读取WAV文件的数据部分的C++

Question

我计划创建一个程序，将可视化的音频波形的.wav文件。

到目前为止，我已经从正确读取上述wav文件的头部分开始。我使用的代码是这样的：

#include <iostream>
#include <string>
#include <fstream>

using namespace std;
using std::string;
using std::fstream;

typedef struct  WAV_HEADER{
    char                RIFF[4];        // RIFF Header      Magic header
    unsigned long       ChunkSize;      // RIFF Chunk Size  
    char                WAVE[4];        // WAVE Header      
    char                fmt[4];         // FMT header       
    unsigned long       Subchunk1Size;  // Size of the fmt chunk                                
    unsigned short      AudioFormat;    // Audio format 1=PCM,6=mulaw,7=alaw, 257=IBM Mu-Law, 258=IBM A-Law, 259=ADPCM 
    unsigned short      NumOfChan;      // Number of channels 1=Mono 2=Sterio                   
    unsigned long       SamplesPerSec;  // Sampling Frequency in Hz                             
    unsigned long       bytesPerSec;    // bytes per second 
    unsigned short      blockAlign;     // 2=16-bit mono, 4=16-bit stereo 
    unsigned short      bitsPerSample;  // Number of bits per sample      
    char                Subchunk2ID[4]; // "data"  string   
    unsigned long       Subchunk2Size;  // Sampled data length    

}wav_hdr; 

// Function prototypes 
int getFileSize(FILE *inFile); 

int main(int argc,char *argv[]){
    wav_hdr wavHeader;
    FILE *wavFile;
    int headerSize = sizeof(wav_hdr),filelength = 0;

    string answer;

    do{
        string input;
        string answer;

        const char* filePath;

        cout << "Pick wav file from the Windows Media File: ";
        cin >> input;
        cin.get();

        cout << endl;

        path = "C:\\Windows\\Media\\" + input + ".wav";
        filePath = path.c_str();

        wavFile = fopen( filePath , "r" );

        if(wavFile == NULL){
            printf("Can not able to open wave file\n");
            //exit(EXIT_FAILURE);
        }

        fread(&wavHeader,headerSize,1,wavFile);
        filelength = getFileSize(wavFile);
        fclose(wavFile);

        cout << "File is                    :" << filelength << " bytes." << endl;

        cout << "RIFF header                :" << wavHeader.RIFF[0] 
                                                << wavHeader.RIFF[1] 
                                                << wavHeader.RIFF[2] 
                                                << wavHeader.RIFF[3] << endl;

        cout << "WAVE header                :" << wavHeader.WAVE[0] 
                                                << wavHeader.WAVE[1] 
                                                << wavHeader.WAVE[2] 
                                                << wavHeader.WAVE[3] 
                                                << endl;

        cout << "FMT                        :" << wavHeader.fmt[0] 
                                                << wavHeader.fmt[1] 
                                                << wavHeader.fmt[2] 
                                                << wavHeader.fmt[3] 
                                                << endl;

        cout << "Data size                  :" << wavHeader.ChunkSize << endl;

        // Display the sampling Rate form the header
        cout << "Sampling Rate              :" << wavHeader.SamplesPerSec << endl;
        cout << "Number of bits used        :" << wavHeader.bitsPerSample << endl;
        cout << "Number of channels         :" << wavHeader.NumOfChan << endl;
        cout << "Number of bytes per second :" << wavHeader.bytesPerSec << endl;
        cout << "Data length                :" << wavHeader.Subchunk2Size << endl;
        cout << "Audio Format               :" << wavHeader.AudioFormat << endl;
        // Audio format 1=PCM,6=mulaw,7=alaw, 257=IBM Mu-Law, 258=IBM A-Law, 259=ADPCM 


        cout << "Block align                :" << wavHeader.blockAlign << endl;

        cout << "Data string                :" << wavHeader.Subchunk2ID[0] 
                                                << wavHeader.Subchunk2ID[1]
                                                << wavHeader.Subchunk2ID[2] 
                                                << wavHeader.Subchunk2ID[3] 
                                                << endl;

        cout << endl << endl << "Try something else? (y/n)";
        cin >> answer;
        //cin.get();
        cout << endl << endl;

    }while( answer == "y" );


    getchar();
    return 0;
} 
// find the file size 
int getFileSize(FILE *inFile){
    int fileSize = 0;
    fseek(inFile,0,SEEK_END);

    fileSize=ftell(inFile);

    fseek(inFile,0,SEEK_SET);
    return fileSize;
}

我已经试过几次了，它给出的数据似乎与Windows文件夹中Media文件夹中不同的wav文件一致。

然后，下一步将以矢量形式存储wav文件的实际数据。然而，我对如何做到这一点一无所知。我发现的在线解决方案只会读取头文件。

关于如何存储(并希望显示) wav文件的实际数据，您有什么想法吗？谢谢!

Answer 1

这张图片来自a Stanford course

​

​

所以您可以看到，音频数据紧跟在您已经读过的头之后，将会有Subchunk2Size字节的音频数据。

此操作的伪代码为

ReadRIFF();
ReadFMT();
int32 chunk2Id = Read32(BigEndian);
int32 chunk2Size = Read32(LittleEndian);
for (int i = 0; i < chunk2Size; i++)
{
    audioData[i] = ReadByte();
}

如果音频是立体声的，那么在data中会有两个音频流。如果音频是压缩的(mp3，aac等)，你必须先解压缩。

Answer 2

我知道这是一个旧的帖子，但是你的fread参数被切换了，这是一个更正确的版本(需要g++-4.7或更高的版本，带有-std=c++11标志，比如"g++ -std=c++11 WaveReader.cpp -o WaveReader")。

#include <iostream>
#include <string>
#include <fstream>
#include <cstdint>

using std::cin;
using std::cout;
using std::endl;
using std::fstream;
using std::string;

typedef struct  WAV_HEADER
{
    /* RIFF Chunk Descriptor */
    uint8_t         RIFF[4];        // RIFF Header Magic header
    uint32_t        ChunkSize;      // RIFF Chunk Size
    uint8_t         WAVE[4];        // WAVE Header
    /* "fmt" sub-chunk */
    uint8_t         fmt[4];         // FMT header
    uint32_t        Subchunk1Size;  // Size of the fmt chunk
    uint16_t        AudioFormat;    // Audio format 1=PCM,6=mulaw,7=alaw,     257=IBM Mu-Law, 258=IBM A-Law, 259=ADPCM
    uint16_t        NumOfChan;      // Number of channels 1=Mono 2=Sterio
    uint32_t        SamplesPerSec;  // Sampling Frequency in Hz
    uint32_t        bytesPerSec;    // bytes per second
    uint16_t        blockAlign;     // 2=16-bit mono, 4=16-bit stereo
    uint16_t        bitsPerSample;  // Number of bits per sample
    /* "data" sub-chunk */
    uint8_t         Subchunk2ID[4]; // "data"  string
    uint32_t        Subchunk2Size;  // Sampled data length
} wav_hdr;

// Function prototypes
int getFileSize(FILE* inFile);

int main(int argc, char* argv[])
{
    wav_hdr wavHeader;
    int headerSize = sizeof(wav_hdr), filelength = 0;

    const char* filePath;
    string input;
    if (argc <= 1)
    {
        cout << "Input wave file name: ";
        cin >> input;
        cin.get();
        filePath = input.c_str();
    }
    else
    {
        filePath = argv[1];
        cout << "Input wave file name: " << filePath << endl;
    }

    FILE* wavFile = fopen(filePath, "r");
    if (wavFile == nullptr)
    {
        fprintf(stderr, "Unable to open wave file: %s\n", filePath);
        return 1;
    }

    //Read the header
    size_t bytesRead = fread(&wavHeader, 1, headerSize, wavFile);
    cout << "Header Read " << bytesRead << " bytes." << endl;
    if (bytesRead > 0)
    {
        //Read the data
        uint16_t bytesPerSample = wavHeader.bitsPerSample / 8;      //Number     of bytes per sample
        uint64_t numSamples = wavHeader.ChunkSize / bytesPerSample; //How many samples are in the wav file?
        static const uint16_t BUFFER_SIZE = 4096;
        int8_t* buffer = new int8_t[BUFFER_SIZE];
        while ((bytesRead = fread(buffer, sizeof buffer[0], BUFFER_SIZE / (sizeof buffer[0]), wavFile)) > 0)
        {
            /** DO SOMETHING WITH THE WAVE DATA HERE **/
            cout << "Read " << bytesRead << " bytes." << endl;
        }
        delete [] buffer;
        buffer = nullptr;
        filelength = getFileSize(wavFile);

        cout << "File is                    :" << filelength << " bytes." << endl;
        cout << "RIFF header                :" << wavHeader.RIFF[0] << wavHeader.RIFF[1] << wavHeader.RIFF[2] << wavHeader.RIFF[3] << endl;
        cout << "WAVE header                :" << wavHeader.WAVE[0] << wavHeader.WAVE[1] << wavHeader.WAVE[2] << wavHeader.WAVE[3] << endl;
        cout << "FMT                        :" << wavHeader.fmt[0] << wavHeader.fmt[1] << wavHeader.fmt[2] << wavHeader.fmt[3] << endl;
        cout << "Data size                  :" << wavHeader.ChunkSize << endl;

        // Display the sampling Rate from the header
        cout << "Sampling Rate              :" << wavHeader.SamplesPerSec << endl;
        cout << "Number of bits used        :" << wavHeader.bitsPerSample << endl;
        cout << "Number of channels         :" << wavHeader.NumOfChan << endl;
        cout << "Number of bytes per second :" << wavHeader.bytesPerSec << endl;
        cout << "Data length                :" << wavHeader.Subchunk2Size << endl;
        cout << "Audio Format               :" << wavHeader.AudioFormat << endl;
        // Audio format 1=PCM,6=mulaw,7=alaw, 257=IBM Mu-Law, 258=IBM A-Law, 259=ADPCM

        cout << "Block align                :" << wavHeader.blockAlign << endl;
        cout << "Data string                :" << wavHeader.Subchunk2ID[0] << wavHeader.Subchunk2ID[1] << wavHeader.Subchunk2ID[2] << wavHeader.Subchunk2ID[3] << endl;
    }
    fclose(wavFile);
    return 0;
}

// find the file size
int getFileSize(FILE* inFile)
{
    int fileSize = 0;
    fseek(inFile, 0, SEEK_END);

    fileSize = ftell(inFile);

    fseek(inFile, 0, SEEK_SET);
    return fileSize;
}