Slashdot Mirror

← Back to Stories (view on slashdot.org)

Open Source Speech Recognition

Posted by ryuzaki0 on from the hello-computer dept.

bedahr writes "The first version of the open source speech recognition suite simon was released. It uses the Julius large vocabulary continuous speech recognition to do the actual recognition and the HTK toolkit to maintain the language model. These components are united under an easy-to-use graphical user interface. Simon can import dictionaries directly from wiktionary (a subproject of wikipedia) or from files formated in the HADIFIX- or HTK format and grammar structures directly from personal texts. It also provides means to train the language model with new samples and add new words."

1 of 140 comments (clear)

  1. Re:been playing with it by Antique+Geekmeister · · Score: 0, Offtopic

    Don't you mean "not watching Star Trek: Deep Space Nine" and "watching the original material they actually stole it from"? When I look at the pilots for Babylon 5 and the major plot lines the director had already included, and compare them to the later-produced byt better-funded, and thus first to be seen Deep Space Nine, the similarity is so striking that it implies theft by Paramount iv the director's ideas.

    This sort of thing is also unfortunately common for new directors and authors when they pitch their ideas to a major studio. It also happens quite a deal in software, where a market niche is filled by a big company before a small company can get their ideas to market, despite the NDA's signed by both when discussing the concept.