1

Trying edu.cmu.sphinx.pocketsphinx with processRaw to detect speech.

Using the following config:

en-us.lm.bin language model

en-us-ptm acoustic model

cmudict-en-us.dict dictionary

also setting remove_noise to True and samprate to 8000

I want to do a Ngram Search.

This is the loop I use:

    Decoder decoder = recognizer.getDecoder();
    int chunk_size = 1024;
    int index_start = 0;
    int index_finish = index_start+chunk_size-1;
    boolean doit = true;

    decoder.startUtt();

    while (doit)
    {
        short[] slice = Arrays.copyOfRange(audioBuffer, index_start, index_finish);
        int processRawRes = decoder.processRaw((slice), slice.length, false, false);

        index_start = index_finish;
        index_finish = index_start+chunk_size-1;

        if (index_finish>audioBuffer.length-1)
        {
            doit = false;

        }
    }// while (doit)

    decoder.endUtt();

When do I call 

decoder.getInSpeech();

Thanks.

Arnon Ilani
  • 63
  • 6
  • Already asked the same question at https://stackoverflow.com/questions/51726743/pocketsphinx-how-to-understand-when-gethypstr-returns-empty-yet-getinspeech – Nikolay Shmyrev Aug 18 '18 at 10:11

0 Answers0