Question

我正在尝试java sphinx语音识别。最初我设置了hello world程序并运行它，但是正在生成跟随错误

class not found !java.lang.ClassNotFoundException:           edu.cmu.sphinx.model.acoustic.WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz.Model 
Exception in thread "main" Property exception component:'flatLinguist' property:'acousticModel' - component 'wsj' is missing

我的配置文件是：

    <?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="flatLinguist"/>
        <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="trivialPruner"
                type="edu.cmu.sphinx.decoder.pruner.SimplePruner"/>

    <component name="threadedScorer"
                type="edu.cmu.sphinx.decoder.scorer.ThreadedAcousticScorer">
        <property name="frontend" value="${frontend}"/>
    </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.jsapi.JSGFGrammar">
        <property name="dictionary" value="dictionary"/>
        <property name="grammarLocation"
               value="file:///F:\realeffecx\cabin\VBrowser\src\vbrowser\hello.gram"/>
        <property name="grammarName" value="hello"/>
<property name="logMath" value="logMath"/>
    </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="allowMissingWords" value="false"/>
        <property name="unitManager" value="unitManager"/>
    </component>

    <!-- ******************************************************** -->
    <!-- The acoustic model configuration                         -->
    <!-- ******************************************************** -->
    <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>

    <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>


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

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

    <!-- ******************************************************** -->
    <!-- The frontend configuration                               -->
    <!-- ******************************************************** -->

    <component name="frontEnd" type="edu.cmu.sphinx.frontend.FrontEnd">
        <propertylist name="pipeline">
            <item>microphone </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 live frontend configuration                          -->
    <!-- ******************************************************** -->
    <component name="epFrontEnd" type="edu.cmu.sphinx.frontend.FrontEnd">
        <propertylist name="pipeline">
            <item>microphone </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 frontend pipelines                                   -->
    <!-- ******************************************************** -->

    <component name="dataBlocker" type="edu.cmu.sphinx.frontend.DataBlocker">
        <!--<property name="blockSizeMs" value="10"/>-->
    </component>

    <component name="speechClassifier"
               type="edu.cmu.sphinx.frontend.endpoint.SpeechClassifier">
        <property name="threshold" value="13"/>
    </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="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"/>

    <component name="microphone"
               type="edu.cmu.sphinx.frontend.util.Microphone">
        <property name="closeBetweenUtterances" value="false"/>
    </component>


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

    <component name="accuracyTracker"
                type="edu.cmu.sphinx.instrumentation.BestPathAccuracyTracker">
        <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>


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

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

</config>

任何人都可以帮我解决这个问题吗？

Answer 1

你不应该使用过时的sphinx4，它现代的sphinx4更容易。你可以从github下载最新的sphinx4：

http://github.com/cmusphinx/sphinx4

最新的演示版没有使用任何xml配置文件，您可以尝试使用Dialog demo进行麦克风识别和Transcriber演示，以识别音频文件。演示代码很简单：

    Configuration configuration = new Configuration();
    // Load model from the jar
    configuration
            .setAcousticModelPath("resource:/edu/cmu/sphinx/models/acoustic/wsj");
    configuration
            .setDictionaryPath("resource:/edu/cmu/sphinx/models/acoustic/wsj/dict/cmudict.0.6d");
    configuration
            .setLanguageModelPath("resource:/edu/cmu/sphinx/models/language/en-us.lm.dmp");

    StreamSpeechRecognizer recognizer = new StreamSpeechRecognizer(
            configuration);
    InputStream stream = TranscriberDemo.class
            .getResourceAsStream("/edu/cmu/sphinx/demo/aligner/10001-90210-01803.wav");

    // Simple recognition with generic model
    recognizer.startRecognition(stream);
    SpeechResult result;
    while ((result = recognizer.getResult()) != null) {
        System.out.format("Hypothesis: %s\n", result.getHypothesis());
        System.out.println("List of recognized words and their times:");
        for (WordResult r : result.getWords()) {
            System.out.println(r);
        }
    }
    recognizer.stopRecognition();

有关详细信息，请参阅教程

http://cmusphinx.sourceforge.net/wiki/tutorialsphinx4

使用CMUSphinx的HelloWorld程序

1 个答案: