目前，我们正在研究使用sphinx4进行语音识别。我们正在尝试为听写类型应用程序实现良好的响应。输入是一个wav文件，我们希望转录它。我查看了Sphinx4提供的LatticeDemo和Transcriber演示。当我使用相同的配置时，响应非常差。我试图调整配置文件，但它根本无法识别单词。提供的转录器演示是为数字，我修改了配置文件以理解单词。但我不确定我是否遗漏了一些东西。我已经附加了配置文件。请提出可以进行的任何改进。
<config>
<!-- ******************************************************** -->
<!-- frequently tuned properties -->
<!-- ******************************************************** -->
<property name="absoluteBeamWidth" value="500"/>
<property name="relativeBeamWidth" value="1E-60"/>
<property name="absoluteWordBeamWidth" value="20"/>
<property name="relativeWordBeamWidth" value="1E-40"/>
<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="true"/>
<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}"/>
</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:/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="<sil>"/>
<property name="unitManager" value="unitManager"/>
</component>
<!-- ******************************************************** -->
<!-- The Language Model configuration -->
<!-- ******************************************************** -->
<component name="trigramModel"
type="edu.cmu.sphinx.linguist.language.ngram.large.LargeTrigramModel">
<property name="unigramWeight" value=".5"/>
<property name="maxDepth" value="3"/>
<property name="logMath" value="logMath"/>
<property name="dictionary" value="dictionary"/>
<property name="location"
value="./models/language/wsj/wsj5kc.Z.DMP"/>
</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 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>
<component name="audioFileDataSource" type="edu.cmu.sphinx.frontend.util.AudioFileDataSource"/>
<component name="microphone"
type="edu.cmu.sphinx.frontend.util.Microphone">
<property name="closeBetweenUtterances" value="false"/>
</component>
<component name="dataBlocker" type="edu.cmu.sphinx.frontend.DataBlocker"/>
<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 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"/>
<!-- Newly Added.. -->
<component name="streamDataSource"
type="edu.cmu.sphinx.frontend.util.StreamDataSource">
<property name="sampleRate" value="16000"/>
<property name="bigEndianData" value="false"/>
</component>
<!-- ******************************************************* -->
<!-- monitors -->
<!-- ******************************************************* -->
<component name="accuracyTracker"
type="edu.cmu.sphinx.instrumentation.BestPathAccuracyTracker">
<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>
答案 0 :(得分：7)
识别准确性差的最常见原因是：
传入音频的采样率不匹配。它必须是16khz 16位单声道小端文件。您需要通过重新采样来修复源的采样率。
从mp3解码的音频文件中的零静音区域破坏了解码器。你可以使用抖动来引入小的随机噪声来解决这个问题。
声学模型的不匹配。您可以使用声学模型自适应来提高准确度
语言模型的不匹配。您可以创建自己的语言模型以匹配您尝试解码的词汇。
您可以从教程中获得更多信息：
http://cmusphinx.sourceforge.net/wiki/tutorial
要获得更详细的帮助，您始终可以提供要尝试解码的音频样本。它们将帮助开发人员更好地分析问题。从解码器和您的期望中提供实际结果也很有帮助。
答案 1 :(得分：2)
CMU Sphinx对我来说非常好，只是为了分享一些知识，我的设置是：
我认为关键是使用这些工具生成适当的trigram.arpa文件。
你必须根据需要调整你的sphinx配置属性，没有灵丹妙药，一些帮助我的是speechClassifierThreshold（44）和speechMarkerTrailer（77）。
希望它有所帮助或者至少能给你一些想法。