libTLK
1.3.1
|
Functions | |
tL_trainer_free (tLTrainer *trainer) | |
Frees memory. | |
tL_trainer_new (tLAModel *amodel, tLAMlogCounts *counts, const tLSeqs *seqs, tLFloat **occs, char **err) | |
Gets a tLTrainer. | |
tL_train (tLTrainer *trainer, const tLFea *fea, const size_t seq) | |
Updates an acoustic model's counts according to the EM algorithm. |
Updates an acoustic model's counts according to the EM algorithm.
This function increases the acoustic model's counts, which are stored in the provided trainer, from one sample (feature vector sequence) and its transcription, using the EM algorithm in order to obtain the logarithmic counts. The sequence is specified as an integer code according to the sequence manager used during the creation of the trainer.
trainer | The trainer. |
fea | A feature vector manager, which must contain a sequence of feature vectors of an adequate type for the amodel. |
seq | The code of the transcription of the sample. |
tL_trainer_free | ( | tLTrainer * | trainer | ) |
Frees memory.
Frees the memory allocated for the trainer.
trainer | The trainer. |
tL_trainer_new | ( | tLAModel * | amodel, |
tLAMlogCounts * | counts, | ||
const tLSeqs * | seqs, | ||
tLFloat ** | occs, | ||
char ** | err | ||
) |
Gets a tLTrainer.
This function creates a trainer used to train an acoustic model from transcriptions using the EM algorithm. This data can only be used to train the symbol sequences stored in seqs during the creation of the auxiliary data. Currently supported types are: Bernoulli, DGaussian and Mixture.
amodel | The acoustic model. |
counts | The logarithmic counts which will be increased. |
seqs | A symbol sequence manager containing the symbol sequences which can be used to train samples. |
occs | If not NULL, it must be a pointer to a matrix in which the state occupancy values will be accumulated. |
err | Pointer to string variable. If not NULL, an error message is allocated in the variable in case of error. |