISO/ANSI C++ standard. This means, among other things, that a lot of code which used to be accepted in previous versions will now be rejected. It costed us months for all the code re-writing and the testing. For detailed information about this release and instructions for downloading and installing, click here.

Speech Recognition Resources

  • Data, Models, Lexicons, and Other Resources
  • Performance and Computing Guidelines
  • Courses, Seminars, and Presentations
  • Relevant Internet-Based Resources

    Featured Partners