2

我一直在尝试在我的 PC 上设置 CMU-Sphinx4，以便使用语音识别制作应用程序。我能够设置大部分部件和配置并尝试运行 Sphinx 提供的 HelloWorld 应用程序，但坚持使用NullPointerExcetptionat recognizer.allocate();.

完整的堆栈跟踪：

12:34:45.501 WARNING dictionary        Missing word: <sil>
12:34:45.517 WARNING jsgfGrammar       Can't find pronunciation for <sil>
12:34:45.517 WARNING dictionary        Missing word: <sil>
12:34:45.517 WARNING jsgfGrammar       Can't find pronunciation for <sil>
Exception in thread "main" java.lang.NullPointerException
    at edu.cmu.sphinx.linguist.flat.SentenceHMMState.collectStates(SentenceHMMState.java:635)
    at edu.cmu.sphinx.linguist.flat.FlatLinguist.compileGrammar(FlatLinguist.java:452)
    at edu.cmu.sphinx.linguist.flat.FlatLinguist.allocate(FlatLinguist.java:304)
    at edu.cmu.sphinx.decoder.search.SimpleBreadthFirstSearchManager.allocate(SimpleBreadthFirstSearchManager.java:646)
    at edu.cmu.sphinx.decoder.AbstractDecoder.allocate(AbstractDecoder.java:87)
    at edu.cmu.sphinx.recognizer.Recognizer.allocate(Recognizer.java:168)
    at com.cmu.sphinx.HelloWorld.main(HelloWorld.java:42)

代码：

 package com.cmu.sphinx;

import edu.cmu.sphinx.frontend.util.Microphone;
import edu.cmu.sphinx.recognizer.Recognizer;
import edu.cmu.sphinx.result.Result;
import edu.cmu.sphinx.util.props.ConfigurationManager;



public class HelloWorld {

public static void main(String[] args) {
    ConfigurationManager cm;

    if (args.length > 0) {
        cm = new ConfigurationManager(args[0]);
    } else {
        cm = new ConfigurationManager(HelloWorld.class.getResource("helloworld.config.xml"));
    }

        Recognizer recognizer = (Recognizer) cm.lookup("recognizer");
        recognizer.allocate();

        // start the microphone or exit if the program if this is not possible
        Microphone microphone = (Microphone) cm.lookup("microphone");
        if (!microphone.startRecording()) {
            System.out.println("Cannot start microphone.");
            recognizer.deallocate();
            System.exit(1);
        }

        System.out.println("Say: (Good morning | Hello) ( Bhiksha | Evandro | Paul | Philip     | Rita | Will )");

        // loop the recognition until the programm exits.
        while (true) {
            System.out.println("Start speaking. Press Ctrl-C to quit.\n");

            Result result = recognizer.recognize();

            if (result != null) {
                String resultText = result.getBestFinalResultNoFiller();
                System.out.println("You said: " + resultText + '\n');
            } else {
                System.out.println("I can't hear what you said.\n");
            }
        }
    }    
}

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:/com/cmu/sphinx/"/>
        <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/dict/cmudict.0.6d"/>
        <property name="fillerPath"
     value="resource:/edu/cmu/sphinx/model/acoustic/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/dict"/>
        <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.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:/edu/cmu/sphinx/model/acoustic/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/"/>
    </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>

语法

#JSGF V1.0;

/**
 * JSGF Grammar for Hello World example
 */

grammar hello;

public <greet> = (Good morning | Hello) ( Bhiksha | Evandro | Paul | Philip | Rita | Will );
4

2 回答 2

2

终于可以运行 Sphinx4 的“HelloWorld”应用程序了。对于上述问题，我不得不更改配置文件。

早些时候的fillerPath财产是：

<property name="fillerPath"
 value="resource:/edu/cmu/sphinx/model/acoustic/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/dict"/>

我刚刚添加了fillerdict它并且它起作用了：

<property name="fillerPath"
     value="resource:/edu/cmu/sphinx/model/acoustic/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/dict/fillerdict"/>
于 2012-03-21T07:41:02.020 回答
0

它说你的填充字典缺少这个词<sil>。您的填充路径不正确。它需要加载noisedict。

这部分配置文件：

<property name="fillerPath"
 value="resource:/edu/cmu/sphinx/model/acoustic/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/dict"/>

一定是这样的

<property name="fillerPath"
 value="resource:/edu/cmu/sphinx/model/acoustic/WSJ_8gau_13dCep_16k_40mel_130Hz_6800Hz/noisedict"/>
于 2012-03-20T21:05:36.950 回答