#include <sent/stddefs.h>
#include <sent/htk_hmm.h>
#include <sent/htk_param.h>
Include dependency graph for hmm.h:
This graph shows which files directly or indirectly include this file:
Go to the source code of this file.
Definition in file hmm.h.
|
Token definition for viterbi segmentation. |
|
Make a HMM instance for recognition from phoneme sequence.
Definition at line 362 of file mkwhmm.c. Referenced by do_align(), and scan_word(). |
|
Make a HMM instance for recognition from phoneme sequence, with connection probabiliry given for each phoneme.
Definition at line 102 of file mkwhmm.c. Referenced by new_make_word_hmm(). |
|
Free an HMM instance.
Definition at line 381 of file mkwhmm.c. Referenced by do_align(). |
|
Perform Viterbi alignment. This function performs viterbi alignment for the given sentence HMM, input parameter and unit definition. Any segmentatino unit (word, phoneme state, etc.) is allowed: the segmentation unit should be specified by specifying a list of state id which are the end of each unit. For example, if you want to obtain phoneme alignment, the list of state number that exist at the end of phones should be specified by endstates.
Definition at line 50 of file vsegment.c. Referenced by do_align(). |
|
Generate a value tables of
Definition at line 40 of file addlog.c. Referenced by outprob_init(). |
|
Rapid computation of If value differs more than LOG_ADDMIN, the larger value will be returned as is.
|
|
Rapid computation of
Definition at line 98 of file addlog.c. Referenced by calc_mix(), calc_tied_mix(), and gmm_calc_mix(). |
|
Initialize and setup acoustic computation functions.
Definition at line 62 of file outprob_init.c. Referenced by final_fusion(). |
|
Prepare for the next input of given frame length.
Definition at line 139 of file outprob_init.c. Referenced by main_recognition_loop(), and RealTimePipeLinePrepare(). |
|
Initialize the cache data, should be called once on startup.
Definition at line 81 of file outprob.c. Referenced by outprob_init(). |
|
Prepare cache for the next input, by clearing the existing cache.
Definition at line 98 of file outprob.c. Referenced by outprob_prepare(). |
|
Compute output probability of a state. Set the needed values to the global variables that begins with "OP_", and call calc_outprob_state(). The calc_outprob_state() is actually a function pointer, and the entity is either calc_tied_mix() for tied-mixture model and calc_mix() for others. (If you use GMS, the entity will be gms_state() instead.) The state-level cache is also consulted here.
Definition at line 167 of file outprob.c. Referenced by next_word(), outprob(), outprob_cd_avg(), outprob_cd_max(), outprob_cd_nbest(), outprob_style(), and start_word(). |
|
Initialize work area for outprob_cd_nbest().
Definition at line 204 of file outprob.c. Referenced by outprob_init(). |
|
Compute the log output probability of a pseudo state set.
Definition at line 312 of file outprob.c. Referenced by next_word(), outprob(), outprob_style(), and start_word(). |
|
Top function to compute the output probability of a HMM state.
Definition at line 346 of file outprob.c. Referenced by viterbi_segment(). |
|
Initialize the GMS related functions and data.
Definition at line 262 of file gms.c. Referenced by outprob_init(). |
|
Setup GMS parameters for next input.
Definition at line 312 of file gms.c. Referenced by outprob_prepare(). |
|
Get HMM State probability of current state with Gaussiam Mixture Selection. If the GMS HMM score of the corresponding basephone is below the N-best, the triphone score will not be computed, and the score of the GMS HMM will be returned instead as a fallback score. Else, the precise triphone will be computed and returned.
Definition at line 352 of file gms.c. Referenced by outprob_init(). |
|
Initialization of GMS HMM likelihood computation.
Definition at line 60 of file gms_gprune.c. Referenced by gms_init(). |
|
Prepare GMS HMM computation for the next speech input. Definition at line 75 of file gms_gprune.c. Referenced by gms_prepare(). |
|
Main function to compute all the GMS HMM states in a frame with the input vectore specified by OP_vec. This function assumes that this will be called for sequencial frame, since it utilizes the result of previous frame for faster pruning.
Definition at line 293 of file gms_gprune.c. Referenced by do_gms(). |
|
Compute the output probability of current state OP_State. No codebook-level cache is done.
Definition at line 39 of file calc_mix.c. Referenced by outprob_init(). |
|
Initialize codebook cache area.
Definition at line 57 of file calc_tied_mix.c. Referenced by outprob_init(). |
|
Setup codebook cache for the next incoming input.
Definition at line 73 of file calc_tied_mix.c. Referenced by outprob_prepare(). |
|
Compute the output probability of current state OP_State on tied-mixture model. This function assumes that the OP_state is assigned to a tied-mixture codebook. Here the output probability of Gaussian mixture component referred by OP_state is consulted to the book level cache, and if not computed yet on that input frame time, it will be computed here.
Definition at line 120 of file calc_tied_mix.c. Referenced by outprob_init(). |
|
Output transition arcs of an HMM instance.
Definition at line 160 of file put_htkdata_info.c. Referenced by put_hmm(). |
|
Output output probability information of an HMM instance.
Definition at line 183 of file put_htkdata_info.c. Referenced by put_hmm(). |
|
Output an HMM instance.
Definition at line 204 of file put_htkdata_info.c. |