libTLK
1.3.1
|
Functions | |
tL_cmllr_adapt_fea (tLCMLLR *cmllr, const tLFea *fea_in, tLFea *fea_out) | |
Adapt a feature sequence. | |
tL_cmllr_free (tLCMLLR *cmllr) | |
Frees memory. | |
tL_cmllr_get_lv_constant (const tLCMLLR *cmllr, const tLAMlogCounts *counts) | |
Gets the additional ![]() | |
tL_cmllr_init (tLCMLLR *cmllr) | |
Initializes the CMLLR transformation matrix. | |
tL_cmllr_new (tLAModel *amodel, char **err) | |
Get a tLCMLLR. | |
tL_cmllr_print_matrix (const tLCMLLR *cmllr, FILE *to) | |
Prints the transformation matrix. | |
tL_cmllr_read_matrix (const tLCMLLR *cmllr, gzFile from, char **err) | |
Reads the transformation matrix. | |
tL_cmllr_update_matrix (tLCMLLR *cmllr, const tLAMlogCounts *counts, const unsigned int niters) | |
Update the transformation matrix. |
tL_cmllr_adapt_fea | ( | tLCMLLR * | cmllr, |
const tLFea * | fea_in, | ||
tLFea * | fea_out | ||
) |
Adapt a feature sequence.
This function applies the CMLLR transformation matrix to the feature sequence stored in the provided feature sequence manager. The feature sequence is assumed to be real and to have the same dimension as the acoustic model related to the CMLLR structure.
cmllr | The CMLLR structure. |
fea_in | A feature sequence manager containing the real feature sequence to adapt. |
fea_out | The feature sequence manager to which the transformed sequence will be stored. |
tL_cmllr_free | ( | tLCMLLR * | cmllr | ) |
Frees memory.
Frees the memory allocated for the CMLLR structure.
cmllr | The CMLLR structure. |
tL_cmllr_get_lv_constant | ( | const tLCMLLR * | cmllr, |
const tLAMlogCounts * | counts | ||
) |
Gets the additional term.
This function calculates the additional term , which must be added to log-likelihood.
cmllr | The CMLLR structure. |
counts | Logarithmic counts related to the acoustic model of the CMLLR structure. |
tL_cmllr_init | ( | tLCMLLR * | cmllr | ) |
Initializes the CMLLR transformation matrix.
This function initializes the CMLLR transformation matrix. The A matrix is initialized as the identity matrix, and the b vector is initialized with zeroes.
cmllr | The CMLLR structure. |
tL_cmllr_new | ( | tLAModel * | amodel, |
char ** | err | ||
) |
Get a tLCMLLR.
This function creates a CMLLR structure used to adapt models and transform features using the CMLLR technique. Only DGaussian based types are supported. This function calls 'tL_cmllr_init'.
amodel | The acoustic model. |
err | Pointer to string variable. If not NULL, an error message is allocated in the variable in case of error. |
tL_cmllr_print_matrix | ( | const tLCMLLR * | cmllr, |
FILE * | to | ||
) |
Prints the transformation matrix.
This function prints the CMLLR transformation matrix to the specified file.
cmllr | The CMLLR structure. |
to | File to which the matrix will be written. |
tL_cmllr_read_matrix | ( | const tLCMLLR * | cmllr, |
gzFile | from, | ||
char ** | err | ||
) |
Reads the transformation matrix.
This function reads the CMLLR transformation matrix from the specified file.
cmllr | The CMLLR structure. |
from | File where the matrix is stored. |
err | Pointer to string variable. If not NULL, an error message is allocated in the variable in case of error. |
tL_cmllr_update_matrix | ( | tLCMLLR * | cmllr, |
const tLAMlogCounts * | counts, | ||
const unsigned int | niters | ||
) |
Update the transformation matrix.
This function recalculates the CMLLR transformation matrix, using the previous values and the provided logarithmic counts. When niters is 0, diagonal CMLLR matrix is calculated. When full matrix is calculated, counts must be created using 'tL_cmlogcounts_new_cmllr'.
cmllr | The CMLLR structure. |
counts | Logarithmic counts related to the acoustic model of the CMLLR structure. The counts must be created using 'tL_cmlogcounts_new_cmllr' if niters>0. |
niters | The number of iterations for the CMLLR, or 0 to indicate that diagonal CMLLR matrix must be calculated. algorithm. Must be greater than 0. |