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?
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
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?