SPRAAK
 All Data Structures Namespaces Files Functions Variables Typedefs Enumerations Enumerator Groups Pages
Programs
spr_add_gaussIncrease the level of tying in a reduced SC_HMM
spr_addkeyAdd/modify a key in the header of a KEY file
spr_bmixmix the data in a file
spr_calc_ldacalculate the lda transformation for a given preprocessing and
spr_calc_oprobsDump state output probs
spr_copyFile copying with conversion
spr_ct2hmmCombine the statistics from multiple segpass or vitpass runs into an updated model.
spr_cwr_mainLarge Vocabulary Continuous Speech Recognition with Hidden Markov models
spr_decorrCalculate a good decorrelation matrix given the full covariance
spr_delkeyDelete a key in the header of a KEY file
spr_fv_gaussfeature space MLLR
spr_fwdbwd_probsFwd-bwd alignment (viterbi alike) te determine boundary probabilities
spr_getkeyGet a key from the header of a KEY file
spr_hmmc2dConvert a (semi)continuous density HMM to a discrete HMM or to a not-reduced semi-continuous HMM
spr_hmmcheckCheck the validity of an HMM
spr_hmmd2cConvert a discrete HMM to a continuous or a semi-continuous HMM
spr_hmmmergeConcatenate two HMMs
spr_hmmnormalizeNormalizes input file so that probabilities sum up to one
spr_hmmprintPrint the values in an HMM file
spr_hmmshakeReorder the states in an HMM
spr_hmmsmoothSmooth the mixture weights in HMM's retrained on little data
spr_hmmsumCombine two HMMs by summing the moments
spr_htk2keyConvert from HTK format to the KEY format
spr_kappendAppend KEY files
spr_kdiffCompare KEY files
spr_knn_dtwfind the k nearest neighbour templates using DTW for a given context
spr_lex_cvtModify a lexicon on a line-by-line basis.
spr_lm_arpaboConvert arpa style N-gram's to and from the binary format used in SPRAAK
spr_mdt_make_cgtcreate cluster gaussian to back-end gaussian association table
spr_msg_execexecute + time a program
spr_mvg_initInitialization for K-means cluster centra and multi variate gaussians
spr_printftest program
spr_scoreres(Re)calculate the CSR score for a given result file.
spr_segpassInitialize an hmm file on the basis of unit or state level segmentations
spr_sel_framesSelect frames corresponding to units or states, or to all data
spr_sel_gaussReduce the number of Gaussians in a mixture
spr_setminprobSet minimal probabilities in an HMM.
spr_sigpsignal processing
spr_space_cakeContinue Automatische Klank-Evaluatie
spr_spraak_socketSpeech interface using sockets
spr_tree2modelConstruction of acoustic models given a decision tree
spr_tree_createCreation of phonetic decision trees for context clustering
spr_tree_gauss_splitDecision tree based splitting of gaussians for HMMs with tied gaussians
spr_tttest program
spr_vitalignViterbi alignment.
spr_vitpassone pass of viterbi training for HMM-models
spr_vitprobsViterbi alignment + path probabilities
spr_wlatpprocessing of word lattices