can i use google speech recognition api in my desktop application

Question

I want to know whether i can use speech recognition api of google for my desktop application. I have seen some example in which i have to convert the speech to a file and send to a url. But it will be little cumbersome task because in my application the user have to continuously submit his voice. So is there any other alternative to use google speech api. I am least interested to go with sphinx because its accuracy is very less and i dont know how to add new words in the dictionary and without adding it to dictionary it wont recognize new words. Any help would be appreciated.

Answer 1

Are you referring to ambient listening? I am actually working on some Voice Activity Detection algorithm with the Google Speech Recognition API. Although I haven't finished the algorithm yet, I've added a volume and frequency calculator so that you don't have to send requests to Google when the person is not talking. Here is the link to the source code.

https://github.com/The-Shadow/java-speech-api

(This isn't what I use, but it's simplistic. You can also add frequency threshold holds and stuff. I threw this code together so no guarantee it will work look at the example branch of the API.)

//package recognitionprocess;
//import org.jaudiotagger.audio.*;


import java.io.FileOutputStream;
import java.io.IOException;
import java.io.RandomAccessFile;

import javax.sound.sampled.AudioFileFormat;

import com.darkprograms.speech.recognizer.GoogleResponse;
import com.darkprograms.speech.recognizer.Recognizer;

public class RecognitionMain {

    public static void main(String[] args)  {
        try{
        ambientListening();
        }
        catch(Exception e){
            e.printStackTrace();
        }
    }

    private static void ambientListening() throws Exception{

        String filename = "tarunaudio.wav";//Your Desired FileName
        MicrophoneAnalyzer mic = new MicrophoneAnalyzer(AudioFileFormat.Type.WAVE);
       mic.open();
        mic.captureAudioToFile(filename);
        final int THRESHOLD = 10;//YOUR THRESHOLD VALUE.
        int ambientVolume = mic.getAudioVolume();//
        int speakingVolume = -2;
        boolean speaking = false;
            for(int i = 0; i<1||speaking; i++){
                int volume = mic.getAudioVolume();
                System.out.println(volume);
                if(volume>ambientVolume+THRESHOLD){
                    speakingVolume = volume;
                    speaking = true;
                    Thread.sleep(1000);
                    System.out.println("SPEAKING");
                }
                if(speaking && volume+THRESHOLD<speakingVolume){
                     break;
                }
                Thread.sleep(200);//Your refreshRate
            }
              mic.close();
            //You can also measure the volume across the entire file if you want
            //to be resource intensive.
            if(!speaking){
                 ambientListening();
            }
        Recognizer rec = new Recognizer(Recognizer.Languages.ENGLISH_US);
        GoogleResponse out = rec.getRecognizedDataForWave(filename);
        System.out.println(out.getResponse());
        ambientListening();
    }
}