C++阅读WAV文件的数据部分

x33g5p2x  于 2023-03-14  发布在  其他
关注(0)|答案(3)|浏览(209)

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,我已经从正确阅读上述wav文件的头部分开始。我使用的代码如下:

#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;
}

我试过几次,它给出的数据似乎通过Windows文件夹中的Media文件夹中的不同WAV文件一致。
下一步就是把wav文件的实际数据存储到一个矢量中,但是我对如何存储还不太清楚,我找到的在线解决方案只是阅读头文件。
关于如何存储(并希望显示)wav文件的实际数据有什么想法吗?谢谢!

yshpjwxd

yshpjwxd1#

此图像取自a Stanford course

因此,您可以看到音频数据紧跟在您已经读取的标头之后,并且将有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,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。

q3aa0525

q3aa05252#

我知道这是一个老职位,但你的fread参数切换,这里是一个更正确的版本(需要g++-4.7或更高的-std=c11标志,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;
}
w8f9ii69

w8f9ii693#

如果您想要读取WAV文件,同时涵盖fmtdata块与其他块“混合”的情况:

#include <iostream>
#include <fstream>
#include <cstring>

using namespace std;

struct RIFFHeader{
    char chunk_id[4];
    uint32_t chunk_size;
    char format[4];
};

struct ChunkInfo{
    char chunk_id[4];
    uint32_t chunk_size;
};

struct FmtChunk{
    uint16_t audio_format;
    uint16_t num_channels;
    uint32_t sample_rate;
    uint32_t byte_rate;
    uint16_t block_align;
    uint16_t bits_per_sample;
};

struct DataChunk
// We assume 16-bit monochannel samples
{  
    int16_t* data;
    int nb_of_samples;
    DataChunk(int s): nb_of_samples{s}, data{new int16_t[s]} {}
    ~DataChunk(){delete[] data;}
};

int main(){
    constexpr char riff_id[4] = {'R','I','F','F'};
    constexpr char format[4] = {'W','A','V','E'};
    constexpr char fmt_id[4] = {'f','m','t',' '};
    constexpr char data_id[4] = {'d','a','t','a'};

    ifstream ifs{"../audio.wav", ios_base::binary};
    if (!ifs){
        cerr << "Cannot open file" << endl;
        return -1;
    }

    // first read RIFF header
    RIFFHeader h;
    ifs.read((char*)(&h), sizeof(h));
    if (!ifs || memcmp(h.chunk_id, riff_id, 4) || memcmp(h.format, format, 4)){
        cerr << "Bad formatting" << endl;
        return -1;
    }

    // read chunk infos iteratively
    ChunkInfo ch;
    bool fmt_read = false;
    bool data_read = false;
    while(ifs.read((char*)(&ch), sizeof(ch))){

        // if fmt chunk?
        if (memcmp(ch.chunk_id, fmt_id, 4) == 0){
            FmtChunk fmt;
            ifs.read((char*)(&fmt), ch.chunk_size);
            fmt_read = true;
        }
        // is data chunk?
        else if(memcmp(ch.chunk_id, data_id, 4) == 0){
            DataChunk dat_chunk(ch.chunk_size/sizeof(int16_t));
            ifs.read((char*)dat_chunk.data, ch.chunk_size);
            data_read = true;
        }
        // otherwise skip the chunk
        else{
            ifs.seekg(ch.chunk_size, ios_base::cur);
        }
    }
    if (!data_read || !fmt_read){
        cout << "Problem when reading data" << endl;
        return -1;
    }
}

**NB:**我假设这里是单通道16位样本。虽然它可以适应处理更多的格式...

相关问题