offline rendering with a lowpass filter causes aliasing and clipping - core-audio

Question

I have a buffer of samples that are 8khz, and I am trying to simply apply a lowpass filter to the buffer. Meaning, I start with a buffer of 8khz samples, and I want to end up with a buffer of 8khz LOWPASSED samples. If I hook up a lowpass unit and connect it with the default output unit and supply my buffer, it sounds perfect and properly low passed. However, as soon as I remove the output and call AudioUnitRender on the low pass audio unit directly, the resulting samples are aliased and clipped.
#import "EffectMachine.h"
#import <AudioToolbox/AudioToolbox.h>
#import "AudioHelpers.h"
#import "Buffer.h"
#interface EffectMachine ()
#property (nonatomic, strong) Buffer *buffer;
#end
typedef struct EffectPlayer {
NSUInteger index;
AudioUnit lowPassUnit;
__unsafe_unretained Buffer *buffer;
} EffectPlayer;
OSStatus EffectMachineCallbackRenderProc(void *inRefCon,
AudioUnitRenderActionFlags *ioActionFlags,
const AudioTimeStamp *inTimeStamp,
UInt32 inBusNumber,
UInt32 inNumberFrames,
AudioBufferList * ioData);
OSStatus EffectMachineCallbackRenderProc(void *inRefCon,
AudioUnitRenderActionFlags *ioActionFlags,
const AudioTimeStamp *inTimeStamp,
UInt32 inBusNumber,
UInt32 inNumberFrames,
AudioBufferList * ioData) {
struct EffectPlayer *player = (struct EffectPlayer *)inRefCon;
for (int i = 0; i < inNumberFrames; i++) {
float sample;
if (player->index < player->buffer.size) {
sample = (float)player->buffer.samples[player->index];
player->index += 1;
} else {
sample = 0;
}
((float *)ioData->mBuffers[0].mData)[i] = sample;
((float *)ioData->mBuffers[1].mData)[i] = sample;
}
return noErr;
}
#implementation EffectMachine {
EffectPlayer player;
}
-(instancetype)initWithBuffer:(Buffer *)buffer {
if (self = [super init]) {
self.buffer = buffer;
}
return self;
}
-(Buffer *)process {
struct EffectPlayer initialized = {0};
player = initialized;
player.buffer = self.buffer;
[self setupAudioUnits];
Buffer *buffer = [self processedBuffer];
[self cleanup];
return buffer;
}
-(void)setupAudioUnits {
AudioComponentDescription lowpasscd = {0};
lowpasscd.componentType = kAudioUnitType_Effect;
lowpasscd.componentSubType = kAudioUnitSubType_LowPassFilter;
lowpasscd.componentManufacturer = kAudioUnitManufacturer_Apple;
AudioComponent comp = AudioComponentFindNext(NULL, &lowpasscd);
if (comp == NULL) NSLog(#"can't get lowpass unit");
AudioComponentInstanceNew(comp, &player.lowPassUnit);
AURenderCallbackStruct input;
input.inputProc = EffectMachineCallbackRenderProc;
input.inputProcRefCon = &player;
CheckError(AudioUnitSetProperty(player.lowPassUnit,
kAudioUnitProperty_SetRenderCallback,
kAudioUnitScope_Input,
0,
&input,
sizeof(input)),
"AudioUnitSetProperty for callback failed");
CheckError(AudioUnitSetParameter(player.lowPassUnit,
kLowPassParam_CutoffFrequency,
kAudioUnitScope_Global,
0,
1500,
0), "AudioUnitSetParameter cutoff for lowpass failed");
CheckError(AudioUnitSetParameter(player.lowPassUnit,
kLowPassParam_Resonance,
kAudioUnitScope_Global,
0,
0,
0), "AudioUnitSetParameter resonance for lowpass failed");
CheckError(AudioUnitInitialize(player.lowPassUnit),
"Couldn't initialize lowpass unit");
}
-(Buffer *)processedBuffer {
AudioBufferList *bufferlist = malloc(sizeof(AudioBufferList));
UInt32 blockSize = 1024;
float *left = malloc(sizeof(float) * blockSize);
float *right = malloc(sizeof(float) * blockSize);
bufferlist->mBuffers[0].mData = left;
bufferlist->mBuffers[1].mData = right;
UInt32 size = sizeof(float) * blockSize;
AudioTimeStamp inTimeStamp;
memset(&inTimeStamp, 0, sizeof(AudioTimeStamp));
inTimeStamp.mSampleTime = 0;
AudioUnitRenderActionFlags flag = 0;
NSUInteger length = ceil(self.buffer.size / (float)blockSize);
double *processed = malloc(sizeof(double) * blockSize * length);
for (int i = 0; i < length; i++) {
bufferlist->mBuffers[0].mDataByteSize = size;
bufferlist->mBuffers[1].mDataByteSize = size;
bufferlist->mNumberBuffers = 2;
inTimeStamp.mFlags = kAudioTimeStampSampleTimeValid;
AudioUnitRender(player.lowPassUnit, &flag, &inTimeStamp, 0, blockSize, bufferlist);
for (NSUInteger j = 0; j < blockSize; j++) {
processed[j + (blockSize * i)] = left[j];
}
inTimeStamp.mSampleTime += blockSize;
}
Buffer *buffer = [[Buffer alloc] initWithSamples:processed size:self.buffer.size sampleRate:self.buffer.sampleRate];
free(bufferlist);
free(left);
free(right);
free(processed);
return buffer;
}
-(void)cleanup {
AudioOutputUnitStop(player.lowPassUnit);
AudioUnitUninitialize(player.lowPassUnit);
AudioComponentInstanceDispose(player.lowPassUnit);
}
#end
If I add a generic output and try to set an 8khz ASBD on its input, then I just get garbage noise for output.. It looks like, 0,0,0,0,0,17438231945853048031929171968.000000,0,0,0,-2548199532257382185315640279040.000000... Yikes!
I tried adding ASBDs to the input and output of the lowpass unit, giving it an 8khz sample rate property, and it did nothing.. I tried adding converter units (with ASBDs set to 8khz) before, and then after, and then before AND after the lowpass filter (in a chain), this also did not work.
As a side question, my buffer is mono 8khz samples, and if I make my buffer list have mNumberBuffers set to 1, then my lowpass input render proc is never called... Is there a way to not have to use stereo channels?

Answer 1

I am using converters at both ends with ASBD set to 8000 samplerate mono floats for input of input converter and output of output converter while using 44100.0 stereo for input and output of the low pass unit, and calling AudioUnitRender on the end converter with no io unit for the offline render. For the online render I put a converter unit before the io unit so the render callback will pull from buffers at 8K for playback too. It appears that the lower sample rate on the output ASBD requires a higher maximum frames per slice and a smaller slice (AudioUnitRender inNumberFrames) and that's why it wouldn't render.
#import "ViewController.h"
#import <AudioToolbox/AudioToolbox.h>
#implementation ViewController{
int sampleCount;
int renderBufferHead;
float *renderBuffer;
}
- (void)viewDidLoad {
[super viewDidLoad];
float sampleRate = 8000;
int bufferSeconds = 3;
sampleCount = sampleRate * bufferSeconds;//seconds
float *originalSaw = generateSawWaveBuffer(440, sampleRate, sampleCount);
renderBuffer = originalSaw;
renderBufferHead = 0;
AURenderCallbackStruct cbStruct = {renderCallback,(__bridge void *)self};
//this will do offline render using the render callback, callback just reads from renderBuffer at samplerate
float *processedBuffer = offlineRender(sampleCount, sampleRate, &cbStruct);
renderBufferHead = 0;//rewind render buffer after processing
//set up audio units to do live render using the render callback at sample rate then self destruct after delay
//it will play originalSaw for bufferSeconds, then after delay will switch renderBuffer to point at processedBuffer
float secondsToPlayAudio = (bufferSeconds + 1) * 2;
onlineRender(sampleRate, &cbStruct,secondsToPlayAudio);
//wait for original to finish playing, then change render callback source buffer to processed buffer
dispatch_after(dispatch_time(DISPATCH_TIME_NOW, (int64_t)((secondsToPlayAudio / 2) * NSEC_PER_SEC)), dispatch_get_main_queue(), ^{
renderBuffer = processedBuffer;
renderBufferHead = 0;//rewind render buffer
});
//destroy after all rendering done
dispatch_after(dispatch_time(DISPATCH_TIME_NOW, (int64_t)(secondsToPlayAudio * NSEC_PER_SEC)), dispatch_get_main_queue(), ^{
free(originalSaw);
free(processedBuffer);
});
}
float * offlineRender(int count, double sampleRate, AURenderCallbackStruct *cbStruct){
AudioComponentInstance inConverter = getComponentInstance(kAudioUnitType_FormatConverter, kAudioUnitSubType_AUConverter);
AudioComponentInstance lowPass = getComponentInstance(kAudioUnitType_Effect, kAudioUnitSubType_LowPassFilter);
AudioComponentInstance outConverter = getComponentInstance(kAudioUnitType_FormatConverter, kAudioUnitSubType_AUConverter);
AudioStreamBasicDescription asbd = getMonoFloatASBD(sampleRate);
AudioUnitSetProperty(inConverter, kAudioUnitProperty_StreamFormat, kAudioUnitScope_Input, 0, &asbd, sizeof(AudioStreamBasicDescription));
AudioUnitSetProperty(outConverter, kAudioUnitProperty_StreamFormat, kAudioUnitScope_Output, 0, &asbd, sizeof(AudioStreamBasicDescription));
AudioUnitSetProperty(inConverter, kAudioUnitProperty_SetRenderCallback, kAudioUnitScope_Input, 0, cbStruct, sizeof(AURenderCallbackStruct));
formatAndConnect(inConverter, lowPass);
formatAndConnect(lowPass, outConverter);
UInt32 maxFramesPerSlice = 4096;
AudioUnitSetProperty(inConverter, kAudioUnitProperty_MaximumFramesPerSlice, kAudioUnitScope_Global, 0, &maxFramesPerSlice, sizeof(UInt32));
AudioUnitSetProperty(lowPass, kAudioUnitProperty_MaximumFramesPerSlice, kAudioUnitScope_Global, 0, &maxFramesPerSlice, sizeof(UInt32));
AudioUnitSetProperty(outConverter, kAudioUnitProperty_MaximumFramesPerSlice, kAudioUnitScope_Global, 0, &maxFramesPerSlice, sizeof(UInt32));
AudioUnitInitialize(inConverter);
AudioUnitInitialize(lowPass);
AudioUnitInitialize(outConverter);
AudioUnitSetParameter(lowPass, kLowPassParam_CutoffFrequency, kAudioUnitScope_Global, 0, 500, 0);
AudioBufferList *bufferlist = malloc(sizeof(AudioBufferList) + sizeof(AudioBufferList));//stereo bufferlist + sizeof(AudioBuffer)
float *left = malloc(sizeof(float) * 4096);
bufferlist->mBuffers[0].mData = left;
bufferlist->mNumberBuffers = 1;
AudioTimeStamp inTimeStamp;
memset(&inTimeStamp, 0, sizeof(AudioTimeStamp));
inTimeStamp.mFlags = kAudioTimeStampSampleTimeValid;
inTimeStamp.mSampleTime = 0;
float *buffer = malloc(sizeof(float) * count);
int inNumberframes = 512;
AudioUnitRenderActionFlags flag = 0;
int framesRead = 0;
while (count){
inNumberframes = MIN(inNumberframes, count);
bufferlist->mBuffers[0].mDataByteSize = sizeof(float) * inNumberframes;
printf("Offline Render %i frames\n",inNumberframes);
AudioUnitRender(outConverter, &flag, &inTimeStamp, 0, inNumberframes, bufferlist);
memcpy(buffer + framesRead, left, sizeof(float) * inNumberframes);
inTimeStamp.mSampleTime += inNumberframes;
count -= inNumberframes;
framesRead += inNumberframes;
}
free(left);
// free(right);
free(bufferlist);
AudioUnitUninitialize(inConverter);
AudioUnitUninitialize(lowPass);
AudioUnitUninitialize(outConverter);
return buffer;
}
OSStatus renderCallback(void * inRefCon,
AudioUnitRenderActionFlags * ioActionFlags,
const AudioTimeStamp * inTimeStamp,
UInt32 inBusNumber,
UInt32 inNumberFrames,
AudioBufferList * ioData){
ViewController *self = (__bridge ViewController*)inRefCon;
float *left = ioData->mBuffers[0].mData;
for (int i = 0; i < inNumberFrames; i++) {
if (self->renderBufferHead >= self->sampleCount) {
left[i] = 0;
}
else{
left[i] = self->renderBuffer[self->renderBufferHead++];
}
}
if(ioData->mNumberBuffers == 2){
memcpy(ioData->mBuffers[1].mData, left, sizeof(float) * inNumberFrames);
}
printf("render %f to %f\n",inTimeStamp->mSampleTime,inTimeStamp->mSampleTime + inNumberFrames);
return noErr;
}
void onlineRender(double sampleRate, AURenderCallbackStruct *cbStruct,float duration){
AudioComponentInstance converter = getComponentInstance(kAudioUnitType_FormatConverter, kAudioUnitSubType_AUConverter);
AudioComponentInstance ioUnit = getComponentInstance(kAudioUnitType_Output, kAudioUnitSubType_DefaultOutput);
AudioStreamBasicDescription asbd = getMonoFloatASBD(sampleRate);
AudioUnitSetProperty(converter, kAudioUnitProperty_StreamFormat, kAudioUnitScope_Input, 0, &asbd, sizeof(AudioStreamBasicDescription));
AudioUnitSetProperty(converter, kAudioUnitProperty_SetRenderCallback, kAudioUnitScope_Input, 0, cbStruct, sizeof(AURenderCallbackStruct));
formatAndConnect(converter, ioUnit);
AudioUnitInitialize(converter);
AudioUnitInitialize(ioUnit);
AudioOutputUnitStart(ioUnit);
dispatch_after(dispatch_time(DISPATCH_TIME_NOW, (int64_t)(duration * NSEC_PER_SEC)), dispatch_get_main_queue(), ^{
AudioOutputUnitStop(ioUnit);
AudioUnitUninitialize(ioUnit);
AudioUnitUninitialize(converter);
});
}
float * generateSawWaveBuffer(float frequency,float sampleRate, int sampleCount){
float *buffer = malloc(sizeof(float) * sampleCount);
float increment = (frequency / sampleRate) * 2;
int increasing = 1;
float sample = 0;
for (int i = 0; i < sampleCount; i++) {
if (increasing) {
sample += increment;
if (sample >= 1) {
increasing = 0;
}
}
else{
sample -= increment;
if (sample < -1) {
increasing = 1;
}
}
buffer[i] = sample;
}
return buffer;
}
AudioComponentInstance getComponentInstance(OSType type,OSType subType){
AudioComponentDescription desc = {0};
desc.componentFlags = 0;
desc.componentFlagsMask = 0;
desc.componentManufacturer = kAudioUnitManufacturer_Apple;
desc.componentSubType = subType;
desc.componentType = type;
AudioComponent ioComponent = AudioComponentFindNext(NULL, &desc);
AudioComponentInstance unit;
AudioComponentInstanceNew(ioComponent, &unit);
return unit;
}
AudioStreamBasicDescription getMonoFloatASBD(double sampleRate){
AudioStreamBasicDescription asbd = {0};
asbd.mSampleRate = sampleRate;
asbd.mFormatID = kAudioFormatLinearPCM;
asbd.mFormatFlags = kAudioFormatFlagIsFloat | kAudioFormatFlagIsNonInterleaved | kAudioFormatFlagIsPacked;
asbd.mFramesPerPacket = 1;
asbd.mChannelsPerFrame = 1;
asbd.mBitsPerChannel = 32;
asbd.mBytesPerPacket = 4;
asbd.mBytesPerFrame = 4;
return asbd;
}
void formatAndConnect(AudioComponentInstance src,AudioComponentInstance dst){
AudioStreamBasicDescription asbd;
UInt32 propsize = sizeof(AudioStreamBasicDescription);
AudioUnitGetProperty(dst, kAudioUnitProperty_StreamFormat,kAudioUnitScope_Input,0,&asbd,&propsize);
AudioUnitSetProperty(src, kAudioUnitProperty_StreamFormat, kAudioUnitScope_Output, 0, &asbd, sizeof(AudioStreamBasicDescription));
AudioUnitConnection connection = {0};
connection.destInputNumber = 0;
connection.sourceAudioUnit = src;
connection.sourceOutputNumber = 0;
AudioUnitSetProperty(dst, kAudioUnitProperty_MakeConnection, kAudioUnitScope_Input, 0, &connection, sizeof(AudioUnitConnection));
}
#end