Large vocabulary speech recognition in sphinx4

问题:

As far as I know till now, sphinx4 requires grammar to identify the words. Is there anyway to get the input without using grammar rules, that is not in the grammar, somewhat like I am dictating and it will write what I will say?

回答1:

As far as I know till now, sphinx4 requires grammar to identify the words.

No, sphinx4 supports large vocabulary speech recognition

Is there anyway to get the input without using grammar rules, that is not in the grammar, somewhat like I am dictating and it will write what I will say? Or any algorithm maybe to check it?

You need to update sphinx4-5prealpha version.

You can check transcriber demo for example of large vocabulary speech recognition setup.

The code should look like this:

package com.example;

import java.io.File;
import java.io.FileInputStream;
import java.io.InputStream;

import edu.cmu.sphinx.api.Configuration;
import edu.cmu.sphinx.api.SpeechResult;
import edu.cmu.sphinx.api.LiveSpeechRecognizer;

public class TranscriberDemo {       

    public static void main(String[] args) throws Exception {

        Configuration configuration = new Configuration();

        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
                .setLanguageModelPath("resource:/edu/cmu/sphinx/models/en-us/en-us.lm.bin");

        LiveSpeechRecognizer recognizer = new LiveSpeechRecognizer(configuration);
        recognizer.startRecognition(true);

        SpeechResult result;
        while ((result = recognizer.getResult()) != null) {
            System.out.format("Hypothesis: %s\n", result.getHypothesis());
        }
        recognizer.stopRecognition();
    }
}