libTLK  1.3.1
Data Structures | Functions
MLLR adaptation
Algorithms

Data Structures

struct  tLMLLRrc
 Used to assign states to regression classes. More...

Functions

 tL_mllr_free (tLMLLR *mllr)
 Frees memory.
 tL_mllr_get_adapted_model (tLMLLR *mllr, tLAModel *amodel)
 Adapts the model.
 tL_mllr_init (tLMLLR *mllr)
 Initializes the MLLR transformation matrices.
 tL_mllr_new (tLAModel *amodel, const tLMLLRrc *rcs, const unsigned int length_rcs, char **err)
 Get a tLMLLR.
 tL_mllr_update_matrices (tLMLLR *mllr, const tLAMlogCounts *counts, const tLAModel *amodel)
 Update the transformation matrices.

Function Documentation

tL_mllr_free ( tLMLLR *  mllr)

Frees memory.

Frees the memory allocated for the MLLR structure.

Parameters:
mllrThe MLLR structure.
tL_mllr_get_adapted_model ( tLMLLR *  mllr,
tLAModel amodel 
)

Adapts the model.

This function adapts the acoustic model passed using the current MLLR transformation matrices. The acoustic model must have the same structure as the original acoustic model which was used to make the MLLR structure.

Parameters:
mllrThe MLLR structure.
amodelThe acoustic model to adapt. If NULL, then the original acoustic is copied and adapted.
Returns:
The adapted acoustic model.
tL_mllr_init ( tLMLLR *  mllr)

Initializes the MLLR transformation matrices.

This function initializes the MLLR transformation matrices. The A matrix is initialized to the identity matrix, and the b vector is initialized with zeroes.

Parameters:
mllrThe MLLR structure.
tL_mllr_new ( tLAModel amodel,
const tLMLLRrc rcs,
const unsigned int  length_rcs,
char **  err 
)

Get a tLMLLR.

This function creates a MLLR structure used to adapt models and transform features using the MLLR technique. Only DGaussian based types are supported. This function calls 'tL_mllr_init'.

Parameters:
amodelThe acoustic model.
rcsAn array used to assign states to regression classes. By default, all classes are assigned to the regression class 0. If NULL, then all states are assigned to the regression class 0.
length_rcsThe size of rcs.
errPointer to string variable. If not NULL, an error message is allocated in the variable in case of error.
Returns:
MLLR structure, or NULL in case of error.
tL_mllr_update_matrices ( tLMLLR *  mllr,
const tLAMlogCounts counts,
const tLAModel amodel 
)

Update the transformation matrices.

This function recalculates the MLLR transformation matrices using the provided logarithmic counts and the parameters of the acoustic model used to estimate the counts. Counts must be created using 'tL_amlogcounts_new_mllr', and the acoustic model must have the same structure as the structure of the acoustic model used to create the MLLR structure.

Parameters:
mllrThe MLLR structure.
countsLogarithmic counts related to the acoustic model of the CMLLR structure. The counts must be created using 'tL_amlogcounts_new_mllr'.
amodelThe acoustic model parameters used to estimate the counts.
 All Data Structures Variables