• win32


    需要先从麦克风中采样,代码样本可以参考官方示例: WASAPI Capture Shared Event Driven 

    官方示例采样10s, 我们需要在WriteWaveFile函数下添加生成原始音频的代码。

    //  Write the contents of a WAV file.  We take as input the data to write and the format of that data.
    //
    bool WriteWaveFile(HANDLE FileHandle, const BYTE *Buffer, const size_t BufferSize, const WAVEFORMATEX *WaveFormat)
    {
        FILE* _file;
        int16_t* _data;
        _data = (int16_t*)Buffer;
        _file = fopen("utterance.raw", "wb +");
        fwrite(_data, 1, BufferSize, _file);
        fclose(_file);
    
        ...

    得到utterance.raw原始音频样本之后,我们需要对其添加wav的头结构来重新生成wav文件

    #include <Windows.h>
    #include <stdio.h>
    #include <MMDeviceAPI.h>
    #include <AudioClient.h>
    #include <assert.h>
    #include <avrt.h>
    #include <strsafe.h>
    #include <fstream> 
    
    using namespace std;
    
    #pragma warning(disable:4996)
    
    struct WAVEHEADER
    {
        DWORD   dwRiff;                     // "RIFF"
        DWORD   dwSize;                     // Size
        DWORD   dwWave;                     // "WAVE"
        DWORD   dwFmt;                      // "fmt "
        DWORD   dwFmtSize;                  // Wave Format Size
    };
    
    const BYTE WaveHeader[] =
    {
        'R',   'I',   'F',   'F',  0x00,  0x00,  0x00,  0x00, 'W',   'A',   'V',   'E',   'f',   'm',   't',   ' ', 0x00, 0x00, 0x00, 0x00
    };
    
    const BYTE WaveData[] = { 'd', 'a', 't', 'a' };
    
    bool WriteWaveFile(HANDLE FileHandle, const BYTE* Buffer, const size_t BufferSize, WAVEFORMATEX* WaveFormat)
    {
        DWORD waveFileSize = sizeof(WAVEHEADER) + sizeof(WAVEFORMATEX) + WaveFormat->cbSize + sizeof(WaveData) + sizeof(DWORD) + static_cast<DWORD>(BufferSize);
        BYTE* waveFileData = new (std::nothrow) BYTE[waveFileSize];
        BYTE* waveFilePointer = waveFileData;
        WAVEHEADER* waveHeader = reinterpret_cast<WAVEHEADER*>(waveFileData);
    
        if (waveFileData == NULL)
        {
            printf("Unable to allocate %d bytes to hold output wave data
    ", waveFileSize);
            return false;
        }
    
        //
        //  Copy in the wave header - we'll fix up the lengths later.
        //
        CopyMemory(waveFilePointer, WaveHeader, sizeof(WaveHeader));
        waveFilePointer += sizeof(WaveHeader);
    
        //
        //  Update the sizes in the header.
        //
        waveHeader->dwSize = waveFileSize - (2 * sizeof(DWORD));
        waveHeader->dwFmtSize = sizeof(WAVEFORMATEX) + WaveFormat->cbSize;
    
        //
        //  Next copy in the WaveFormatex structure.
        //
        CopyMemory(waveFilePointer, WaveFormat, sizeof(WAVEFORMATEX) + WaveFormat->cbSize);
        waveFilePointer += sizeof(WAVEFORMATEX) + WaveFormat->cbSize;
    
    
        //
        //  Then the data header.
        //
        CopyMemory(waveFilePointer, WaveData, sizeof(WaveData));
        waveFilePointer += sizeof(WaveData);
        *(reinterpret_cast<DWORD*>(waveFilePointer)) = static_cast<DWORD>(BufferSize);
        waveFilePointer += sizeof(DWORD);
    
        //
        //  And finally copy in the audio data.
        // 
    
        CopyMemory(waveFilePointer, Buffer, BufferSize);
        //
        //  Last but not least, write the data to the file.
        //
        DWORD bytesWritten;
        if (!WriteFile(FileHandle, waveFileData, waveFileSize, &bytesWritten, NULL))
        {
            printf("Unable to write wave file: %d
    ", GetLastError());
            delete[]waveFileData;
            return false;
        }
    
        if (bytesWritten != waveFileSize)
        {
            printf("Failed to write entire wave file
    ");
            delete[]waveFileData;
            return false;
        }
        delete[]waveFileData;
        return true;
    }
    
    //
    //  Write the captured wave data to an output file so that it can be examined later.
    //
    void SaveWaveData(BYTE* CaptureBuffer, size_t BufferSize, WAVEFORMATEX* WaveFormat)
    {
        wchar_t waveFileName[MAX_PATH];
        HRESULT hr = StringCbCopy(waveFileName, sizeof(waveFileName), L"WASAPICaptureEventDriven-");
        if (SUCCEEDED(hr))
        {
            GUID testGuid;
            if (SUCCEEDED(CoCreateGuid(&testGuid)))
            {
                wchar_t* guidString;
                if (SUCCEEDED(StringFromCLSID(testGuid, &guidString)))
                {
                    hr = StringCbCat(waveFileName, sizeof(waveFileName), guidString);
                    if (SUCCEEDED(hr))
                    {
                        hr = StringCbCat(waveFileName, sizeof(waveFileName), L".WAV");
                        if (SUCCEEDED(hr))
                        {
                            HANDLE waveHandle = CreateFile(waveFileName, GENERIC_WRITE, FILE_SHARE_READ, NULL, CREATE_ALWAYS,
                                FILE_ATTRIBUTE_NORMAL | FILE_FLAG_SEQUENTIAL_SCAN,
                                NULL);
                            if (waveHandle != INVALID_HANDLE_VALUE)
                            {
                                if (WriteWaveFile(waveHandle, CaptureBuffer, BufferSize, WaveFormat))
                                {
                                    printf("Successfully wrote WAVE data to %S
    ", waveFileName);
                                }
                                else
                                {
                                    printf("Unable to write wave file
    ");
                                }
                                CloseHandle(waveHandle);
                            }
                            else
                            {
                                printf("Unable to open output WAV file %S: %d
    ", waveFileName, GetLastError());
                            }
                        }
                    }
                    CoTaskMemFree(guidString);
                }
            }
        }
    }
    
    int main()
    {
        long buffersize = 3528000;// For 10s audio sample, we can set the value of buffersize to 3528000
        BYTE* captureBuffer = new (std::nothrow) BYTE[buffersize]; 
        
        FILE* _file;
        _file = fopen("utterance.raw", "rb"); //raw audio path
        fread(captureBuffer, 1, buffersize, _file);
        fclose(_file);
    
        WAVEFORMATEX wavformat;
        wavformat.wFormatTag = WAVE_FORMAT_IEEE_FLOAT;
        wavformat.nChannels = 2;
        wavformat.nSamplesPerSec = 44100;
        wavformat.nAvgBytesPerSec = 352800;
        wavformat.nBlockAlign = 8;
        wavformat.wBitsPerSample = 32;
        wavformat.cbSize = 22;
        SaveWaveData(captureBuffer, buffersize, &wavformat);
    
        return 0;
    }

    通过将样本的路径添加给fopen,经过一些处理就可以得到了。

    补充:

    我们也可以使用ofstream来采样,代码见下:

    //  Write the contents of a WAV file.  We take as input the data to write and the format of that data.
    //
    bool WriteWaveFile(HANDLE FileHandle, const BYTE *Buffer, const size_t BufferSize, const WAVEFORMATEX *WaveFormat)
    {
        ofstream binaryFile("file.raw", ios::out | ios::binary);
        binaryFile.write((char*)Buffer, BufferSize);
        binaryFile.close();
        ...

    再使用ifstream获取样本,添加wav的头结构来重新编码。

        ifstream infile("file.raw", std::ifstream::binary);
         // get size of file
        infile.seekg(0, infile.end);
        long size = infile.tellg();
        infile.seekg(0);
    
        BYTE* captureBuffer = new (std::nothrow) BYTE[size];
        
        infile.read((char*)captureBuffer, size);
        infile.close();
    
        WAVEFORMATEX wavformat;
        wavformat.wFormatTag = WAVE_FORMAT_IEEE_FLOAT;
        wavformat.nChannels = 2;
        wavformat.nSamplesPerSec = 44100;
        wavformat.nAvgBytesPerSec = 352800;
        wavformat.nBlockAlign = 8;
        wavformat.wBitsPerSample = 32;
        wavformat.cbSize = 22;
        SaveWaveData(captureBuffer, size, &wavformat);
  • 相关阅读:
    Selenium3+python3自动化(二十九)--绕过验证码(add_cookie)
    Selenium3+python3自动化(二十八)--cookie相关操作
    Selenium3+python3自动化(二十七)--webdriver中等待,显式等待(WebDriverWait),强制等待sleep(),隐式等待implicitly_wait()
    Selenium3+python3自动化(二十七)--爬页面源码(page_source)
    Selenium3+python3自动化(二十六)--判断元素存在
    Selenium3+python3自动化(二十五)--获取元素属性,driver.title,driver.text,driver.tag_name,get_attribut("属性名"),输入框文本值get_attribute("value"),driver.name
    Selenium3+python3自动化(二十四)--获取百度输入联想词
    Selenium3+python3自动化(二十三)--文件上传(send_keys)
    Selenium3+python3自动化(二十二)--窗口多标签处理方法总结
    POJ
  • 原文地址:https://www.cnblogs.com/strive-sun/p/13921658.html
Copyright © 2020-2023  润新知