我正在编写一个应用程序,通过Microsoft Media Foundation从麦克风中捕获声音。 这是代码
#include <stdio.h>
#include <assert.h>
#include <mfapi.h>
#include <mfidl.h>
#include <Mfreadwrite.h>
#include <Mferror.h>
template <class T> void SafeRelease(T **ppT)
{
if (*ppT)
{
(*ppT)->Release();
*ppT = NULL;
}
}
HRESULT ProcessSamples(IMFSourceReader *pReader, IMFSinkWriter *writer)
{
HRESULT hr = S_OK;
IMFSample *pSample = NULL;
size_t cSamples = 0;
bool quit = false;
while (!quit)
{
DWORD streamIndex, flags;
LONGLONG llTimeStamp;
hr = pReader->ReadSample(
MF_SOURCE_READER_ANY_STREAM, // Stream index.
0, // Flags.
&streamIndex, // Receives the actual stream index.
&flags, // Receives status flags.
&llTimeStamp, // Receives the time stamp.
&pSample // Receives the sample or NULL.
);
if (FAILED(hr))
{
break;
}
wprintf(L"Stream %d (%I64d)\n", streamIndex, llTimeStamp);
if (flags & MF_SOURCE_READERF_ENDOFSTREAM)
{
wprintf(L"\tEnd of stream\n");
quit = true;
}
if (flags & MF_SOURCE_READERF_NEWSTREAM)
{
wprintf(L"\tNew stream\n");
}
if (flags & MF_SOURCE_READERF_NATIVEMEDIATYPECHANGED)
{
wprintf(L"\tNative type changed\n");
}
if (flags & MF_SOURCE_READERF_CURRENTMEDIATYPECHANGED)
{
wprintf(L"\tCurrent type changed\n");
}
if (flags & MF_SOURCE_READERF_STREAMTICK)
{
wprintf(L"\tStream tick\n");
}
if (pSample)
{
writer->WriteSample(streamIndex, pSample);
++cSamples;
if (cSamples > 300)quit = true;
}
SafeRelease(&pSample);
}
if (FAILED(hr))
{
wprintf(L"ProcessSamples FAILED, hr = 0x%x\n", hr);
}
else
{
wprintf(L"Processed %d samples\n", cSamples);
}
SafeRelease(&pSample);
return hr;
}
int _tmain(int argc, _TCHAR* argv[])
{
IMFMediaSource *source = 0;
IMFMediaSession* m_pSession;
IMFAttributes *pAttributes = NULL;
HRESULT hr = CoInitializeEx(NULL, COINIT_APARTMENTTHREADED | COINIT_DISABLE_OLE1DDE);
if (SUCCEEDED(hr))
{
hr = MFStartup(MF_VERSION);
}
hr = MFCreateAttributes(&pAttributes, 2);
if (SUCCEEDED(hr))
{
hr = pAttributes->SetGUID(
MF_DEVSOURCE_ATTRIBUTE_SOURCE_TYPE,
MF_DEVSOURCE_ATTRIBUTE_SOURCE_TYPE_AUDCAP_GUID
);
}
if (SUCCEEDED(hr))
{
hr = MFCreateDeviceSource(pAttributes, &source);
}
SafeRelease(&pAttributes);
hr = MFCreateAttributes(&pAttributes, 1);
IMFSourceReader *pReader;
hr = MFCreateSourceReaderFromMediaSource(source, NULL, &pReader);
IMFMediaType *type;
IMFSinkWriter *writer = 0;
hr = MFCreateSinkWriterFromURL(L"D:\\wma.wma", NULL, NULL, &writer);
IMFMediaType *inputType = 0;
hr = MFCreateMediaType(&inputType);
hr = inputType->SetGUID(MF_MT_MAJOR_TYPE, MFMediaType_Audio);
hr = inputType->SetGUID(MF_MT_SUBTYPE, MFAudioFormat_Float);
hr = inputType->SetUINT32(MF_MT_AUDIO_NUM_CHANNELS, 2);
hr = inputType->SetUINT32(MF_MT_AUDIO_SAMPLES_PER_SECOND, 44100);
hr = inputType->SetUINT32(MF_MT_AUDIO_BLOCK_ALIGNMENT, 8);
hr =inputType->SetUINT32(MF_MT_AUDIO_AVG_BYTES_PER_SECOND, 352800);
hr = inputType->SetUINT32(MF_MT_AUDIO_BITS_PER_SAMPLE, 32);
hr = inputType->SetUINT32(MF_MT_ALL_SAMPLES_INDEPENDENT, 1);
hr = inputType->SetUINT32(MF_MT_AUDIO_CHANNEL_MASK, 3);
writer->SetInputMediaType(0, inputType, NULL);
DWORD streamNum = 0;
hr = writer->AddStream(inputType, &streamNum);
hr = writer->BeginWriting();
ProcessSamples(pReader,writer);
writer->Finalize();
return 0;
}
它适用于从麦克风捕获声音,但在调用pReader->ReadSample
后有不必要的功能 - 我的耳机中的音量降低了。我认为它是最佳捕获质量的媒体基础的特征,但我不需要它。有没有办法禁用这种行为?提前谢谢!
答案 0 :(得分:1)
首先,欢迎来到StackOverflow!
您描述的行为称为Automatic ducking or Stream Attenuation(Win7的新功能)。它适用于通信应用程序。由于您的耳机是通信设备,因此会受到此行为的影响。简单来说,在传入的“呼叫”期间,其他设备的数量会减少。
关闭此功能的最简单方法是导航到“声音”控制面板上的最后一个标签(如下所示),您可以在其中更改音量选项。
否则,您可以提供here显示的自定义闪避行为。
您还可以使用与here类似的代码禁用自动闪避,但请记住您将混合使用WASAPI和Media Foundation,并且需要相应地管理会话。
希望这有帮助。