java - 接收 JSGF Gramma 规则名称

Question

我创建了一个语法

#JSGF V1.0;

/**
 * JSGF Grammar 
 */

grammar grammar;

public <number> = ( zero | one | two | three | four | five | six | seven | nine | ten
                   | eleven | twelve | thirteen | fourteen | fifteen | sixteen | seventeen | eighteen | nineteen | twenty 
                   | thirty | forty | fifty | sixty | seventy | eighty | ninety |
                    hundred | thousand | million | billion)+;                   
public <operation> = <number>{1} (plus | minus | multiply | division){1} <number>{1};
public <greet> = ( hello | hey | hi )* world;
public <sport> = (football | tennis);
public <program> = (notepad | calculator);
public <run> = (run | open | start) <program>;

我在简单的 Sphinx4 语音识别器中使用它，我即将为程序答案创建基本逻辑。

这就是程序识别单词(代码片段)的方式:

Configuration configuration = new Configuration();
        //SetVoice
        textToSpeech.setVoice("cmu-bdl-hsmm");
        // Load model from the jar
        configuration.setAcousticModelPath("resource:/edu/cmu/sphinx/models/en-us/en-us");
        configuration.setDictionaryPath("resource:/edu/cmu/sphinx/models/en-us/cmudict-en-us.dict");
        configuration.setGrammarPath("resource:/grammars");
        configuration.setGrammarName("grammar");
        configuration.setUseGrammar(true);

try {
            recognizer = new LiveSpeechRecognizer(configuration);
        } catch (IOException ex) {
            logger.log(Level.SEVERE, null, ex);
        }

        // Start recognition process pruning previously cached data.
        recognizer.startRecognition(true);

        SpeechResult speechResult = recognizer.getResult();
                    if (speechResult != null) {

                        result = speechResult.getHypothesis();
                        System.out.println("You said: [" + result + "]\n");

有没有办法获取可识别的语法规则名称？问候

Answer 1

没有办法做到这一点。如果您想执行语义分析，您可以简单地使用正则表达式解析语音识别器的输出。另请参阅

How do you retrieve tags from JSGF grammars using sphinx?

Why tags are not supported in pocketsphinx?