-
Couldn't load subscription status.
- Fork 271
added: new algo for cmn #23
base: master
Are you sure you want to change the base?
Conversation
| int32 i, j; | ||
| mfcc_t cep_cur[cmn->veclen]; // is it correctly? | ||
|
|
||
| if (nfr <= 0) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Add curly braces.
|
Please follow the project's coding style. |
|
Hi Alexander, These style-errors have been fixed. |
src/libsphinxbase/feat/cmn_adapt.c
Outdated
| if ( cep_cur[0] > cmn->max[0] ) | ||
| cmn->max[0] = cep_cur[0] * prob0 + cmn->max[0] * (1.0f-prob0); | ||
|
|
||
| mfcc_t e_prob = incep[i][0] / cmn->max[0] * 0.001f; |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
What does 0.001f mean here. Also please note that mfcc_t can be a fixed point number (int) in fixed point mode, floating point operation is not easy here.
|
Hi Team! Test "-cmn adapt" with option "-remove_silence no" |
Hi Team,
This is new CMN algorithm, that can working "online" and has support cep-normalization.
Best regards,
Zamir