/// <summary>
/// Action to catch audio frames as voice processor produces them
/// </summary>
/// <param name="pcm">Frame of pcm audio</param>
private void OnFrameCaptured(short[] pcm)
{
try
{
bool _isFinalized = _rhino.Process(pcm);
if (_isFinalized)
{
Inference inference = _rhino.GetInference();
if (_inferenceCallback != null)
{
_inferenceCallback.Invoke(inference);
}
_voiceProcessor.StopRecording();
}
}
catch (Exception ex)
{
if (_errorCallback != null)
{
_errorCallback(ex);
}
else
{
Debug.LogError(ex.ToString());
}
}
}
/// <summary>
/// Processes a frame of the incoming audio stream. Upon detection of wake word and completion of follow-on command
/// inference invokes user-defined callbacks.
/// </summary>
/// <param name="pcm">
/// A frame of audio samples. The number of samples per frame can be found by calling `.FrameLength`.
/// The incoming audio needs to have a sample rate equal to `.SampleRate` and be 16-bit linearly-encoded.
/// Picovoice operates on single-channel audio.
/// </param>
public void Process(short[] pcm)
{
if (pcm.Length != FrameLength)
{
throw new ArgumentException(string.Format("Input audio frame size ({0}) was not the size specified by Picovoice engine ({1}). ", pcm.Length, FrameLength) +
"Use picovoice.FrameLength to get the correct size.");
}
if (_porcupine == null || _rhino == null)
{
throw new ObjectDisposedException("picovoice", "Cannot process frame - resources have been released.");
}
if (!_isWakeWordDetected)
{
int keywordIndex = _porcupine.Process(pcm);
if (keywordIndex >= 0)
{
_isWakeWordDetected = true;
_wakeWordCallback.Invoke();
}
}
else
{
bool isFinalized = _rhino.Process(pcm);
if (isFinalized)
{
_isWakeWordDetected = false;
_inferenceCallback.Invoke(_rhino.GetInference());
}
}
}