Hello everyone,

                      I have recently started learning HTK. I am not an expert in linguistics or speech processing.I am doing a project for lip synchronization in animation. For that I need to do a phonetic transcription and syllabification of a speech file. My input is a .wav file in which a single speaker speaks something. I basically want to learn how to do a speaker dependent phonetic transcription and also it is free alignment not forced alignment. I would be grateful if someone could help me through this. Thank you very much.

--- (Edited on 3/26/2011 7:50 am [GMT-0500] by ) ---

> I basically want to learn how to do a speaker dependent phonetic transcription 

For Julius, there are settings you can specify to tell it to output phonetic transcription.  For example, when running Julius in server mode, you can tell it to output only the phones using the outcode parameter:

       -outcode [W][L][P][S][C][w][l][p][s] 
              (Only for Server Module Mode) Switch which symbols of recognized 
              words  to be sent to client.  Specify 'W' for output symbol, 'L' 
              for N-gram entry, 'P' for phoneme sequence, 'S' for  score,  and 
              'C' for confidence score, respectively.  Capital letters are for 
              the second pass  (final  result),  and  small  letters  are  for 
              results  of  the  first  pass.  For example, if you want to send 
              only the output symbols and phone  sequences  as  a  recognition 

              result to a client, specify "-outcode WP". 

There should be something similar in HTK (though no server mode)

--- (Edited on 3/30/2011 10:33 am [GMT-0400] by kmaclean) ---