A Dialog Manager is one component of a Speech Recognition System.

Telephony and Command & Control Dialog Managers

A Dialog Manager used in Telephony applications (IVR - Interactive Voice Response), and in some desktop Command and Control Application, assigns meaning to the words recognized by the Speech Recognition Engine, determines how the utterance fits into the dialog spoken so far,and decides what to do next.  It might need to retrieve information from an external source.  If a response to the user is required, it will choose the words and phrases to be used in its response to the user, and transmit these to the Text-to-Speech System to speak the response to the user.

Dictation Dialog Manager 

A Dictation Dialog Manager will typically take the words recognized by the Speech Recognition Engine and type out the corresponding text on your computer screen.  It may also have some Command and Control elements, but these are usually limited to the types of commands typically used in a word processing program.  It usually responds to the user using text (i.e. it might not use Text to Speech to respond to the user).

Examples 

Examples of Telephony Dialog Managers include: 

• Ravenclaw,
• jvoicexml,
• ariadne, or
• jaspis. 

Examples of Command & Control Dialog Managers:

• Gnome-Voice-Control  (uses PocketSphinx)
• SpeechLion (uses Sphinx4)
• Vedics (uses Sphinx4)
  
• PerlBox (uses Sphinx2)
• Simon (uses Julius)
• OpenEars (uses PocketSphinx on iPad/iPhone)
• Kiku (uses Julius)
• ruby-pocketsphinx-server (for Android)
  
• Jaivox (uses Sphinx4)
• pocketVox (uses PocketSphinx)

Examples of Dictation Dialog Managers, with Command & Control elements, would be:

• xVoice (needs IBM's ViaVoice engine for Linux - no longer available)
• Evaldictator (uses Sphinx4)
• speechoo (uses Julius) a dictation pad for LibreOffice
• freespeech-vr Free streaming voice recognition with dynamic language learning

You can also write a domain specific application to perform Dialog Manager-like tasks using a traditional programming language (C, C++, Java, etc.) or a scripting Language (Perl, Python, Ruby, etc.). For example:

• Sphinx
  • using Perl: Cepstral's Speech and audio POE components (announcement);
  • Perl: Speech-Recognizer-SPX-0.09 (CPAN)
  • Perl and PHP: Sphinx and Asterisk integration (as a starting point for creating your own script-based dialog manager)
  • Python: voximp
    
  • Java & C++ API: Voce
  • Python: Blather
  • Javascript: JuliusJS
    
• Julius:
  
  • PHP: Querying a database using open source voice control software
  • Python:
    • Writing a command and control application with voice recognition
    • Robot Arm with Voice Control
    • E.V.E.
      
  • Bash: http://bitbucket.org/ptg/vox/src
    • see also waryishe's post
      
  • Java: voice-remote-android
  • Lua: PEIS Julius
  • Javascript: PocketSphinx.js
    
• HTK
  • using Java
    
    

Here is an article (Google translated from Russian) that gives another example of using Julius with Python:

$ vi sample.voca

% NS_B
<s> sil

% NS_E
</s> sil

% ID
DO d uw

% COMMAND
PLAY pl ey
NEXT n eh kst
PREV pr iy v
SILENCE s ay l ax ns

$ vi sample.grammar

S: NS_B ID COMMAND NS_E

Create your grammar:

$ mkdfa sample

test with Julius

$ julius -input mic -C julian.jconf

$ vi command.py

def parse(line):
   params = [param.lower() for param in line.split() if param]
   commands = {
   'play': 'audacious2 -p',
   'silence': 'audacious2 -u',
   'next': 'audacious2 -f',
   'prev': 'audacious2 -r',
   }
   if params[1] in commands: os.popen(commands[params[1]])

Run as follows:

$ julius -quiet -input mic -C julian.jconf 2>/dev/null | ./command.py