使用sphinx 4的Java语音文本 [英] Java speech to text using sphinx 4

查看：117
本文介绍了使用sphinx 4的Java语音文本的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！

问题描述

我在使用Sphinx库运行程序时遇到问题，错误是：



I am facing problems in running a program using Sphinx library, the error is:

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
edu.cmu.sphinx.util.props.InternalConfigurationException: component 'wsj' is missing
	at edu.cmu.sphinx.util.props.PropertySheet.getComponent(PropertySheet.java:289)
	at edu.cmu.sphinx.linguist.flat.FlatLinguist.setupAcousticModel(FlatLinguist.java:278)
	at edu.cmu.sphinx.linguist.flat.FlatLinguist.newProperties(FlatLinguist.java:244)
	at edu.cmu.sphinx.util.props.PropertySheet.getOwner(PropertySheet.java:505)
	at edu.cmu.sphinx.util.props.PropertySheet.getComponent(PropertySheet.java:287)
	at edu.cmu.sphinx.decoder.search.SimpleBreadthFirstSearchManager.newProperties(SimpleBreadthFirstSearchManager.java:182)
	at edu.cmu.sphinx.util.props.PropertySheet.getOwner(PropertySheet.java:505)
	at edu.cmu.sphinx.util.props.PropertySheet.getComponent(PropertySheet.java:287)
	at edu.cmu.sphinx.decoder.AbstractDecoder.newProperties(AbstractDecoder.java:65)
	at edu.cmu.sphinx.decoder.Decoder.newProperties(Decoder.java:37)
	at edu.cmu.sphinx.util.props.PropertySheet.getOwner(PropertySheet.java:505)
	at edu.cmu.sphinx.util.props.PropertySheet.getComponent(PropertySheet.java:287)
	at edu.cmu.sphinx.recognizer.Recognizer.newProperties(Recognizer.java:90)
	at edu.cmu.sphinx.util.props.PropertySheet.getOwner(PropertySheet.java:505)
	at edu.cmu.sphinx.util.props.ConfigurationManager.lookup(ConfigurationManager.java:161)
	at com.xebia.speech.HelloWorld.main(HelloWorld.java:28)
Java Result: 1
BUILD SUCCESSFUL (total time: 0 seconds)





我的hello world文件是



My hello world file is

package com.xebia.speech-to-text-converter ; 
 
import java.io.IOException;
import java.net.URL;
 
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;
import edu.cmu.sphinx.util.props.PropertyException;
 
/**
 * A simple HelloWorld demo showing a simple speech application built using Sphinx-4. This application uses the Sphinx-4
 * endpointer, which automatically segments incoming audio into utterances and silences.
 */
public class HelloWorld {
 
    public static void main(String[] args) throws IOException, PropertyException, InstantiationException {
        ConfigurationManager cm;
 
        if (args.length > 0) {
            URL url = new URL(args[0]);
            cm = new ConfigurationManager(url);
        } 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) (( Winfred | Evandro | Paul | Philip | Will )");
 
        // loop the recognition until the program 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");
            }
        }
    }
}





Hello world配置文件





Hello world config file

<!--
   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}" />
        <property name="isCpuRelative" value="true" />
        <property name="numThreads" value="0" />
        <property name="minScoreablesPerThread" value="10" />
        <property name="scoreablesKeepFeature" value="true" />
    </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" />
    </property></component>
     
    <!-- ******************************************************** -->
    <!-- The Grammar  configuration                               -->
    <!-- ******************************************************** -->
            
    <component name="jsgfGrammar" type="edu.cmu.sphinx.jsapi.JSGFGrammar">
        <property name="dictionary" value="dictionary" />
        <property name="grammarLocation">
             value="src/main/java/com/hi/open_name_speech_to_text_convertor/"/>
        <property name="grammarName" value="hello" />
	<property name="logMath" value="logMath" />
    </property></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" />
    </property></property></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>premphasizer </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>speechClassifier </item>
            <item>speechMarker </item>
            <item>nonSpeechDataFilter </item>
            <item>premphasizer </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="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="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="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.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>
    
    
    <!-- ******************************************************* -->
    <!--  Miscellaneous components                               -->
    <!-- ******************************************************* -->
    
    <component name="logMath" type="edu.cmu.sphinx.util.LogMath">
        <property name="logBase" value="1.0001" />
        <property name="useAddTable" value="true" />
    </component>
    
</component></component></component></component></component></component></component></config>





Grammar file





Grammar file

#JSGF V1.0;
/**
* JSGF Grammar for Hello World example
*/
grammar hello;
 
public <greet> = (Good morning | Hello) <name>;
<name> = ( Winfred | Evandro | Paul | Philip | Will );</name></name></greet>





Plz i need help , its my project



Plz i need help , its my project

推荐答案

{absoluteBeamWidth}\" />
<property name=\"relativeBeamWidth\" value=\"
{absoluteBeamWidth}" /> <property name="relativeBeamWidth" value="


{relativeBeamWidth}\" />
</compon ent>

<component name=\"trivialPruner\">
type=\"edu.cmu.sphinx.decoder.pruner.SimplePruner\"/>

<component name=\"threadedScorer\">
type=\"edu.cmu.sphinx.decoder.scorer.ThreadedAcousticScorer\">
<property name=\"frontend\" 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>

<!-- ******************************************************** -->
<!-- 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=\"
{frontend}" /> <property name="isCpuRelative" value="true" /> <property name="numThreads" value="0" /> <property name="minScoreablesPerThread" value="10" /> <property name="scoreablesKeepFeature" value="true" /> </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="


这篇关于使用sphinx 4的Java语音文本的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！

查看全文
相关文章
其他开发语言最新文章
热门教程
热门工具
登录 关闭
扫码关注1秒登录
发送“验证码”获取 | 15天全站免登陆