Corrie Walwyn - 2003-08-08

I am starting from the Communicator acoustic models (communicator-200-11.. dated 12-Mar-2002 11:24 22.1 M from www.speech.cs.cmu.edu/sphinx/models/hmm) and would like to train further using another set of data.  I am using the Sphinx2 decoder.  Does anyone know which settings (for example: agc max or none; varnorm and cmm) were used to train the Communicator acoustic model?