Dear sir,
can you tell me the diffrent between SIL model and other phone model that
sphinx has defined. In training phase, how do sphinx know when SIL has occured
between 2 words in transcription file to pick the right triphone model to
train on.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I think it's called 'embedded training'. Check it out in
www.stanford.edu/class/cs224s/lec/224s.09.lec10.ppt
While training a sentence HMM alternate paths between any two words which
incorporate SIL are formed. See figure 9.10 in this book Spoken language
processing:
a guide to theory, algorithm, and system development
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Dear sir,
can you tell me the diffrent between SIL model and other phone model that
sphinx has defined. In training phase, how do sphinx know when SIL has occured
between 2 words in transcription file to pick the right triphone model to
train on.
Hi,
I think it's called 'embedded training'. Check it out in
www.stanford.edu/class/cs224s/lec/224s.09.lec10.ppt
While training a sentence HMM alternate paths between any two words which
incorporate SIL are formed. See figure 9.10 in this book Spoken language
processing:
a guide to theory, algorithm, and system development