Menu ▾ ▴

Transcribing Words using WSJ

Speech Recognition Theory
Jher
2010-09-27
2012-09-22

  • Jher

    Jher - 2010-09-27

    Can anyone look into my code because i'm having a hard time in doing my thesis
    because of this. I will greatly acknowledge anyone who will help me. Please
    help.

    I'm currently doing thesis about using sphinx 4 in transcribing words in .WAV
    files.

    -
    -
    -
    - <config>
    -
    -
    -
    <property name="absoluteBeamWidth" value="500">
    <property name="relativeBeamWidth" value="1E-80">
    <property name="absoluteWordBeamWidth" value="20">
    <property name="relativeWordBeamWidth" value="1E-60">
    <property name="wordInsertionProbability" value="1E-16">
    <property name="languageWeight" value="7.0">
    <property name="silenceInsertionProbability" value=".1">
    <property name="frontend" value="epFrontEnd">
    <property name="recognizer" value="recognizer">
    <property name="showCreations" value="false">
    -
    -
    -
    - <component name="batch" type="edu.cmu.sphinx.tools.batch.BatchModeRecognizer">
    - <propertylist name="inputDataProcessors">
    <item>streamDataSource</item>
    </propertylist>
    <property name="skip" value="0">
    <property name="recognizer" value="${recognizer}">
    </property></property></component>
    -
    -
    -
    - <component name="recognizer" type="edu.cmu.sphinx.recognizer.Recognizer">
    <property name="decoder" value="decoder">
    - <propertylist name="monitors">
    <item>accuracyTracker</item>
    <item>speedTracker</item>
    <item>memoryTracker</item>
    <item>recognizerMonitor</item>
    </propertylist>
    </property></component>
    -
    -
    -
    - <component name="wordPruningSearchManager" type="edu.cmu.sphinx.decoder.search.WordPruningBreadthFirstSearchManager">
    <property name="logMath" value="logMath">
    <property name="linguist" value="lexTreeLinguist">
    <property name="pruner" value="trivialPruner">
    <property name="scorer" value="threadedScorer">
    <property name="activeListManager" value="activeListManager">
    <property name="growSkipInterval" value="0">
    <property name="checkStateOrder" value="false">
    <property name="buildWordLattice" value="false">
    <property name="acousticLookaheadFrames" value="1.7">
    <property name="relativeBeamWidth" value="${relativeBeamWidth}">
    </property></property></property></property></property></property></property></property></property></property></component>
    -
    -
    -
    - <component name="searchManager" type="edu.cmu.sphinx.decoder.search.SearchManager">
    <property name="logMath" value="logMath">
    <property name="linguist" value="lexTreeLinguist">
    <property name="pruner" value="trivialPruner">
    <property name="scorer" value="threadedScorer">
    <property name="activeListManager" value="activeListManager">
    <property name="growSkipInterval" value="0">
    <property name="checkStateOrder" value="false">
    <property name="buildWordLattice" value="false">
    <property name="maxLatticeEdges" value="3">
    <property name="acousticLookaheadFrames" value="1.7">
    <property name="relativeBeamWidth" value="${relativeBeamWidth}">
    </property></property></property></property></property></property></property></property></property></property></property></component>
    -
    -
    -
    - <component name="activeListManager" type="edu.cmu.sphinx.decoder.search.SimpleActiveListManager">
    - <propertylist name="activeListFactories">
    <item>standardActiveListFactory</item>
    <item>wordActiveListFactory</item>
    <item>wordActiveListFactory</item>
    <item>standardActiveListFactory</item>
    <item>standardActiveListFactory</item>
    <item>standardActiveListFactory</item>
    </propertylist>
    </component>
    - <component name="standardActiveListFactory" type="edu.cmu.sphinx.decoder.search.PartitionActiveListFactory">
    <property name="logMath" value="logMath">
    <property name="absoluteBeamWidth" value="${absoluteBeamWidth}">
    <property name="relativeBeamWidth" value="${relativeBeamWidth}">
    </property></property></property></component>
    - <component name="wordActiveListFactory" type="edu.cmu.sphinx.decoder.search.PartitionActiveListFactory">
    <property name="logMath" value="logMath">
    <property name="absoluteBeamWidth" value="${absoluteWordBeamWidth}">
    <property name="relativeBeamWidth" value="${relativeWordBeamWidth}">
    </property></property></property></component>
    -
    -
    -
    <component name="trivialPruner" type="edu.cmu.sphinx.decoder.pruner.SimplePruner">
    -
    -
    -
    - <component name="threadedScorer" type="edu.cmu.sphinx.decoder.scorer.ThreadedAcousticScorer">
    <property name="frontend" value="${frontend}">
    <property name="isCpuRelative" value="false">
    <property name="numThreads" value="0">
    <property name="minScoreablesPerThread" value="10">
    <property name="scoreablesKeepFeature" value="false">
    </property></property></property></property></property></component>
    -
    -
    -
    - <component name="lexTreeLinguist" type="edu.cmu.sphinx.linguist.lextree.LexTreeLinguist">
    <property name="logMath" value="logMath">
    <property name="acousticModel" value="wsj">
    <property name="languageModel" value="trigramModel">
    <property name="dictionary" value="dictionary">
    <property name="addFillerWords" value="false">
    <property name="fillerInsertionProbability" value="1E-10">
    <property name="generateUnitStates" value="false">
    <property name="wantUnigramSmear" value="true">
    <property name="unigramSmearWeight" value="1">
    <property name="wordInsertionProbability" value="${wordInsertionProbability}">
    <property name="silenceInsertionProbability" value="${silenceInsertionProbability}">
    <property name="languageWeight" value="${languageWeight}">
    </property></property></property></property></property></property></property></property></property></property></property></property></component>
    -
    -
    -
    - <component name="dictionary" type="edu.cmu.sphinx.linguist.dictionary.FastDictionary">
    <property name="dictionaryPath" value="resource:/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/dict/cmudict.0.6d">
    <property name="fillerPath" value="resource:/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/dict/fillerdict">
    <property name="addSilEndingPronunciation" value="false">
    <property name="wordReplacement" value="sil">
    </property></property></property></property></component>
    -
    -
    -
    - <component name="trigramModel" type="edu.cmu.sphinx.linguist.language.ngram.SimpleNGramModel">
    <property name="location" value="resource:/edu/cmu/sphinx/demo/hellongram/hellongram.trigram.lm">
    <property name="logMath" value="logMath">
    <property name="dictionary" value="dictionary">
    <property name="maxDepth" value="3">
    <property name="unigramWeight" value=".7">
    </property></property></property></property></property></component>
    -
    -
    -
    - <component name="wsj" type="edu.cmu.sphinx.linguist.acoustic.tiedstate.trainer.TrainerAcousticModel">
    <property name="loader" value="wsjLoader">
    <property name="unitManager" value="unitManager">
    </property></property></component>
    - <component name="wsjLoader" type="edu.cmu.sphinx.linguist.acoustic.tiedstate.trainer.Sphinx4Loader">
    <property name="logMath" value="logMath">
    <property name="unitManager" value="unitManager">
    <property name="location" value="resource:/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz">
    <property name="modelDefinition" value="etc/WSJ_clean_13dCep_16k_40mel_130Hz_6800Hz.4000.mdef">
    <property name="dataLocation" value="cd_continuous_8gau/">
    </property></property></property></property></property></component>
    -
    -
    -
    <component name="unitManager" type="edu.cmu.sphinx.linguist.acoustic.UnitManager">
    -
    -
    -
    - <component name="wavFrontEnd" type="edu.cmu.sphinx.frontend.FrontEnd">
    - <propertylist name="pipeline">
    <item>audioFileDataSource</item>
    <item>speechClassifier</item>
    <item>speechMarker</item>
    <item>nonSpeechDataFilter</item>
    <item>premphasizer</item>
    <item>windower</item>
    <item>fft</item>
    <item>melFilterBank</item>
    <item>dct</item>
    <item>liveCMN</item>
    -
    <item>featureExtraction</item>
    </propertylist>
    </component>
    <component name="audioFileDataSource" type="edu.cmu.sphinx.frontend.util.AudioFileDataSource">
    - <component name="speechClassifier" type="edu.cmu.sphinx.frontend.endpoint.SpeechClassifier">
    -
    </component>
    <component name="nonSpeechDataFilter" type="edu.cmu.sphinx.frontend.endpoint.NonSpeechDataFilter">
    - <component name="speechMarker" type="edu.cmu.sphinx.frontend.endpoint.SpeechMarker">
    -
    </component>
    - <component name="premphasizer" type="edu.cmu.sphinx.frontend.filter.Preemphasizer">
    -
    </component>
    - <component name="windower" type="edu.cmu.sphinx.frontend.window.RaisedCosineWindower">
    -
    </component>
    <component name="fft" type="edu.cmu.sphinx.frontend.transform.DiscreteFourierTransform">
    - <component name="melFilterBank" type="edu.cmu.sphinx.frontend.frequencywarp.MelFrequencyFilterBank">
    -
    </component>
    <component name="dct" type="edu.cmu.sphinx.frontend.transform.DiscreteCosineTransform">
    <component name="liveCMN" type="edu.cmu.sphinx.frontend.feature.LiveCMN">
    <component name="batchCMN" type="edu.cmu.sphinx.frontend.feature.BatchCMN">
    <component name="featureExtraction" type="edu.cmu.sphinx.frontend.feature.DeltasFeatureExtractor">
    -
    -
    -
    - <component name="accuracyTracker" type="edu.cmu.sphinx.instrumentation.BestPathAccuracyTracker">
    <property name="recognizer" value="${recognizer}">
    <property name="showAlignedResults" value="false">
    <property name="showRawResults" value="false">
    </property></property></property></component>
    - <component name="memoryTracker" type="edu.cmu.sphinx.instrumentation.MemoryTracker">
    <property name="recognizer" value="${recognizer}">
    <property name="showSummary" value="false">
    <property name="showDetails" value="false">
    </property></property></property></component>
    - <component name="speedTracker" type="edu.cmu.sphinx.instrumentation.SpeedTracker">
    <property name="recognizer" value="${recognizer}">
    <property name="frontend" value="${frontend}">
    <property name="showSummary" value="true">
    <property name="showDetails" value="false">
    </property></property></property></property></component>
    - <component name="recognizerMonitor" type="edu.cmu.sphinx.instrumentation.RecognizerMonitor">
    <property name="recognizer" value="${recognizer}">
    - <propertylist name="allocatedMonitors">
    <item>configMonitor</item>
    </propertylist>
    </property></component>
    - <component name="configMonitor" type="edu.cmu.sphinx.instrumentation.ConfigMonitor">
    <property name="showConfig" value="true">
    </property></component>
    -
    -
    -
    - <component name="logMath" type="edu.cmu.sphinx.util.LogMath">
    <property name="logBase" value="1.0001">
    <property name="useAddTable" value="true">
    </property></property></component>
    </component></component></component></component></component></component></component></component></component></property></property></property></property></property></property></property></property></property></property></config>

     

  • Nickolay V. Shmyrev

    Nickolay V. Shmyrev - 2010-09-27

    Hello

    Beams in your configuration file as well as language model aren't optimal for
    maximum decoding accuracy. We have several carefully optimized configuraitons
    for standard decoding tasks. For example tests/performance/wsj20k is a
    configuration for the decoding task with vocabulary of 20000 words.

     

  • Jher

    Jher - 2010-09-28

    Can you send me a file or post it here how will I do it. I really really need
    it for my thesis.
    Thanks.

     

Log in to post a comment.