[英]C++ Reading the Data part of a WAV file
I plan to create a program that will visualize the audio waveform of a .wav file.我计划创建一个程序来可视化 .wav 文件的音频波形。
So far, I have started by properly reading the header part of the said wav file.到目前为止,我已经开始正确阅读上述 wav 文件的标题部分。 The code I use would be this: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;
}
I've tried it several times and the data it gives seems consistent through different wav files in the Media folder in the Windows folder.我已经尝试了几次,通过 Windows 文件夹中 Media 文件夹中的不同 wav 文件,它提供的数据似乎是一致的。
The next step then would be storing the actual data of the wav file in a vector.下一步是将 wav 文件的实际数据存储在向量中。 However, I'm quite clueless on how to do this.但是,我对如何做到这一点一无所知。 Online solutions that I found only went as far as reading the header file.我发现的在线解决方案只能读取头文件。
Any ideas on how to store (and hopefully display) the actual data of the wav file?关于如何存储(并希望显示)wav 文件的实际数据的任何想法? Thanks!谢谢!
This image is taken from a Stanford course这张图片取自斯坦福大学的课程
So you can see that the audio data occurs immediately after the headers you already read and there will be Subchunk2Size
bytes of audio data.所以你可以看到音频数据在你已经读过的头之后立即出现,并且会有Subchunk2Size
字节的音频数据。
The pseudocode for this would be这个的伪代码是
ReadRIFF();
ReadFMT();
int32 chunk2Id = Read32(BigEndian);
int32 chunk2Size = Read32(LittleEndian);
for (int i = 0; i < chunk2Size; i++)
{
audioData[i] = ReadByte();
}
If the audio is stereo you'll have two audio streams in data
.如果音频是立体声,您将在data
有两个音频流。 If the audio is compressed (mp3, aac, etc) you'll have to decompress it first.如果音频已压缩(mp3、aac 等),则必须先对其进行解压缩。
I know this is an old post, but your fread parameters are switched, here is a more correct version (requires g++-4.7 or higher with -std=c++11 flag like this "g++ -std=c++11 WaveReader.cpp -o WaveReader").我知道这是一篇旧帖子,但是您的 fread 参数已切换,这是一个更正确的版本(需要 g++-4.7 或更高版本,带有 -std=c++11 标志,例如“g++ -std=c++11 WaveReader.txt”)。 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;
}
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.