你不会在 (Ext)AudioFile 中找到幅度缩放操作,因为它是你能做的最简单的 DSP。
假设您使用 ExtAudioFile 将您读取的任何内容转换为 32 位浮点数。要更改幅度,您只需乘以:
float ampScale = 0.5f; //this will reduce the 'volume' by -6db
for (int ii=0; ii<numSamples; ++ii) {
*sampOut = *sampIn * ampScale;
sampOut++; sampIn++;
}
要增加增益,您只需使用 > 1.f 的比例。例如,2.f 的 ampScale 将为您提供 +6dB 的增益。
如果要标准化,则必须对音频进行两次传递:一次确定具有最大幅度的样本。然后另一个实际应用您计算的增益。
使用 AudioQueue 服务只是为了访问音量属性是严重的,严重的矫枉过正。
更新:
在您更新的代码中,您将每个字节乘以0.5 而不是每个样本。这是您的代码的快速而肮脏的修复,但请参阅下面的注释。我不会做你正在做的事。
...
// create short pointers to our byte data
int16_t *inDataShort = (int16_t *)inData;
int16_t *outDataShort = (int16_t *)inData;
int16_t ampScale = 2;
for (int i = 0; i < fileSize; i++) {
outDataShort[i] = inDataShort[i] / ampScale;
}
...
当然,这不是最好的处理方式:它假定您的文件是 little-endian 16 位有符号线性 PCM。(大多数 WAV 文件是,但不是 AIFF、m4a、mp3 等。)我会使用 ExtAudioFile API 而不是 AudioFile API,因为这会将您正在阅读的任何格式转换为您想要在代码中使用的任何格式。通常最简单的做法是将样本读取为 32 位浮点数。这是您使用 ExtAudioAPI 处理任何输入文件格式的代码示例,包括立体声和单声道
void ScaleAudioFileAmplitude(NSURL *theURL, float ampScale) {
OSStatus err = noErr;
ExtAudioFileRef audiofile;
ExtAudioFileOpenURL((CFURLRef)theURL, &audiofile);
assert(audiofile);
// get some info about the file's format.
AudioStreamBasicDescription fileFormat;
UInt32 size = sizeof(fileFormat);
err = ExtAudioFileGetProperty(audiofile, kExtAudioFileProperty_FileDataFormat, &size, &fileFormat);
// we'll need to know what type of file it is later when we write
AudioFileID aFile;
size = sizeof(aFile);
err = ExtAudioFileGetProperty(audiofile, kExtAudioFileProperty_AudioFile, &size, &aFile);
AudioFileTypeID fileType;
size = sizeof(fileType);
err = AudioFileGetProperty(aFile, kAudioFilePropertyFileFormat, &size, &fileType);
// tell the ExtAudioFile API what format we want samples back in
AudioStreamBasicDescription clientFormat;
bzero(&clientFormat, sizeof(clientFormat));
clientFormat.mChannelsPerFrame = fileFormat.mChannelsPerFrame;
clientFormat.mBytesPerFrame = 4;
clientFormat.mBytesPerPacket = clientFormat.mBytesPerFrame;
clientFormat.mFramesPerPacket = 1;
clientFormat.mBitsPerChannel = 32;
clientFormat.mFormatID = kAudioFormatLinearPCM;
clientFormat.mSampleRate = fileFormat.mSampleRate;
clientFormat.mFormatFlags = kLinearPCMFormatFlagIsFloat | kAudioFormatFlagIsNonInterleaved;
err = ExtAudioFileSetProperty(audiofile, kExtAudioFileProperty_ClientDataFormat, sizeof(clientFormat), &clientFormat);
// find out how many frames we need to read
SInt64 numFrames = 0;
size = sizeof(numFrames);
err = ExtAudioFileGetProperty(audiofile, kExtAudioFileProperty_FileLengthFrames, &size, &numFrames);
// create the buffers for reading in data
AudioBufferList *bufferList = malloc(sizeof(AudioBufferList) + sizeof(AudioBuffer) * (clientFormat.mChannelsPerFrame - 1));
bufferList->mNumberBuffers = clientFormat.mChannelsPerFrame;
for (int ii=0; ii < bufferList->mNumberBuffers; ++ii) {
bufferList->mBuffers[ii].mDataByteSize = sizeof(float) * numFrames;
bufferList->mBuffers[ii].mNumberChannels = 1;
bufferList->mBuffers[ii].mData = malloc(bufferList->mBuffers[ii].mDataByteSize);
}
// read in the data
UInt32 rFrames = (UInt32)numFrames;
err = ExtAudioFileRead(audiofile, &rFrames, bufferList);
// close the file
err = ExtAudioFileDispose(audiofile);
// process the audio
for (int ii=0; ii < bufferList->mNumberBuffers; ++ii) {
float *fBuf = (float *)bufferList->mBuffers[ii].mData;
for (int jj=0; jj < rFrames; ++jj) {
*fBuf = *fBuf * ampScale;
fBuf++;
}
}
// open the file for writing
err = ExtAudioFileCreateWithURL((CFURLRef)theURL, fileType, &fileFormat, NULL, kAudioFileFlags_EraseFile, &audiofile);
// tell the ExtAudioFile API what format we'll be sending samples in
err = ExtAudioFileSetProperty(audiofile, kExtAudioFileProperty_ClientDataFormat, sizeof(clientFormat), &clientFormat);
// write the data
err = ExtAudioFileWrite(audiofile, rFrames, bufferList);
// close the file
ExtAudioFileDispose(audiofile);
// destroy the buffers
for (int ii=0; ii < bufferList->mNumberBuffers; ++ii) {
free(bufferList->mBuffers[ii].mData);
}
free(bufferList);
bufferList = NULL;
}