如何解决24位FLAC和WAV文件的readData
| 我成功使用readData读取了16位音频文件并生成了用于波形显示的峰值文件。但是,我在解释24位FLAC和WAV文件的PCM值时遇到一些麻烦。 首先,24位的块大小是多少? 16位带符号值的范围是-32768至+32768,而24位范围是-8388607至+8388607。 我将4096字节的块大小用于16位文件(65536/16 = 4096)。它可以很好地检测峰。 如果我对24位进行相同的计算,则16777215/24 = 699050.625字节。我错了吗?我想我必须使用32位变量来存储24位值。但是读取文件时我应该使用什么块大小? 699051?如何调整转换为浮点数组? 这是我用来为16位PCM数据生成峰值文件的完整C#代码。我故意将24位代码留空,因为它不起作用。一些代码引用了我自己的FMOD包装器,但它应该很容易理解。 // Declare variables
FMOD.RESULT result = FMOD.RESULT.OK;
FileStream fileStream = null;
BinaryWriter binaryWriter = null;
GZipStream gzipStream = null;
bool generatePeakFile = false;
int CHUNKSIZE = 0;
uint length = 0;
uint read = 0;
uint bytesread = 0;
Int16[] left16BitArray = null;
Int16[] right16BitArray = null;
Int32[] left32BitArray = null;
Int32[] right32BitArray = null;
float[] floatLeft = null;
float[] floatRight = null;
byte[] buffer = null;
IntPtr data = new IntPtr(); // initialized properly later
WaveDataMinMax minMax = null;
try
{
// Set current file directory
m_peakFileDirectory = Path.GetDirectoryName(Assembly.GetExecutingAssembly().Location) + \"\\\\Peak Files\\\\\";
// Get file name from argument
string fileName = (string)e.Argument;
// Create sound system with NOSOUND
MPfm.sound.System soundSystem = new MPfm.sound.System(FMOD.OUTPUTTYPE.NOSOUND,string.Empty);
// Create sound
MPfm.sound.sound sound = soundSystem.CreateSound(fileName,false);
// Get sound format; specifically bits per sample (changes the calculations later)
SoundFormat soundFormat = sound.GetSoundFormat();
// Get the length of the file in PCM bytes
sound.BaseSound.getLength(ref length,FMOD.TIMEUNIT.PCMBYTES);
// Check if the folder for peak files exists
if (!Directory.Exists(PeakFileDirectory))
{
// Create directory
Directory.CreateDirectory(PeakFileDirectory);
}
// Generate the file name for the peak file by using the full path without special characters
string peakFilePath = PeakFileDirectory + fileName.Replace(@\"\\\",\"_\").Replace(\":\",\"_\").Replace(\".\",\"_\") + \".mpfmPeak\";
// Check if peak file exists
if(!File.Exists(peakFilePath))
{
// Set flag
generatePeakFile = true;
// Create peak file
fileStream = new FileStream(peakFilePath,FileMode.Create,FileAccess.Write);
binaryWriter = new BinaryWriter(fileStream);
gzipStream = new GZipStream(fileStream,CompressionMode.Compress);
}
// Check the bits per sample to determine what chunk size to get
if (soundFormat.BitsPerSample == 16)
{
// 4096 bytes for 16-bit PCM data
CHUNKSIZE = 4096;
}
else if (soundFormat.BitsPerSample == 24)
{
// 699050.625 bytes for 24-bit PCM data (???)
CHUNKSIZE = 699051;
}
// Create buffer
data = Marshal.AllocHGlobal(CHUNKSIZE);
buffer = new byte[CHUNKSIZE];
// Loop through file using chunk size
do
{
// Check for cancel
if (m_workerWaveForm.CancellationPending)
{
return;
}
// Check the bits per sample
if (soundFormat.BitsPerSample == 16)
{
// Read data chunk (4096 bytes for 16-bit PCM data)
result = sound.BaseSound.readData(data,(uint)CHUNKSIZE,ref read);
Marshal.copy(data,buffer,CHUNKSIZE);
bytesread += read;
// Is freehglobal needed? it crashes after one use.
//Marshal.FreeHGlobal(data);
// Convert the byte (8-bit) arrays into a short (16-bit) arrays (signed values)
left16BitArray = new Int16[buffer.Length / 4];
right16BitArray = new Int16[buffer.Length / 4];
// Loop through byte (8-bit) array buffer; increment by 4 (i.e. 4 times more data in 16-bit than 8-bit)
for (int i = 0; i < buffer.Length; i = i + 4)
{
// Convert values to 16-bit
left16BitArray[i / 4] = BitConverter.ToInt16(buffer,i);
right16BitArray[i / 4] = BitConverter.ToInt16(buffer,i + 2); // alternate between left and right channel
}
// Convert the short arrays to float arrays (signed values)
// This will convert the -32768 to 32768 value range to -1 to 1 (useful for wave display)
floatLeft = new float[left16BitArray.Length];
floatRight = new float[left16BitArray.Length];
for (int i = 0; i < left16BitArray.Length; i++)
{
// 16-bit data for unsigned values range from 0 to 65536.
floatLeft[i] = left16BitArray[i] / 65536.0f;
floatRight[i] = right16BitArray[i] / 65536.0f;
}
}
else if (soundFormat.BitsPerSample == 24)
{
// (non-working code removed)
// (I have no idea if this works) Convert the short arrays to float arrays (signed values)
// This will convert the -8388608 to 8388608value range to -1 to 1 (useful for wave display)
floatLeft = new float[left32BitArray.Length];
floatRight = new float[left32BitArray.Length];
for (int i = 0; i < left32BitArray.Length; i++)
{
// 16-bit data for unsigned values range from 0 to 16777215.
floatLeft[i] = left32BitArray[i] / 16777215.0f;
floatRight[i] = right32BitArray[i] / 16777215.0f;
}
}
// Calculate min/max
minMax = AudioTools.GetMinMaxFromWaveData(floatLeft,floatRight,false);
WaveDataHistory.Add(minMax);
// Report progress
m_bytesRead = bytesread;
m_totalBytes = length;
m_percentageDone = ((float)bytesread / (float)length) * 100;
// Write peak information to hard disk
if (generatePeakFile)
{
// Write peak information
binaryWriter.Write((double)minMax.leftMin);
binaryWriter.Write((double)minMax.leftMax);
binaryWriter.Write((double)minMax.rightMin);
binaryWriter.Write((double)minMax.rightMax);
binaryWriter.Write((double)minMax.mixMin);
binaryWriter.Write((double)minMax.mixMax);
}
}
while (result == FMOD.RESULT.OK && read == CHUNKSIZE);
// Release sound from memory
sound.Release();
// Close sound system and release from memory
soundSystem.Close();
soundSystem.Release();
// Set nulls for garbage collection
sound = null;
soundSystem = null;
left16BitArray = null;
right16BitArray = null;
left32BitArray = null;
right32BitArray = null;
floatLeft = null;
floatRight = null;
buffer = null;
minMax = null;
}
catch (Exception ex)
{
throw ex;
}
finally
{
// Did we have to generate a peak file?
if (generatePeakFile)
{
// Close writer and stream
gzipStream.Close();
binaryWriter.Close();
fileStream.Close();
// Set nulls
gzipStream = null;
binaryWriter = null;
fileStream = null;
}
}
// Call garbage collector
GC.Collect();
这是从float数组中提取最小值/最大值的方法:
/// <summary>
/// This method takes the left channel and right channel wave raw data and analyses it to get
/// the maximum and minimum values in the float structure. It returns a data structure named
/// WaveDataMinMax (see class description for more information). Negative values can be converted to
/// positive values before min and max comparaison. Set this parameter to true for output meters and
/// false for wave form display controls.
/// </summary>
/// <param name=\"waveDataLeft\">Raw wave data (left channel)</param>
/// <param name=\"waveDataRight\">Raw wave data (right channel)</param>
/// <param name=\"convertNegativetoPositive\">Convert negative values to positive values (ex: true when used for output meters,/// false when used with wave form display controls (since the negative value is used to draw the bottom end of the waveform).<</param>
/// <returns>WaveDataMinMax data structure</returns>
public static WaveDataMinMax GetMinMaxFromWaveData(float[] waveDataLeft,float[] waveDataRight,bool convertNegativetoPositive)
{
// Create default data
WaveDataMinMax data = new WaveDataMinMax();
// Loop through values to get min/max
for (int i = 0; i < waveDataLeft.Length; i++)
{
// Set values to compare
float left = waveDataLeft[i];
float right = waveDataRight[i];
// Do we have to convert values before comparaison?
if (convertNegativetoPositive)
{
// Compare values,if negative then remove negative sign
if (left < 0)
{
left = -left;
}
if (right < 0)
{
right = -right;
}
}
// Calculate min/max for left channel
if (left < data.leftMin)
{
data.leftMin = left;
}
if (left > data.leftMax)
{
data.leftMax = left;
}
// Calculate min/max for right channel
if (right < data.rightMin)
{
data.rightMin = right;
}
if (right > data.rightMax)
{
data.rightMax = right;
}
// Calculate min/max mixing both channels
if (left < data.mixMin)
{
data.mixMin = left;
}
if (right < data.mixMin)
{
data.mixMin = right;
}
if (left > data.mixMax)
{
data.mixMax = left;
}
if (right > data.mixMax)
{
data.mixMax = right;
}
}
return data;
}
有人可以给我提示该怎么做吗?我希望我的代码还不错,可以用作16位文件的示例。谢谢你的帮助!
编辑:
这是使用32位变量转换代码的3x8位到24位:
left32BitArray = new Int32[buffer.Length / 6];
right32BitArray = new Int32[buffer.Length / 6];
for (int i = 0; i < buffer.Length; i = i + 6)
{
// Create smaller array in order to add the 4th 8-bit value
byte[] byteArrayLeft = new byte[4] {buffer[i],buffer[i + 1],buffer[i + 2],0 };
byte[] byteArrayRight = new byte[4] { buffer[i + 3],buffer[i + 4],buffer[i + 5],0 };
// Convert values to 32-bit variables
left32BitArray[i / 6] = BitConverter.ToInt32(byteArrayLeft,0);
right32BitArray[i / 6] = BitConverter.ToInt32(byteArrayRight,0);
}
解决方法
24位音频文件的块对齐为3 *通道数。为什么不选择100毫秒的音频:
int blockSize = 3 * channels * (sampleRate / 10);
这对于24位WAV可以正常工作。 FLAC阅读器是否允许您读出该粒度取决于其内部实现。
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。