Шумопонижение в CMU Sphinx

# Configuration script for sphinx trainer                  -*-mode:Perl-*-

$CFG_VERBOSE = 1;		# Determines how much goes to the screen.

# These are filled in at configuration time
$CFG_DB_NAME = "voxforge_en";
# Experiment name, will be used to name model files and log files
$CFG_EXPTNAME = "$CFG_DB_NAME";

# Directory containing SphinxTrain binaries
$CFG_BASE_DIR = "/home/speechdat/voxforge-en";
$CFG_SPHINXTRAIN_DIR = "/usr/local/lib/sphinxtrain";
$CFG_BIN_DIR = "/usr/local/libexec/sphinxtrain";
$CFG_SCRIPT_DIR = "/usr/local/lib/sphinxtrain/scripts";


# Audio waveform and feature file information
$CFG_WAVFILES_DIR = "$CFG_BASE_DIR/wav";
$CFG_WAVFILE_EXTENSION = 'wav';
$CFG_WAVFILE_TYPE = 'mswav'; # one of nist, mswav, raw
$CFG_FEATFILES_DIR = "$CFG_BASE_DIR/feat";
$CFG_FEATFILE_EXTENSION = 'mfc';
$CFG_VECTOR_LENGTH = 13;


# Feature extraction parameters
$CFG_WAVFILE_SRATE = 16000.0;
$CFG_NUM_FILT = 40; # For wideband speech it's 40, for telephone 8khz reasonable value is 31
$CFG_LO_FILT = 133.33334; # For telephone 8kHz speech value is 200
$CFG_HI_FILT = 6855.4976; # For telephone 8kHz speech value is 3500
$CFG_TRANSFORM = "dct"; # Previously legacy transform is used, but dct is more accurate
$CFG_LIFTER = "22"; # Cepstrum lifter is smoothing to improve recognition

$CFG_MIN_ITERATIONS = 1;  # BW Iterate at least this many times
$CFG_MAX_ITERATIONS = 10; # BW Don't iterate more than this, somethings likely wrong.

# (none/max) Type of AGC to apply to input files
$CFG_AGC = 'none';
# (current/none) Type of cepstral mean subtraction/normalization
# to apply to input files
$CFG_CMN = 'current';
$CFG_CMNINIT = 10.0;
# (yes/no) Normalize variance of input files to 1.0
$CFG_VARNORM = 'no';
# (yes/no) Train full covariance matrices
$CFG_FULLVAR = 'no';
# (yes/no) Use diagonals only of full covariance matrices for
# Forward-Backward evaluation (recommended if CFG_FULLVAR is yes)
$CFG_DIAGFULL = 'no';

# (yes/no) Perform vocal tract length normalization in training.  This
# will result in a "normalized" model which requires VTLN to be done
# during decoding as well.
$CFG_VTLN = 'no';
# Starting warp factor for VTLN
$CFG_VTLN_START = 0.80;
# Ending warp factor for VTLN
$CFG_VTLN_END = 1.40;
# Step size of warping factors
$CFG_VTLN_STEP = 0.05;

# Directory to write queue manager logs to
$CFG_QMGR_DIR = "$CFG_BASE_DIR/qmanager";
# Directory to write training logs to
$CFG_LOG_DIR = "$CFG_BASE_DIR/logdir";
# Directory for re-estimation counts
$CFG_BWACCUM_DIR = "$CFG_BASE_DIR/bwaccumdir";
# Directory to write model parameter files to
$CFG_MODEL_DIR = "$CFG_BASE_DIR/model_parameters";

# Directory containing transcripts and control files for
# speaker-adaptive training
$CFG_LIST_DIR = "$CFG_BASE_DIR/etc";


# Decoding variables for MMIE training
$CFG_LANGUAGEWEIGHT = "11.5";
$CFG_BEAMWIDTH      = "1e-100";
$CFG_WORDBEAM       = "1e-80";
$CFG_LANGUAGEMODEL  = "$CFG_LIST_DIR/${CFG_DB_NAME}_full.lm.DMP";
$CFG_WORDPENALTY    = "0.2";

# Lattice pruning variables
$CFG_ABEAM              = "1e-50";
$CFG_NBEAM              = "1e-10";
$CFG_PRUNED_DENLAT_DIR  = "$CFG_BASE_DIR/pruned_denlat";

# MMIE training related variables
$CFG_MMIE = "no";
$CFG_MMIE_MAX_ITERATIONS = 5;
$CFG_LATTICE_DIR = "$CFG_BASE_DIR/lattice";
$CFG_MMIE_TYPE   = "best"; # Valid values are "rand", "best" or "ci"
$CFG_MMIE_CONSTE = "3.0";
$CFG_NUMLAT_DIR  = "$CFG_BASE_DIR/numlat";
$CFG_DENLAT_DIR  = "$CFG_BASE_DIR/denlat";


# Variables used in main training of models
$CFG_DICTIONARY     = "$CFG_LIST_DIR/$CFG_DB_NAME.dict";
$CFG_RAWPHONEFILE   = "$CFG_LIST_DIR/$CFG_DB_NAME.phone";
$CFG_FILLERDICT     = "$CFG_LIST_DIR/$CFG_DB_NAME.filler";
$CFG_LISTOFFILES    = "$CFG_LIST_DIR/${CFG_DB_NAME}_full.fileids";
$CFG_TRANSCRIPTFILE = "$CFG_LIST_DIR/${CFG_DB_NAME}_full.transcription";
$CFG_FEATPARAMS     = "$CFG_LIST_DIR/feat.params";

# Variables used in characterizing models

$CFG_HMM_TYPE = '.cont.'; # Sphinx 4, PocketSphinx
#$CFG_HMM_TYPE  = '.semi.'; # PocketSphinx
#$CFG_HMM_TYPE  = '.ptm.'; # PocketSphinx (larger data sets)

if (($CFG_HMM_TYPE ne ".semi.")
    and ($CFG_HMM_TYPE ne ".ptm.")
    and ($CFG_HMM_TYPE ne ".cont.")) {
  die "Please choose one CFG_HMM_TYPE out of '.cont.', '.ptm.', or '.semi.', " .
    "currently $CFG_HMM_TYPEn";
}

# This configuration is fastest and best for most acoustic models in
# PocketSphinx and Sphinx-III.  See below for Sphinx-II.
$CFG_STATESPERHMM = 3;
$CFG_SKIPSTATE = 'no';

if ($CFG_HMM_TYPE eq '.semi.') {
  $CFG_DIRLABEL = 'semi';
# Four stream features for PocketSphinx
  $CFG_FEATURE = "s2_4x";
  $CFG_NUM_STREAMS = 4;
  $CFG_INITIAL_NUM_DENSITIES = 256;
  $CFG_FINAL_NUM_DENSITIES = 256;
  die "For semi continuous models, the initial and final models have the same density" 
    if ($CFG_INITIAL_NUM_DENSITIES != $CFG_FINAL_NUM_DENSITIES);
} elsif ($CFG_HMM_TYPE eq '.ptm.') {
  $CFG_DIRLABEL = 'ptm';
# Four stream features for PocketSphinx
  $CFG_FEATURE = "s2_4x";
  $CFG_NUM_STREAMS = 4;
  $CFG_INITIAL_NUM_DENSITIES = 64;
  $CFG_FINAL_NUM_DENSITIES = 64;
  die "For phonetically tied models, the initial and final models have the same density" 
    if ($CFG_INITIAL_NUM_DENSITIES != $CFG_FINAL_NUM_DENSITIES);
} elsif ($CFG_HMM_TYPE eq '.cont.') {
  $CFG_DIRLABEL = 'cont';
# Single stream features - Sphinx 3
  $CFG_FEATURE = "1s_c_d_dd";
  $CFG_NUM_STREAMS = 1;
  $CFG_INITIAL_NUM_DENSITIES = 1;
  $CFG_FINAL_NUM_DENSITIES = 32;
  die "The initial has to be less than the final number of densities" 
    if ($CFG_INITIAL_NUM_DENSITIES > $CFG_FINAL_NUM_DENSITIES);
}

# Number of top gaussians to score a frame. A little bit less accurate computations
# make training significantly faster. Uncomment to apply this during the training
# For good accuracy make sure you are using the same setting in decoder
# In theory this can be different for various training stages. For example 4 for
# CI stage and 16 for CD stage
# $CFG_CI_TOPN = 4;
# $CFG_CD_TOPN = 16;

# (yes/no) Train multiple-gaussian context-independent models (useful
# for alignment, use 'no' otherwise) in the models created
# specifically for forced alignment
$CFG_FALIGN_CI_MGAU = 'no';
# (yes/no) Train multiple-gaussian context-independent models (useful
# for alignment, use 'no' otherwise)
$CFG_CI_MGAU = 'no';
# Number of tied states (senones) to create in decision-tree clustering
$CFG_N_TIED_STATES = 3000;
# How many parts to run Forward-Backward estimatinon in
$CFG_NPART = 1;

# (yes/no) Train a single decision tree for all phones (actually one
# per state) (useful for grapheme-based models, use 'no' otherwise)
$CFG_CROSS_PHONE_TREES = 'no';

# Use force-aligned transcripts (if available) as input to training
$CFG_FORCEDALIGN = 'no';

# Use a specific set of models for force alignment.  If not defined,
# context-independent models for the current experiment will be used.
$CFG_FORCE_ALIGN_MDEF = "$CFG_BASE_DIR/model_architecture/$CFG_EXPTNAME.falign_ci.mdef";
$CFG_FORCE_ALIGN_MODELDIR = "$CFG_MODEL_DIR/$CFG_EXPTNAME.falign_ci_$CFG_DIRLABEL";

# Use a specific dictionary and filler dictionary for force alignment.
# If these are not defined, a dictionary and filler dictionary will be
# created from $CFG_DICTIONARY and $CFG_FILLERDICT, with noise words
# removed from the filler dictionary and added to the dictionary (this
# is because the force alignment is not very good at inserting them)

# $CFG_FORCE_ALIGN_DICTIONARY = "$ST::CFG_BASE_DIR/falignout$ST::CFG_EXPTNAME.falign.dict";;
# $CFG_FORCE_ALIGN_FILLERDICT = "$ST::CFG_BASE_DIR/falignout/$ST::CFG_EXPTNAME.falign.fdict";;

# Use a particular beam width for force alignment.  The wider
# (i.e. smaller numerically) the beam, the fewer sentences will be
# rejected for bad alignment.
$CFG_FORCE_ALIGN_BEAM = 1e-60;

# Calculate an LDA/MLLT transform?
$CFG_LDA_MLLT = 'yes';
# Dimensionality of LDA/MLLT output
$CFG_LDA_DIMENSION = 29;

# This is actually just a difference in log space (it doesn't make
# sense otherwise, because different feature parameters have very
# different likelihoods)
$CFG_CONVERGENCE_RATIO = 0.1;

# Queue::POSIX for multiple CPUs on a local machine
# Queue::PBS to use a PBS/TORQUE queue
$CFG_QUEUE_TYPE = "Queue::POSIX";

# Name of queue to use for PBS/TORQUE
$CFG_QUEUE_NAME = "workq";

# (yes/no) Build questions for decision tree clustering automatically
$CFG_MAKE_QUESTS = "yes";
# If CFG_MAKE_QUESTS is yes, questions are written to this file.
# If CFG_MAKE_QUESTS is no, questions are read from this file.
$CFG_QUESTION_SET = "${CFG_BASE_DIR}/model_architecture/${CFG_EXPTNAME}.tree_questions";
#$CFG_QUESTION_SET = "${CFG_BASE_DIR}/linguistic_questions";

$CFG_CP_OPERATION = "${CFG_BASE_DIR}/model_architecture/${CFG_EXPTNAME}.cpmeanvar";

# This variable has to be defined, otherwise utils.pl will not load.
$CFG_DONE = 1;

return 1;

-alpha 0.97
-dither yes
-doublebw no
-nfilt __CFG_NUM_FILT__
-ncep __CFG_VECTOR_LENGTH__
-lowerf __CFG_LO_FILT__
-upperf __CFG_HI_FILT__
-samprate __CFG_WAVFILE_SRATE__
-nfft 512
-wlen 0.0256
-transform __CFG_TRANSFORM__
-feat __CFG_FEATURE__
-agc __CFG_AGC__
-cmn __CFG_CMN__
-varnorm __CFG_VARNORM__
-remove_noise yes
-lifter __CFG_LIFTER__

<component name="mfcFrontEnd"
          type="edu.cmu.sphinx.frontend.FrontEnd">
        <propertylist name="pipeline">
            <item>audioFileDataSource</item>
            <item>dither</item>
            <item>preemphasizer</item>
            <item>windower</item>
            <item>fft</item>
            <item>melFilterBank</item>
            <item>denoise</item>
            <item>dct</item>
            <item>lifter</item>
            <item>batchCMN</item>
            <item>featureExtraction</item>
            <item>featureTransform</item>
        </propertylist>
    </component>    

    <component name="audioFileDataSource"
          type="edu.cmu.sphinx.frontend.util.AudioFileDataSource">
    </component>

    <component name="preemphasizer"
          type="edu.cmu.sphinx.frontend.filter.Preemphasizer">
    </component>

    <component name="dither"
          type="edu.cmu.sphinx.frontend.filter.Dither">
    </component>

    <component name="windower"
          type="edu.cmu.sphinx.frontend.window.RaisedCosineWindower">
    </component>

    <component name="fft"
          type="edu.cmu.sphinx.frontend.transform.DiscreteFourierTransform">
    </component>

    <component name="melFilterBank"
          type="edu.cmu.sphinx.frontend.frequencywarp.MelFrequencyFilterBank">
        <property name="numberFilters" value="40"/>
        <property name="minimumFrequency" value="133.33334"/>
        <property name="maximumFrequency" value="6855.4976"/>
    </component>
    
    <component name="denoise" 
	  type="edu.cmu.sphinx.frontend.denoise.Denoise">
    </component>

    <component name="dct"
          type="edu.cmu.sphinx.frontend.transform.DiscreteCosineTransform2">
    </component>
    
    <component name="lifter" 
	  type="edu.cmu.sphinx.frontend.transform.Lifter">
    </component>

    <component name="batchCMN"
          type="edu.cmu.sphinx.frontend.feature.BatchCMN">
    </component>

    <component name="featureExtraction"
          type="edu.cmu.sphinx.frontend.feature.DeltasFeatureExtractor">
    </component>

    <component name="featureTransform"
          type="edu.cmu.sphinx.frontend.feature.FeatureTransform">
        <property name="loader" value="modelLoader"/>
    </component>