Question

我使用一个结构来读取音频格式为3（= IEEE FLOAT 32位）的Wav-Files，其中包含一个58字节的wav-header。问题是：字节38以＆＃34;事实＆＃34;开头。块。这似乎没问题。 DwFactSize的偏移量应为42.这里的问题就开始了！抵消是44 !!!首先我想，问题在于填充位。所以我尝试了uints，unsigned chars和 attribute （（packed））。这并没有改变任何事情。

这是wav标题的定义：

0 - 3＆＃39; RIFF＆＃39; /＆＃39; RIFX＆＃39;小/大端

4 - 7 wRiffLength文件长度减去8字节riff头

8 - 11＆＃39; WAVE＆＃39;

12 - 15＆＃39; fmt＆＃39;

16 - 19 wFmtSize格式块长度减去8字节标题

20 - 21 wFormatTag识别PCM，ULAW等

22 - 23 wChannels

每通道每秒24 - 27 dwSamplesPerSecond样本

28 - 31 dwAvgBytesPerSec对于压缩格式非常重要

32 - 33 wBlockAlign基本块大小

34 - 35 wBitsPerSample非常重要的压缩格式

（直到字节35与通常的44字节标题一样）

36 - 37 wExtSize = 0格式扩展名的长度

38 - 41＆＃39;事实＆＃39;

42 - 45 dwFactSize =事实块的长度减去8字节   头

46 - 49 dwSamplesWritten写出的实际样本数

50 - 53＆＃39;数据＆＃39;

54 - 57 dwDataLength数据块长度减去8字节头

输出：

...

直到这里......正确...

事实[4] 38

!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!

DwFactSize 44

dwSamplesWritten 48

数据[4] 52

dwDataLength 56

快速破解以显示偏移问题：

#include <stdio.h>
#include <stdint.h>
#include <stdlib.h>
#include <cstring>
#include <iostream>
#include <cstddef>

typedef struct  WAV_HEADER
{
unsigned char       RIFF[4];        /* RIFF Header      */ //Magic header
unsigned long       ChunkSize;      /* RIFF Chunk Size  */
unsigned char       WAVE[4];        /* WAVE Header      */
unsigned char       fmt[4];         /* FMT header       */
unsigned long       Subchunk1Size;  /* Size of the fmt chunk: 16=PCM, 18=IEEE Float, 40=Extensible                     */
unsigned short      AudioFormat;    /* Audio format 1=PCM, 3=IEEE Float, 6=mulaw,7=alaw, 257=IBM Mu-Law, 258=IBM A-Law, 259=ADPCM, 65534=Extensible */
unsigned short      NumOfChan;      /* Number of channels 1=Mono 2=Stereo                   */
unsigned long       SamplesPerSec;  /* Sampling Frequency in Hz                             */
unsigned long       bytesPerSec;    /* bytes per second */
unsigned short      blockAlign;     /* 2=16-bit mono, 4=16-bit stereo , 6=24-bit stereo,8=32-bit stereo*/
unsigned short      bitsPerSample;  /* Number of bits per sample, inkl. hier=36 bytes  */
unsigned short      wExtSize;       /*  2 byte, wExtSize = 0  the length of the format extension   */
unsigned char       Fact[4];        /* "fact"  string   */
/*Problem here! -> +2bytes*/
unsigned long       DwFactSize;     /* Sampled data length,  inkl. hier bei 44 bytes */
unsigned long       dwSamplesWritten;
unsigned char       Data[4];        /* leerer string falls extensible -> Beginn nicht nach 44 sondern 68!  */
unsigned long       dwDataLength;   /* raw DataLength */
}__attribute__((packed)) wav_hdr;


int getFileSize(FILE *inFile);

int main(int argc,char *argv[])
{
char *file;
file = argv[1];
wav_hdr wavHeader;
FILE *wavFile;
int headerSize = sizeof(wav_hdr),filelength = 0;
wavFile = fopen(file,"r");
if(wavFile == NULL)
{
    printf("\nCan not open wave file. Usage: program [file] \n");
    exit(EXIT_FAILURE);
}

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


std::cout << "\nRIFF " << offsetof(WAV_HEADER, RIFF) <<  std::endl;
std::cout << "\nChunkSize " << offsetof(WAV_HEADER, ChunkSize) <<  std::endl;
std::cout << "\nWAVE[4] " << offsetof(WAV_HEADER, WAVE) <<  std::endl;
std::cout << "\nfmt[4] " << offsetof(WAV_HEADER, fmt) <<  std::endl;
std::cout << "\nSubchunk1Size " << offsetof(WAV_HEADER, Subchunk1Size) <<  std::endl;
std::cout << "\nAudioFormat " << offsetof(WAV_HEADER, AudioFormat) <<  std::endl;
std::cout << "\nNumOfChan " << offsetof(WAV_HEADER, NumOfChan) <<  std::endl;
std::cout << "\nSamplesPerSec " << offsetof(WAV_HEADER, SamplesPerSec) <<  std::endl;
std::cout << "\nbytesPerSec " << offsetof(WAV_HEADER, bytesPerSec) <<  std::endl;
std::cout << "\nblockAlign " << offsetof(WAV_HEADER, blockAlign) <<  std::endl;
std::cout << "\nbitsPerSample " << offsetof(WAV_HEADER, bitsPerSample) <<  std::endl;
std::cout << "\nwExtSize (2) " << offsetof(WAV_HEADER, wExtSize) <<  std::endl;
std::cout << "\nFact[4] " << offsetof(WAV_HEADER, Fact) <<  std::endl;

std::cout << "\nDwFactSize " << offsetof(WAV_HEADER, DwFactSize) <<  std::endl;
std::cout << "\ndwSamplesWritten " << offsetof(WAV_HEADER, dwSamplesWritten) <<  std::endl;
std::cout << "\nData[4] " << offsetof(WAV_HEADER, Data) <<  std::endl;
std::cout << "\ndwDataLength " << offsetof(WAV_HEADER, dwDataLength) <<  std::endl;


return 0;
}

int getFileSize(FILE *inFile)
{
int fileSize = 0;
fseek(inFile,0,SEEK_END);
fileSize=ftell(inFile);
fseek(inFile,0,SEEK_SET);
return fileSize;
}

要生成这样的32位浮点数，88200 Wav文件： sox input16_44100.wav -b 32 -e float output32F_88200.wav rate -s -a -v -L 88200

Answer 1

显然，Fact[]和DwFactSize之间有2个字节的填充。

我怀疑是因为你在那里使用了typedef。只需将其写为常规C ++定义：struct __attribute__((packed)) WAV_HEADER { ...

Struct C / C ++ - 读取WAV标头32位浮点数 - 字节偏移错误

输出：

1 个答案: