Free recognition software for linux

Modular Audio Recognition Framework is a general cross-platform framework with a collection of algorithms for audio (voice, speech, and sound) and natural language text analysis and recognition, along with sample applications (identification, NLP, etc.) of its use.
MARF may act as a library in applications or be used as a source for learning and extension. A few example applications are provided to show how to use the framework.
There is also a detailed manual and the API references in the javadoc format as the project tends to be well-documented. MARF and its applications are released under a BSD-style license.
Enhancements:
- This release features a number of bugfixes and the completion of integration for a couple feature requests.
- It passes well through the standard testing runs.

Kognition is an omnifont OCR software for KDE. It is the result of two diploma theses about omnifont optical character recognition which are included as documentation (in German).

Due to the fact that each step of the OCR process can be visualized you can get a quick idea of how OCR works and where the problems lie.

However the program may be of minor/no use for end users in its current state.

Techisa Desktop Environment is a lightweight alternative desktop environment developed using Qt.
The projects goal is to provide users with a comfortable environment using as few resources as possible. Only a Brazillian Portuguese translation is currently available.
Enhancements:
- Better support for KDE desktop files.
- Improved recognition of KDM/GDM sessions.
- New icon search paths.
- Enhancements to the TDE menu.
- Better handling of links and properties.
- TDESU shows correct error codes.
- Thumbnails.
- A tree view in the file browser. tdeopen accepts new parameters: [file name] directly executes a file or associated application, and -f [source] [destination] shows a popup allowing user to copy, move, or link.

Speech::Recognizer::SPX::Server is a Perl module for writing streaming audio speech recognition servers using Sphinx2.

SYNOPSIS

my $sock = new IO::Socket(... blah blah blah ...);
my $log = new IO::File(server.log);
my $audio_fh = new IO::File(speech.raw);
my $srvr
= Speech::Recognizer::SPX::Server->init({ -arg => val, ... }, $sock, $log, $verbose)
or die "couldnt initialize sphinx2: $!";

my $client = new IO::Socket;
while (accept $sock, $client) {
next unless fork;
$srvr->sock($client);
$srvr->calibrate or die "couldnt calibrate audio stream: $!";
while (!$done && defined(my $txt
= $srvr->next_utterance(sub { print $log "listeningn" },
sub { print $log "not listeningn },
$audio_fh))) {
print "recognized text is $txtn";
...
}
$srvr->fini or die "couldnt shut down server: $!";
exit 0;
}

This module encapsulates a bunch of the stuff needed to write a Sphinx2 server which takes streaming audio as input on an arbitrary filehandle. Its not meant to be flexible or transparent - if you want that, then read the code and write your own server program using just the Speech::Recognizer::SPX module.

The interface is vaguely object-oriented, but unfortunately it is presently not possible to create multiple instances of Speech::Recognizer::SPX::Server within the same process, due to severe limitations of the underlying Sphinx-II library. You can, however, create multiple distinct servers with judicious use of fork, as shown in the example above.

It is possible that this will be fixed in a future release of Sphinx-II.

ArtistX is a comfortable way of trying multimedia GNU/Linux softwares without any installation. ArtistXs goal is to show multimedia creators that the world of GNU/Linux multimedia softwares is going further and further every day, sometimes faster than proprietary operating systems and softwares.
Since we know you have very limited time resources weve setup everything you need to test free multimedia softwares in a live cd/dvd which boots directly a complete GNU/Linux system without affecting your current installation (macs need virtualization to emulate a x86 computer): when you end your tests just reboot and ArtistX will be gone forever (except if you deserve it a second try...).
Software included in this site and in the live cd/dvd:
- Free 3D Engine and Development Software
- Free 3D Modelling and Animation Software
- Free Cluster Software
- Free Editor and Script Software
- Free Video Player Software
- Free Image and Picture Editing Software
- Free Render Queues Software
- Free Renderer Software
- Free Shader and GPU Tools
- Free CAD Software
- Free DMX light control Software
- Free DVD Ripping and Mastering Software
- Free Video Encoding and Decoding Software
- Free Video Editing Software
- Free Video Extra Software
- Free TV and Recording Software
- Free Video Streaming Software
- Free Fractals Software
- Free Vectorial and UML Software
- Free Optical Caracter Recognition (OCR) Software
- Free Image Synthesis Software
- Free Image and Picture Viewer Software
- Free Audio Synthesis and Editing Software
- Free Audio Streaming Software
- Free Audio Codec Software
- Free Audio Decoder Software
- Free Audio Encoder Software
- Free Audio Frameworks
- Free Radio Software
- Free Voice Recognition and Synthesis Software
- Free Font Software
- Free Audio Mixer Software
- Free Media Archives
Enhancements:
- All the ArtistX infrastructure and software were updated to the new Debian Live code.
- Software that is not packaged for Debian or not in the official archive (especially for video and 3D production) is included.
- The look and feel were revamped using suggestions from media professionals.
- KDE and GNOME applications now look nearly the same and dark, relaxing colors are used.

YALA is a web-based LDAP administration GUI. The idea is to simplify the directory administration with a graphical interface and neat features, though to stay a general-purpose program (unlike some LDAP browsers written specifically for managing users on the system).
Yet Another LDAP Administrator goal is to simplify the administration but not to make the YALA user stupid: to achieve this, we try to show the user what YALA does behind the scenes, what it sends to the server (unlike Microsoft Active Directory, for example).
Main features:
- Clear and Simple interface
- Cross-Platform: YALA can be accessed from any platform using any modern browser
- Cute javascript to improve the web-interface, which can be set off if you would like
- Theoretically works with any LDAP server, see README file for list of supported LDAP servers.
- Reads the schema from the LDAP server and gets lots of useful information off there.
- Entry Types recognition: You can configure YALA to recognize an entry of objectclasses X & Y, for example, as a user entry, have a special icon for it, and allow simple creation of new entries of this type (i.e. add a new user).
- Its free (under the GPL)