I am Trying to use OpenNi 2.2 and Nite 2.2 for skeleton tracking. On the other hand I want to use Kinect SDK 1.7 for Speech processing. Is it possible? I am trying to use this code. But it fails.
Init(){
openni::Device device;
openni::Status rc = openni::OpenNI::initialize();
openni::Status rc = device.open(openni::ANY_DEVICE);
nite::NiTE::initialize();
INuiSensor * NuiSensor;
HRESULT hr;
hr = NuiCreateSensorByIndex(0, &NuiSensor);
hr = pNuiSensor->NuiInitialize(NUI_INITIALIZE_FLAG_USES_AUDIO);
if (NULL == pNuiSensor || FAILED(hr))
printf("No ready Kinect found!\n");}
If this is not possible then why?? please explain.
It is possible! See kinect-i blogspot's post on how to do this. It uses a bride you can view here. However you need to use the SDK 1.6, but that sounds like it will be ok for you since you aren't using Fusion (see What's New to see what updates there were in 1.7)