Im currently using sphinx3_continuous decoder. My output is similar to the one described in this link - http://cmusphinx.sourceforge.net/sphinx3/doc/s3_description.html#sec_hypseg, except that I get this decimal number appended after the utterance id.
e.g. recording_0.256
And the start frames don't seem to match the word string in the audio file.
Does this decimal number have to do with the start frames in the output like an offset or something?
here is an actual output:
2c588c66-f51e-45d4-9e86-4ff3c5214187_0.816
S -551274
T -2478900
A -2395227
L -83673
8 -433313 -8984 THE
20 -1414106 -33601 CARNEGIE
73 92012 -33413 DID
104
Thanks a lot!
- kris
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi,
Im currently using sphinx3_continuous decoder. My output is similar to the one described in this link - http://cmusphinx.sourceforge.net/sphinx3/doc/s3_description.html#sec_hypseg, except that I get this decimal number appended after the utterance id.
e.g. recording_0.256
And the start frames don't seem to match the word string in the audio file.
Does this decimal number have to do with the start frames in the output like an offset or something?
here is an actual output:
2c588c66-f51e-45d4-9e86-4ff3c5214187_0.816
S -551274
T -2478900
A -2395227
L -83673
8 -433313 -8984 THE
20 -1414106 -33601 CARNEGIE
73 92012 -33413 DID
104
Thanks a lot!
- kris