Adiilah - 2008-02-20

Hello all,
while running my sphinx4 application, i obtain lotzz of warnings like words not found in dictionary..and it's going on displaying these lines:

06:59.471 INFO trigramModel LM Cache: 3-g 577 2-g 381
06:59.471 INFO trigramModel LM Cache: 3-g 577 2-g 381
06:59.511 INFO trigramModel LM Cache: 3-g 577 2-g 381
06:59.521 INFO trigramModel LM Cache: 3-g 577 2-g 381
06:59.531 INFO trigramModel LM Cache: 3-g 577 2-g 381
06:59.531 INFO trigramModel LM Cache: 3-g 577 2-g 381
06:59.541 INFO trigramModel LM Cache: 3-g 577 2-g 381
06:59.541 INFO trigramModel LM Cache: 3-g 577 2-g 381
06:59.561 INFO trigramModel LM Cache: 3-g 577 2-g 381
06:59.571 INFO trigramModel LM Cache: 3-g 577 2-g 381

Can anyone please advice me what's wrong?It's really very urgent.My config file is a follows:

<?xml version="1.0" encoding="UTF-8"?>

<!--
Sphinx-4 Configuration file
-->

<!-- ******** -->
<!-- an4 configuration file -->
<!-- ******** -->

<config>

<!-- ******** -->
<!-- frequently tuned properties -->
<!-- ******** -->

<property name="relativeBeamWidth" value="1E-60"/>

<property name="absoluteWordBeamWidth" value="22"/>
<property name="relativeWordBeamWidth" value="1E-30" />
<property name="wordInsertionProbability" value=".2" />
<property name="languageWeight" value="10.5" />
<property name="silenceInsertionProbability" value=".1" />
<property name="acousticLookahead" value="1.7" />
<property name="absoluteBeamWidth" value="-1" />

<property name="frontend" value="epFrontEnd"/>
<property name="recognizer" value="recognizer"/>
<property name="showCreations" value="true"/>
<property name="logLevel" value="INFO"/>

<!-- ******** -->
<!-- word recognizer configuration -->
<!-- ******** -->

<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>
<item>beamFinder</item>

</propertylist>
</component>

<component name="lexTreeLinguist"
type="edu.cmu.sphinx.linguist.lextree.LexTreeLinguist">
<property name="silenceInsertionProbability"
value="${silenceInsertionProbability}" />
<property name="wantUnigramSmear" value="true" />
<property name="fillerInsertionProbability" value=".02" />
<property name="addFillerWords" value="true" />
<property name="acousticModel" value="wsj" />
<property name="languageModel" value="trigramModel" />
<property name="wordInsertionProbability"
value="${wordInsertionProbability}" />
<property name="languageWeight" value="14" />
<property name="logMath" value="logMath" />
<property name="dictionary" value="dictionary" />
<property name="unigramSmearWeight" value="1" />
<property name="cacheSize" value="0" />
<property name="generateUnitStates" value="false" />
<property name="unitManager" value="unitManager" />
</component>

<!-- ******** -->
<!-- The Decoder configuration -->
<!-- ******** -->

<component name="decoder" type="edu.cmu.sphinx.decoder.Decoder">
<property name="searchManager" value="wordPruningSearchManager"/>
</component>

  • <!-- ********
    -->
  • <!-- wordPruningSearchManager
    -->
  • <!-- ********
    -->
  • <component name="wordPruningSearchManager"
    type="edu.cmu.sphinx.decoder.search.WordPruningBreadthFirstSearchManager">
    <property name="scorer" value="threadedScorer" />
    <property name="pruner" value="trivialPruner" />
    <property name="acousticLookaheadFrames" value="2.0" />
    <property name="logMath" value="logMath" />
    <property name="activeListManager" value="activeListManager" />
    <property name="buildWordLattice" value="true" />
    <property name="maxLatticeEdges" value ="50" />
    <property name="relativeBeamWidth" value="1E-60" />
    <property name="growSkipInterval" value="8" />
    <property name="linguist" value="lexTreeLinguist" />
    <property name="checkStateOrder" value="false" />
    <property name="keepAllTokens" value="true" />
    </component>

<component name="activeList"
type="edu.cmu.sphinx.decoder.search.PartitionActiveListFactory">
<property name="logMath" value="logMath"/>
<property name="absoluteBeamWidth" value="${absoluteBeamWidth}"/>
<property name="relativeBeamWidth" value="${relativeBeamWidth}"/>
</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="true"/>
<property name="numThreads" value="0"/>
<property name="minScoreablesPerThread" value="10"/>
<property name="scoreablesKeepFeature" value="true"/>
</component>

<!-- ******* -->
<!-- acoustic model -->
<!-- ******* -->

<component name="wsj"
type="edu.cmu.sphinx.model.acoustic.WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz.Model">
<property name="loader" value="wsjLoader" />
<property name="unitManager" value="unitManager" />
</component>
<!-- ******* -->
<!-- sphinx3Loader -->
<!-- ******* -->
<component name="wsjLoader"
type="edu.cmu.sphinx.model.acoustic.WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz.ModelLoader">
<property name="logMath" value="logMath" />
<property name="unitManager" value="unitManager" />
</component>
<!-- ******* -->
<!-- trigramModel -->
<!-- ******* -->
<component name="trigramModel"

type="edu.cmu.sphinx.linguist.language.ngram.large.LargeTrigramModel">
<property name="unigramWeight" value=".5"/>
<property name="maxDepth" value="3"/>
<property name="logMath" value="logMath"/>
<property name="dictionary" value="dictionary"/>
<property name="location"
value="C:/Documents and Settings/Mohammad Reaaz/My Documents/Mobile_Translator/language_model.arpaformat.DMP"/>
</component>

<!-- ******** -->
<!-- The Dictionary configuration -->
<!-- ******** -->

<component name="dictionary"
type="edu.cmu.sphinx.linguist.dictionary.FastDictionary">
<property name="dictionaryPath"
value="resource:/edu.cmu.sphinx.model.acoustic.WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz.Model!/edu/cmu/sphinx/model/acoustic/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/dict/cmudict.0.6d"/>
<property name="fillerPath"
value="resource:/edu.cmu.sphinx.model.acoustic.WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz.Model!/edu/cmu/sphinx/model/acoustic/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/dict/fillerdict"/>
<property name="addSilEndingPronunciation" value="false"/>
<property name="wordReplacement" value="&lt;sil&gt;"/>
<property name="allowMissingWords" value="false"/>
<property name="unitManager" value="unitManager"/>
</component>

<!-- ******** -->
<!-- The unit manager configuration -->
<!-- ******** -->

<component name="unitManager"
type="edu.cmu.sphinx.linguist.acoustic.UnitManager"/>

<!-- ******** -->
<!-- The live frontend configuration -->
<!-- ******** -->
<component name="epFrontEnd" type="edu.cmu.sphinx.frontend.FrontEnd">
<propertylist name="pipeline">
<item>streamDataSource </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>batchCMN </item>
<item>featureExtraction </item>
</propertylist>
</component>

<!-- ******** -->
<!-- The frontend pipelines -->
<!-- ******** -->

<component name="streamDataSource"
type="edu.cmu.sphinx.frontend.util.StreamDataSource">
<property name="sampleRate" value="16000"/>
<property name="bitsPerSample" value="16"/>
<property name="bigEndianData" value="false"/>
<property name="signedData" value="true"/>
<property name="bytesPerRead" value="320"/>
</component>

<component name="speechClassifier"
type="edu.cmu.sphinx.frontend.endpoint.SpeechClassifier">
<property name="threshold" value="16"/>
</component>

<component name="nonSpeechDataFilter"
type="edu.cmu.sphinx.frontend.endpoint.NonSpeechDataFilter"/>

<component name="speechMarker"
type="edu.cmu.sphinx.frontend.endpoint.SpeechMarker" >
<property name="speechTrailer" value="50"/>
</component>

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

<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">
</component>

<component name="dct"
type="edu.cmu.sphinx.frontend.transform.DiscreteCosineTransform"/>

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

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

<!-- ********** -->
<!-- monitors -->
<!-- ********** -->

<component name="accuracyTracker"
type="edu.cmu.sphinx.instrumentation.AccuracyTracker">
<property name="recognizer" value="${recognizer}"/>
<property name="showAlignedResults" value="false"/>
<property name="showRawResults" value="false"/>
</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"/>
</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"/>
</component>

  • <!-- ********
    -->
  • <!-- activeListManager
    -->
  • <!-- ********
    -->
  • <component name="activeListManager"
    type="edu.cmu.sphinx.decoder.search.SimpleActiveListManager">
  • <propertylist name="activeListFactories">
    <item>unitExitActiveList</item>
    <item>wordActiveList</item>
    <item>wordActiveList</item>
    <item>activeList</item>
    <item>activeList</item>
    <item>activeList</item>
    </propertylist>
    </component>

<!-- *******
-->
- <!-- unitExitActiveList
-->
- <!-- *******
-->
- <component name="unitExitActiveList"
type="edu.cmu.sphinx.decoder.search.PartitionActiveListFactory">
<property name="absoluteBeamWidth" value="-1" />
<property name="logMath" value="logMath" />
<property name="relativeBeamWidth" value="${relativeBeamWidth}" />
</component>
- <!-- *******
-->
- <!-- wordActiveList
-->
- <!-- *******
-->
- <component name="wordActiveList"
type="edu.cmu.sphinx.decoder.search.WordActiveListFactory">
<property name="absoluteBeamWidth" value="21" />
<property name="logMath" value="logMath" />
<property name="relativeBeamWidth" value="1E-25" />
</component>

  • <!-- ********
    -->
  • <!-- recognizerMonitor
    -->
  • <!-- ********
    -->
  • <component name="recognizerMonitor"

type="edu.cmu.sphinx.instrumentation.RecognizerMonitor">
<property name="recognizer" value="recognizer"/>
<propertylist name="allocatedMonitors">
<item>configMonitor </item>
</propertylist>
</component>

<!-- create the configMonitor -->
<component name="configMonitor"
type="edu.cmu.sphinx.instrumentation.ConfigMonitor">
<property name="showConfig" value="false"/>
<!--property name="showConfigAdGDL" value="true"/-->
</component>

<!-- ********** -->
<!-- Miscellaneous components -->
<!-- ********** -->

<component name="logMath" type="edu.cmu.sphinx.util.LogMath">
<property name="logBase" value="1.0001"/>
<property name="useAddTable" value="true"/>
</component>

<component name="confidenceScorer"
type="edu.cmu.sphinx.result.MAPConfidenceScorer">
<property name="languageWeight" value="${languageWeight}"/>
</component>

<!-- ******* -->
<!-- beamFinder (seems like a good idea but causes strange
warnings-->
<!-- ******* -->

&lt;component name=&quot;beamFinder&quot;
      type=&quot;edu.cmu.sphinx.instrumentation.BeamFinder&quot;&gt;
    &lt;property name=&quot;showDetails&quot; value=&quot;true&quot;/&gt;
    &lt;property name=&quot;logMath&quot; value=&quot;logMath&quot;/&gt;
    &lt;property name=&quot;showSummary&quot; value=&quot;true&quot;/&gt;
    &lt;property name=&quot;recognizer&quot; value=&quot;${recognizer}&quot;/&gt;
    &lt;property name=&quot;enable&quot; value=&quot;false&quot;/&gt;
&lt;/component&gt;

</config>