I wanted to announce a first release of an open source project called Skrybot doMowy, which is based on a well known decoder Julius. This software is a result of 3 year research and is a LVCSR dictation system for Windows platform available from http://sourceforge.net/projects/skrybotdomowy/
The aim of this software which code is written in C# is to allow other fellow software engineers to write their own plugins and extensions to dictation system.
Currently the program supports only Polish acoustic and language models making it possible to use for dictation of emails or simple documents. It has a live view of a microphone input allowing the user to monitor the volume of their speech.
One of the other aims was to make speech dictation available for free to everyone with a quality similar to commercial programs.
I encourage other researchers or programmers to get into contact with me and and potentially develop other language GUI versions as well as acoustic and language models for their native languages. We are soon considering supporting British English version of this software, however we still need to develop such models.
More details can be found on http://skrybot.pl/en/
>I wanted to announce a first release of an open source
>project called Skrybot doMowy, which is based on a well
>known decoder Julius.
I noticed that your commercial skrybot speech recognition system also runs on Linux... does it use the same code base that is used in skrybotdomowy (GPL 2; on Source Forge)? if so, are you using something like mono to get it to operate on Linux?
Skrybot doMowy is basicall a GUI front end for a slightly modified Julius decoder, so the models are compliant in general with Julius with some small changes. GUI is written with .NET 2.0 and DirectX managed code for DirectX 9.0c
DirectX is used for recording audio from microphone as well as for presentation of recorded wave. I think it should not be too difficult to port it to Linux, however there could be a problem with accessibility of DirectX version for Linux (if any exists?). If none is available then recording of speech and presentation of oscillogram would have to be replaced by other classes.
I am happy to anwser any more questions regarding this project.
Thanks for the clarification
Hello - if anyone is interested I recently published a brand new version of SkryBot - open source speech dictation system in Polish. The program is written in C# and C++ and uses a modified Julius engine. It can be downloaded from http://sourceforge.net/projects/skrybotdomowy/
How can I reduce dictionary in your Polish model?
I need only few words and for my usage the recognition
seams takes too long...
Great work btw!