I need a dictionary and a model the language

[pini]

Please I need, a dictionary, the model of language and the file .mdef to make an application of voice recognition.

The application sirvira to move the mouse with voice commandos, but no matter how hard attempt I to create these archives is impossible to me to obtain that it works.

the dicionario and the model of the language or which could construct thanks to the application that is offered in this connection http://www.speech.cs.cmu.edu/tools/lmtool.html. But even so it does not work to me.

Please to have if somebody can help me outside whereupon a small dictionary it is worth to me well. because on the other hand when I prove with the dictionary unloaded the package (cmudict.0.6d) it says perhaps to me that the memory fills because this dictionary contains too many words.

A greeting and thank you very much

[pini]

as I must create a dicionario and a model of language in Spanish?

[The Grand Janitor]

If you build the system from scratch, you should. but probably you could try to start from this page first.

http://speech.mty.itesm.mx/~jnolazco/proyectos.htm

-a

[Vero]

hi,
I have a proyect in spanish to, but the rate of recognize of sphinx is very low, do you something else?
i prove with htk and is very good but the license is a problem.
bye

Hola,
Yo estoy realizando un proyecto en español (Español Colombiano), tengo el diccionario, el modelo acustico y el modelo de lenguaje, pero la tasa de reconocimiento es muy baja, como del 8% (tasa de error 91.88%), alguno de ustedes conoce un reconocedor mejor?
Ya probe con htk, el reconocimiento es muy bueno casi del 100%, pero hay problemas con la licencia (software solo de experimentacion).
Chao.

[pini]

Thanks for this connection in dictionary in Spanish me vendra very well, as well as the Model Definition cases out for Spanish, nevertheless the language model that this page provides does not work to me as I can create a file .lm

[The Grand Janitor]

It always take a while to prepare resource. :-) So have fun! -a

[pini]

Hello thank you very much by the aid already and been able to make a reconocedor of voice that accepts a dictionary to me created in Spanish, nevertheless the results are not absolutely good and tendre that for taking other options to make my project.

to have if I have luck and I can analyze the information stored in an object dataline, so that it recognizes although single it is a pair of words.

Thank you very much again by the aid

[The Grand Janitor]

You are always welcomed.
Do note that the dictionary I pointed to you is for Mexican Spanish. You might want to fine-tune for the specific purpose.

Have fun with Sphinx!
-tgj

[pini]

If desire a fine degree of frequency that I must change to the file config.xml?.

This file I have it formed of the following way, and it does not pass anything because he is Spanish Mexican since there is no great difference with the words that I want to use for my application.

Please hechame a look to the file config.xml to see if you can orient to me that I must change
<?xml version="1.0" encoding="UTF-8"?>

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

<!-- ******** -->
<!-- biship configuration file -->
<!-- ******** -->

<config>
<!-- ******** -->
<!-- frequently tuned properties -->
<!-- ******** -->
<property name="absoluteBeamWidth" value="500"/>
<property name="relativeBeamWidth" value="1E-80"/>
<property name="absoluteWordBeamWidth" value="20"/>
<property name="relativeWordBeamWidth" value="1E-60"/>
<property name="wordInsertionProbability" value="1E-16"/>
<property name="languageWeight" value="7.0"/>
<property name="silenceInsertionProbability" value=".1"/>
<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>
        <item>recognizerMonitor </item>
    </propertylist>
</component>

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

<component name="decoder" type="edu.cmu.sphinx.decoder.Decoder">
    <property name="searchManager" value="wordPruningSearchManager"/>
    <property name="featureBlockSize" value="50"/>
</component>

<!-- ******************************************************** -->
<!-- The Search Manager                                       -->
<!-- ******************************************************** -->

<component name="wordPruningSearchManager" 
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="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>


<!-- ******************************************************** -->
<!-- The Active Lists                                         -->
<!-- ******************************************************** -->

<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 Pruner                                               -->
<!-- ******************************************************** --> 
<component name="trivialPruner" 
            type="edu.cmu.sphinx.decoder.pruner.SimplePruner"/>

<!-- ******************************************************** -->
<!-- TheScorer                                                -->
<!-- ******************************************************** --> 
<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="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 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/dicEs.dict"/>
    <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="wordReplacement" value="<sil>"/>
    <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="resource:/AudioReconocedor!/trigramEs.lm"/>
    <property name="logMath" value="logMath"/>
    <property name="dictionary" value="dictionary"/>
    <property name="maxDepth" value="3"/>
    <property name="unigramWeight" value=".7"/>
</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="mfcFrontEnd" 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>

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

<component name="windower" 
type="edu.cmu.sphinx.frontend.window.RaisedCosineWindower"/>

<component name="fft" 
    type="edu.cmu.sphinx.frontend.transform.DiscreteFourierTransform"/>

<component name="melFilterBank" 
    type="edu.cmu.sphinx.frontend.frequencywarp.MelFrequencyFilterBank"/>

<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.AccuracyTracker">
    <property name="recognizer" value="${recognizer}"/>
    <property name="showRawResults" value="false"/>
    <property name="showAlignedResults" value="false"/>
</component>

<component name="memoryTracker" 
            type="edu.cmu.sphinx.instrumentation.MemoryTracker">
    <property name="recognizer" value="${recognizer}"/>
<property name="showDetails" value="false"/>
<property name="showSummary" value="false"/>
</component>

<component name="speedTracker" 
            type="edu.cmu.sphinx.instrumentation.SpeedTracker">
    <property name="recognizer" value="${recognizer}"/>
    <property name="frontend" value="${frontend}"/>
<property name="showDetails" value="false"/>
</component>

<component name="recognizerMonitor" 
            type="edu.cmu.sphinx.instrumentation.RecognizerMonitor">
    <property name="recognizer" value="${recognizer}"/>
    <propertylist name="allocatedMonitors">
        <item>configMonitor </item>
    </propertylist>
</component>

<component name="configMonitor" 
            type="edu.cmu.sphinx.instrumentation.ConfigMonitor">
    <property name="showConfig" 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>

the archive trigram.ml is:

Language model created by QuickLM on Wed Nov 1 11:38:15 EST 2006
Copyright (c) 1996-2000
Carnegie Mellon University and Alexander I. Rudnicky

This model based on a corpus of 2 sentences and 20 words
The (fixed) discount mass is 0.5

\data\
ngram 1=20
ngram 2=20
ngram 3=18

\1-grams:
-1.3424 </s> -0.3010
-1.3424 <s> -0.2808
-1.6435 ABAJO -0.2910
-1.6435 ARRIBA -0.2910
-1.6435 CINCO -0.2910
-1.6435 COGER -0.2910
-1.6435 CUATRO -0.2910
-1.6435 DEJAR -0.2910
-1.6435 DERECHA -0.2910
-1.6435 DOS -0.2910
-1.6435 FIN -0.2910
-1.6435 IZQUIERDA -0.2910
-1.6435 MAS -0.2910
-1.6435 MENOS -0.2910
-1.6435 OCHO -0.2808
-1.6435 PULSAR -0.2910
-1.6435 SEIS -0.2910
-1.6435 SIETE -0.2808
-1.6435 TRES -0.2910
-1.6435 UNO -0.2910

\2-grams:
-0.6021 <s> ARRIBA 0.0000
-0.6021 <s> OCHO 0.0000
-0.3010 ABAJO DERECHA 0.0000
-0.3010 ARRIBA ABAJO 0.0000
-0.3010 CINCO SEIS 0.0000
-0.3010 COGER DEJAR 0.0000
-0.3010 CUATRO CINCO 0.0000
-0.3010 DEJAR FIN 0.0000
-0.3010 DERECHA IZQUIERDA 0.0000
-0.3010 DOS TRES 0.0000
-0.3010 FIN MAS 0.0000
-0.3010 IZQUIERDA PULSAR 0.0000
-0.3010 MAS MENOS 0.0000
-0.3010 MENOS UNO 0.0000
-0.3010 OCHO </s> -0.3010
-0.3010 PULSAR COGER 0.0000
-0.3010 SEIS SIETE 0.0000
-0.3010 SIETE </s> -0.3010
-0.3010 TRES CUATRO 0.0000
-0.3010 UNO DOS 0.0000

\3-grams:
-0.3010 <s> ARRIBA ABAJO
-0.3010 <s> OCHO </s>
-0.3010 ABAJO DERECHA IZQUIERDA
-0.3010 ARRIBA ABAJO DERECHA
-0.3010 CINCO SEIS SIETE
-0.3010 COGER DEJAR FIN
-0.3010 CUATRO CINCO SEIS
-0.3010 DEJAR FIN MAS
-0.3010 DERECHA IZQUIERDA PULSAR
-0.3010 DOS TRES CUATRO
-0.3010 FIN MAS MENOS
-0.3010 IZQUIERDA PULSAR COGER
-0.3010 MAS MENOS UNO
-0.3010 MENOS UNO DOS
-0.3010 PULSAR COGER DEJAR
-0.3010 SEIS SIETE </s>
-0.3010 TRES CUATRO CINCO
-0.3010 UNO DOS TRES

\end\

And the diccionary is:

ARRIBA A RR I B A
ABAJO A B A J O
DERECHA D E R E CH A
IZQUIERDA I S K I E R D A

PULSAR P U L S A R
COGER K O J E R
DEJAR D E J A R
FIN F I N

MAS M A S
MENOS M E N O S

UNO U N O
DOS D O S
TRES T R E S
CUATRO K U A T R O
CINCO S I N K O
SEIS S E I S
SIETE S I E T E
OCHO O CH O

thank you

[pini]

Hola vero, yo realice un proyecto con los paquetes de cloudGarden y el reconocimiento no era del todo malo, aunque fallaba a veces, problema... es solo para windows porque necesita un motor de reconocimiento y ademas solo funciona durante treinta dias a menos que consigas una licencia.

Por favor me podrias mandar lo que as conseguido con htk para hecharle un vistazo???, me interesa que la tasa de reconocimiento sea tan alta, seria a a la direccion ivan_pini@hotmail.com, si quieres cuando me envies lo que has conseguido te reenvio yo la aplicacion que consegui hacer con los paquetes de cloudGarden, se trata de reconocer palabras incluidas en una pequeña gramatica para despues dependendiendo de la palabra dicha mover el raton.

Un saludo y gracias