Streaming input to System.Speech.Recognition.SpeechRecognitionEngine

Question

I am trying to do "streaming" speech recognition in C# from a TCP socket. The problem I am having is that SpeechRecognitionEngine.SetInputToAudioStream() seems to require a Stream of a defined length which can seek. Right now the only way I can think to make this work is to repeatedly run the recognizer on a MemoryStream as more input comes in.

Here's some code to illustrate:

            SpeechRecognitionEngine appRecognizer = new SpeechRecognitionEngine();

            System.Speech.AudioFormat.SpeechAudioFormatInfo formatInfo = new System.Speech.AudioFormat.SpeechAudioFormatInfo(8000, System.Speech.AudioFormat.AudioBitsPerSample.Sixteen, System.Speech.AudioFormat.AudioChannel.Mono);

            NetworkStream stream = new NetworkStream(socket,true);
            appRecognizer.SetInputToAudioStream(stream, formatInfo);
            // At the line above a "NotSupportedException" complaining that "This stream does not support seek operations."

Does anyone know how to get around this? It must support streaming input of some sort, since it works fine with the microphone using SetInputToDefaultAudioDevice().

Thanks, Sean

Answer 1

I got live speech recognition working by overriding the stream class:

class SpeechStreamer : Stream
{
    private AutoResetEvent _writeEvent;
    private List<byte> _buffer;
    private int _buffersize;
    private int _readposition;
    private int _writeposition;
    private bool _reset;

    public SpeechStreamer(int bufferSize)
    {
        _writeEvent = new AutoResetEvent(false);
         _buffersize = bufferSize;
         _buffer = new List<byte>(_buffersize);
         for (int i = 0; i < _buffersize;i++ )
             _buffer.Add(new byte());
        _readposition = 0;
        _writeposition = 0;
    }

    public override bool CanRead
    {
        get { return true; }
    }

    public override bool CanSeek
    {
        get { return false; }
    }

    public override bool CanWrite
    {
        get { return true; }
    }

    public override long Length
    {
        get { return -1L; }
    }

    public override long Position
    {
        get { return 0L; }
        set {  }
    }

    public override long Seek(long offset, SeekOrigin origin)
    {
        return 0L;
    }

    public override void SetLength(long value)
    {

    }

    public override int Read(byte[] buffer, int offset, int count)
    {
        int i = 0;
        while (i<count && _writeEvent!=null)
        {
            if (!_reset && _readposition >= _writeposition)
            {
                _writeEvent.WaitOne(100, true);
                continue;
            }
            buffer[i] = _buffer[_readposition+offset];
            _readposition++;
            if (_readposition == _buffersize)
            {
                _readposition = 0;
                _reset = false;
            }
            i++;
        }

        return count;
    }

    public override void Write(byte[] buffer, int offset, int count)
    {
        for (int i = offset; i < offset+count; i++)
        {
            _buffer[_writeposition] = buffer[i];
            _writeposition++;
            if (_writeposition == _buffersize)
            {
                _writeposition = 0;
                _reset = true;
            }
        }
        _writeEvent.Set();

    }

    public override void Close()
    {
        _writeEvent.Close();
        _writeEvent = null;
        base.Close();
    }

    public override void Flush()
    {

    }
}

... and using an instance of that as the stream input to the SetInputToAudioStream method. As soon as the stream returns a length or the returned count is less than that requested the recognition engine thinks the input has finished. This sets up a circular buffer that never finishes.