1

我目前正在研究 Sphinx4，更具体地说是 TranslatorDemo。但是，当我运行它时，它的默认字典和模型仅输出数字。说明说要更改我拥有的这个特定模型的 config.xml 文件，但是阅读它让我感到困惑，并且多次尝试更改字典名称似乎不起作用。

这是页面上的说明：

http://cmusphinx.sourceforge.net/sphinx4/src/apps/edu/cmu/sphinx/demo/transcriber/README.html http://cmusphinx.sourceforge.net/sphinx4/doc/ProgrammersGuide.html

这是我的配置文件：

<?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.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 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.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 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"/>


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

我已经多次尝试将字典更改为数字以外的内容，并且我尝试了其他一些东西，但我们将不胜感激，或者至少简化说明会更好。谢谢你。

4

1 回答 1

0

改变字典是不够的。您必须为您的单词创建两个字典条目并将新单词包含在语言模型中 - 在您的情况下是 JSGF 语法。

您将需要确定新词在应用程序中出现的方式和时间，并创建适当的 jsgf 定义。

或者，您可以创建一个 n-gram 语言模型（即使只有 unigrams）。它可以根据您的语料库自动生成（使用lmtoolsphinx utils），也可以手动创建。

于 2013-07-21T20:30:58.937 回答