I am working on an application for recognizing speech from pcm data. Currently I am printing the pcm buffer.
int N = AudioRecord.getMinBufferSize(8000,AudioFormat.CHANNEL_IN_MONO, AudioFormat.ENCODING_PCM_16BIT);
recorder = new AudioRecord(AudioSource.MIC, 8000, AudioFormat.CHANNEL_IN_MONO, AudioFormat.ENCODING_PCM_16BIT, N*10);
track = new AudioTrack(AudioManager.STREAM_MUSIC, 8000,
AudioFormat.CHANNEL_OUT_MONO, AudioFormat.ENCODING_PCM_16BIT, N*10, AudioTrack.MODE_STREAM);
recorder.startRecording();
/*
* Loops until something outside of this thread stops it.
* Reads the data from the recorder and writes it to the audio track f
*/
while(!stopped)
{
//Log.i("Map", "Writing new data to buffer");
short[] buffer = buffers[ix++ % buffers.length];
N = recorder.read(buffer,0,buffer.length);
for(int i = 0; i < buffer.length; i ++) {
System.out.println(String.valueOf(buffer[i]));
}
}
I would like to either 1) have the pcm data be matched to previous pcm data or 2) have it be recognized as a word. For example. If I say 'hello' inside the mic, it turns the pcm data into the word hello and I can process according to the word or if I record a 'hello' and a 'world' in two separate buffers, then say 'hello' again, it can determine that I repeated the 'hello' and not the world. Help Please.
