使用htk进行非数字识别

Question

我一直在尝试将 HTk 与 sphinx4 结合使用用于语音识别应用程序。我以 wav 文件形式提供输入，并且使用 sphinx 提供的“Transcriber demo”和“Lattice Demo”，但是输出几乎不可接受。所以我决定将 HTK 与 Sphinx4 一起引入。但最终的输出似乎还很遥远。我确信配置可以比我正在做的进一步调整。我已经很好地搜索了是否有与使用 htk 和 sphinx4 相关的教程。除了这个令人惊叹的博客（http://nsh.nexiwave.com/2009/09/using-htk-models-in-sphinx4.html）我还没有发现其他任何东西。任何人都可以帮助我在这里提高我的识别准确性。

我的配置文件是 sphinx 如下：

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

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

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

<config>        

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

    <property name="logLevel" value="WARNING"/>

    <property name="absoluteBeamWidth"  value="-1"/>
    <property name="relativeBeamWidth"  value="1E-80"/>
    <property name="wordInsertionProbability" value="1E-36"/>
    <property name="languageWeight"     value="8"/>

    <property name="frontend" value="epFrontEnd"/>
    <property name="recognizer" value="recognizer"/>
    <property name="showCreations" value="false"/>


    <!-- ******************************************************** -->
    <!-- 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>
        </propertylist>
   </component>

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

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

  <!--   <component name="searchManager" 
        type="edu.cmu.sphinx.decoder.search.SimpleBreadthFirstSearchManager">
        <property name="logMath" value="logMath"/>
        <property name="linguist" value="lexTreeLinguist"/>
        <property name="pruner" value="trivialPruner"/>
        <property name="scorer" value="threadedScorer"/>
        <property name="activeListFactory" value="activeList"/>
    </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="searchManager" 
              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="activeListFactory" value="activeList"/>
        <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}"/>
    </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}"/>
    </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}"/>
    </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}"/>
    </component>

    <!-- ******************************************************** -->
    <!-- The linguist  configuration                              -->
    <!-- ******************************************************** -->

    <component name="flatLinguist"
                type="edu.cmu.sphinx.linguist.flat.FlatLinguist">
        <property name="logMath" value="logMath"/>
        <property name="grammar" value="jsgfGrammar"/>
        <property name="acousticModel" value="wsj"/>
        <property name="wordInsertionProbability"
                value="${wordInsertionProbability}"/>
        <property name="languageWeight" value="${languageWeight}"/>
        <property name="unitManager" value="unitManager"/>
    </component>


    <!-- ******************************************************** -->
    <!-- The Grammar  configuration                               -->
    <!-- ******************************************************** -->

    <component name="jsgfGrammar" type="edu.cmu.sphinx.jsgf.JSGFGrammar">
        <property name="dictionary" value="dictionary"/>
        <property name="grammarLocation" 
             value="resource:/edu/cmu/sphinx/demo/transcriber/"/>
        <property name="grammarName" value="digits"/>
    <property name="logMath" value="logMath"/>
    </component>

    <!-- ******************************************************** -->
    <!-- The Dictionary configuration               
        <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/noisedict"/>
        <property name="addSilEndingPronunciation" value="false"/>
        <property name="wordReplacement" value="&lt;sil&gt;"/>
        <property name="unitManager" value="unitManager"/>
    </component>             -->
    <!-- ******************************************************** -->



         <!-- ******************************************************** -->
    <!-- The Dictionary configuration                            -->
    <!-- ******************************************************** -->
    <component name="dictionary" 
        type="edu.cmu.sphinx.linguist.dictionary.FastDictionary">
        <property name="dictionaryPath"
                  value="file:C:\Raveesh\Softwares\apache-tomcat-6.0.32\apache-tomcat-6.0.32\bin\models\language\wsj\5100.dic"/>
        <property name="fillerPath" 
              value="resource:/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/noisedict"/>
        <property name="addSilEndingPronunciation" value="false"/>
        <property name="wordReplacement" value="&lt;sil&gt;"/>
        <property name="unitManager" value="unitManager"/>
    </component>

    <!-- ******************************************************** -->
    <!-- The acoustic model configuration                         -->
    <!-- ******************************************************** -->
    <component name="wsj"
               type="edu.cmu.sphinx.linguist.acoustic.tiedstate.TiedStateAcousticModel">
        <property name="loader" value="wsjLoader"/>
        <property name="unitManager" value="unitManager"/>
    </component>



        <component name="wsjLoader" type="edu.cmu.sphinx.linguist.acoustic.tiedstate.HTKLoader">
        <property name="logMath" value="logMath"/>
        <property name="modelDefinition" value="hmmdefs"/>
        <property name="unitManager" value="unitManager"/>
    </component>

<!-- 

    <component name="wsjLoader" type="edu.cmu.sphinx.linguist.acoustic.tiedstate.Sphinx3Loader">
        <property name="logMath" value="logMath"/>
        <property name="unitManager" value="unitManager"/>
        <property name="location" value="resource:/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz"/>
    </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>audioFileDataSource </item>
            <item>dataBlocker </item>
            <item>speechClassifier </item>
            <item>speechMarker </item>
            <item>nonSpeechDataFilter </item>
            <item>preemphasizer </item>
            <item>windower </item>
            <item>fft </item>
            <item>melFilterBank </item>
            <item>dct </item>
            <item>liveCMN </item>
            <item>featureExtraction </item>
        </propertylist>
    </component>



-->

 <!-- the front end configuration using the HTK loader..     -->

     <component name="epFrontEnd" type="edu.cmu.sphinx.frontend.FrontEnd">
        <propertylist name="pipeline">
        <item>streamHTKSource</item>
        </propertylist>
    </component>

    <component name="streamHTKSource" type="edu.cmu.sphinx.frontend.util.StreamHTKCepstrum">
        <property name="cepstrumLength" value="39"/>
    </component>

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

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

    <component name="dataBlocker" type="edu.cmu.sphinx.frontend.DataBlocker"/>

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

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

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

    <component name="preemphasizer"
               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="liveCMN" 
               type="edu.cmu.sphinx.frontend.feature.LiveCMN"/>

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

               <!-- Newly Added..   -->
    <component name="streamDataSource"
        type="edu.cmu.sphinx.frontend.util.StreamDataSource">
        <property name="sampleRate" value="16000"/>
        <property name="bigEndianData" value="false"/>
    </component>


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

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


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

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

    <!-- ******************************************************** -->
    <!-- The linguist  configuration                              -->
    <!-- ******************************************************** -->

    <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 name="unitManager" value="unitManager"/>
    </component>    

     <!-- ******************************************************** -->
    <!-- The Language Model configuration                         -->
    <!-- ******************************************************** -->
    <component name="trigramModel" 
        type="edu.cmu.sphinx.linguist.language.ngram.SimpleNGramModel">
        <property name="location" 
            value="file:C:\Raveesh\Softwares\apache-tomcat-6.0.32\apache-tomcat-6.0.32\bin\models\language\wsj\5100.lm"/>
        <property name="logMath" value="logMath"/>
        <property name="dictionary" value="dictionary"/>
        <property name="maxDepth" value="3"/>
        <property name="unigramWeight" value=".7"/>
    </component>    
</config>

任何帮助将非常感激

Answer 1

sphinx4 尚不支持使用 HTK 模型对音频流进行解码。 HTK 前端配置需要不同。您只能解码使用 HTK 提取的 mfc 文件，如博客中所述。博客评论中也描述了有关前端问题的详细信息。