void HRTFPanner::pan(double desiredAzimuth,
double elevation,
const AudioBus* inputBus,
AudioBus* outputBus,
size_t framesToProcess,
AudioBus::ChannelInterpretation channelInterpretation) {
unsigned numInputChannels = inputBus ? inputBus->numberOfChannels() : 0;
bool isInputGood = inputBus && numInputChannels >= 1 && numInputChannels <= 2;
ASSERT(isInputGood);
bool isOutputGood = outputBus && outputBus->numberOfChannels() == 2 &&
framesToProcess <= outputBus->length();
ASSERT(isOutputGood);
if (!isInputGood || !isOutputGood) {
if (outputBus)
outputBus->zero();
return;
}
HRTFDatabase* database = m_databaseLoader->database();
if (!database) {
outputBus->copyFrom(*inputBus, channelInterpretation);
return;
}
// IRCAM HRTF azimuths values from the loaded database is reversed from the
// panner's notion of azimuth.
double azimuth = -desiredAzimuth;
bool isAzimuthGood = azimuth >= -180.0 && azimuth <= 180.0;
ASSERT(isAzimuthGood);
if (!isAzimuthGood) {
outputBus->zero();
return;
}
// Normally, we'll just be dealing with mono sources.
// If we have a stereo input, implement stereo panning with left source
// processed by left HRTF, and right source by right HRTF.
const AudioChannel* inputChannelL =
inputBus->channelByType(AudioBus::ChannelLeft);
const AudioChannel* inputChannelR =
numInputChannels > 1 ? inputBus->channelByType(AudioBus::ChannelRight)
: nullptr;
// Get source and destination pointers.
const float* sourceL = inputChannelL->data();
const float* sourceR = numInputChannels > 1 ? inputChannelR->data() : sourceL;
float* destinationL =
outputBus->channelByType(AudioBus::ChannelLeft)->mutableData();
float* destinationR =
outputBus->channelByType(AudioBus::ChannelRight)->mutableData();
double azimuthBlend;
int desiredAzimuthIndex =
calculateDesiredAzimuthIndexAndBlend(azimuth, azimuthBlend);
// Initially snap azimuth and elevation values to first values encountered.
if (m_azimuthIndex1 == UninitializedAzimuth) {
m_azimuthIndex1 = desiredAzimuthIndex;
m_elevation1 = elevation;
}
if (m_azimuthIndex2 == UninitializedAzimuth) {
m_azimuthIndex2 = desiredAzimuthIndex;
m_elevation2 = elevation;
}
// Cross-fade / transition over a period of around 45 milliseconds.
// This is an empirical value tuned to be a reasonable trade-off between
// smoothness and speed.
const double fadeFrames = sampleRate() <= 48000 ? 2048 : 4096;
// Check for azimuth and elevation changes, initiating a cross-fade if needed.
if (!m_crossfadeX && m_crossfadeSelection == CrossfadeSelection1) {
if (desiredAzimuthIndex != m_azimuthIndex1 || elevation != m_elevation1) {
// Cross-fade from 1 -> 2
m_crossfadeIncr = 1 / fadeFrames;
m_azimuthIndex2 = desiredAzimuthIndex;
m_elevation2 = elevation;
}
}
if (m_crossfadeX == 1 && m_crossfadeSelection == CrossfadeSelection2) {
if (desiredAzimuthIndex != m_azimuthIndex2 || elevation != m_elevation2) {
// Cross-fade from 2 -> 1
m_crossfadeIncr = -1 / fadeFrames;
m_azimuthIndex1 = desiredAzimuthIndex;
m_elevation1 = elevation;
}
}
// This algorithm currently requires that we process in power-of-two size
// chunks at least AudioUtilities::kRenderQuantumFrames.
ASSERT(1UL << static_cast<int>(log2(framesToProcess)) == framesToProcess);
DCHECK_GE(framesToProcess, AudioUtilities::kRenderQuantumFrames);
const unsigned framesPerSegment = AudioUtilities::kRenderQuantumFrames;
const unsigned numberOfSegments = framesToProcess / framesPerSegment;
for (unsigned segment = 0; segment < numberOfSegments; ++segment) {
// Get the HRTFKernels and interpolated delays.
HRTFKernel* kernelL1;
HRTFKernel* kernelR1;
HRTFKernel* kernelL2;
HRTFKernel* kernelR2;
double frameDelayL1;
double frameDelayR1;
double frameDelayL2;
double frameDelayR2;
database->getKernelsFromAzimuthElevation(azimuthBlend, m_azimuthIndex1,
m_elevation1, kernelL1, kernelR1,
frameDelayL1, frameDelayR1);
database->getKernelsFromAzimuthElevation(azimuthBlend, m_azimuthIndex2,
m_elevation2, kernelL2, kernelR2,
frameDelayL2, frameDelayR2);
bool areKernelsGood = kernelL1 && kernelR1 && kernelL2 && kernelR2;
ASSERT(areKernelsGood);
if (!areKernelsGood) {
outputBus->zero();
return;
}
ASSERT(frameDelayL1 / sampleRate() < MaxDelayTimeSeconds &&
frameDelayR1 / sampleRate() < MaxDelayTimeSeconds);
ASSERT(frameDelayL2 / sampleRate() < MaxDelayTimeSeconds &&
frameDelayR2 / sampleRate() < MaxDelayTimeSeconds);
// Crossfade inter-aural delays based on transitions.
double frameDelayL =
(1 - m_crossfadeX) * frameDelayL1 + m_crossfadeX * frameDelayL2;
double frameDelayR =
(1 - m_crossfadeX) * frameDelayR1 + m_crossfadeX * frameDelayR2;
// Calculate the source and destination pointers for the current segment.
unsigned offset = segment * framesPerSegment;
const float* segmentSourceL = sourceL + offset;
const float* segmentSourceR = sourceR + offset;
float* segmentDestinationL = destinationL + offset;
float* segmentDestinationR = destinationR + offset;
// First run through delay lines for inter-aural time difference.
m_delayLineL.setDelayFrames(frameDelayL);
m_delayLineR.setDelayFrames(frameDelayR);
m_delayLineL.process(segmentSourceL, segmentDestinationL, framesPerSegment);
m_delayLineR.process(segmentSourceR, segmentDestinationR, framesPerSegment);
bool needsCrossfading = m_crossfadeIncr;
// Have the convolvers render directly to the final destination if we're not
// cross-fading.
float* convolutionDestinationL1 =
needsCrossfading ? m_tempL1.data() : segmentDestinationL;
float* convolutionDestinationR1 =
needsCrossfading ? m_tempR1.data() : segmentDestinationR;
float* convolutionDestinationL2 =
needsCrossfading ? m_tempL2.data() : segmentDestinationL;
float* convolutionDestinationR2 =
needsCrossfading ? m_tempR2.data() : segmentDestinationR;
// Now do the convolutions.
// Note that we avoid doing convolutions on both sets of convolvers if we're
// not currently cross-fading.
if (m_crossfadeSelection == CrossfadeSelection1 || needsCrossfading) {
m_convolverL1.process(kernelL1->fftFrame(), segmentDestinationL,
convolutionDestinationL1, framesPerSegment);
m_convolverR1.process(kernelR1->fftFrame(), segmentDestinationR,
convolutionDestinationR1, framesPerSegment);
}
if (m_crossfadeSelection == CrossfadeSelection2 || needsCrossfading) {
m_convolverL2.process(kernelL2->fftFrame(), segmentDestinationL,
convolutionDestinationL2, framesPerSegment);
m_convolverR2.process(kernelR2->fftFrame(), segmentDestinationR,
convolutionDestinationR2, framesPerSegment);
}
if (needsCrossfading) {
// Apply linear cross-fade.
float x = m_crossfadeX;
float incr = m_crossfadeIncr;
for (unsigned i = 0; i < framesPerSegment; ++i) {
segmentDestinationL[i] = (1 - x) * convolutionDestinationL1[i] +
x * convolutionDestinationL2[i];
segmentDestinationR[i] = (1 - x) * convolutionDestinationR1[i] +
x * convolutionDestinationR2[i];
x += incr;
}
// Update cross-fade value from local.
m_crossfadeX = x;
if (m_crossfadeIncr > 0 && fabs(m_crossfadeX - 1) < m_crossfadeIncr) {
// We've fully made the crossfade transition from 1 -> 2.
m_crossfadeSelection = CrossfadeSelection2;
m_crossfadeX = 1;
m_crossfadeIncr = 0;
} else if (m_crossfadeIncr < 0 && fabs(m_crossfadeX) < -m_crossfadeIncr) {
// We've fully made the crossfade transition from 2 -> 1.
m_crossfadeSelection = CrossfadeSelection1;
m_crossfadeX = 0;
m_crossfadeIncr = 0;
}
}
}
}
void HRTFPanner::pan(double desiredAzimuth, double elevation, const AudioBus* inputBus, AudioBus* outputBus, size_t framesToProcess)
{
unsigned numInputChannels = inputBus ? inputBus->numberOfChannels() : 0;
bool isInputGood = inputBus && numInputChannels >= 1 && numInputChannels <= 2;
ASSERT(isInputGood);
bool isOutputGood = outputBus && outputBus->numberOfChannels() == 2 && framesToProcess <= outputBus->length();
ASSERT(isOutputGood);
if (!isInputGood || !isOutputGood) {
if (outputBus)
outputBus->zero();
return;
}
// This code only runs as long as the context is alive and after database has been loaded.
HRTFDatabase* database = HRTFDatabaseLoader::defaultHRTFDatabase();
ASSERT(database);
if (!database) {
outputBus->zero();
return;
}
// IRCAM HRTF azimuths values from the loaded database is reversed from the panner's notion of azimuth.
double azimuth = -desiredAzimuth;
bool isAzimuthGood = azimuth >= -180.0 && azimuth <= 180.0;
ASSERT(isAzimuthGood);
if (!isAzimuthGood) {
outputBus->zero();
return;
}
// Normally, we'll just be dealing with mono sources.
// If we have a stereo input, implement stereo panning with left source processed by left HRTF, and right source by right HRTF.
const AudioChannel* inputChannelL = inputBus->channelByType(AudioBus::ChannelLeft);
const AudioChannel* inputChannelR = numInputChannels > 1 ? inputBus->channelByType(AudioBus::ChannelRight) : 0;
// Get source and destination pointers.
const float* sourceL = inputChannelL->data();
const float* sourceR = numInputChannels > 1 ? inputChannelR->data() : sourceL;
float* destinationL = outputBus->channelByType(AudioBus::ChannelLeft)->mutableData();
float* destinationR = outputBus->channelByType(AudioBus::ChannelRight)->mutableData();
double azimuthBlend;
int desiredAzimuthIndex = calculateDesiredAzimuthIndexAndBlend(azimuth, azimuthBlend);
// This algorithm currently requires that we process in power-of-two size chunks at least 128.
ASSERT(1UL << static_cast<int>(log2(framesToProcess)) == framesToProcess);
ASSERT(framesToProcess >= 128);
const unsigned framesPerSegment = 128;
const unsigned numberOfSegments = framesToProcess / framesPerSegment;
for (unsigned segment = 0; segment < numberOfSegments; ++segment) {
if (m_isFirstRender) {
// Snap exactly to desired position (first time and after reset()).
m_azimuthIndex = desiredAzimuthIndex;
m_isFirstRender = false;
} else {
// Each segment renders with an azimuth index closer by one to the desired azimuth index.
// Because inter-aural time delay is mostly a factor of azimuth and the delay is where the clicks and graininess come from,
// we don't bother smoothing the elevations.
int numberOfAzimuths = database->numberOfAzimuths();
bool wrap = wrapDistance(m_azimuthIndex, desiredAzimuthIndex, numberOfAzimuths);
if (wrap) {
if (m_azimuthIndex < desiredAzimuthIndex)
m_azimuthIndex = (m_azimuthIndex - 1 + numberOfAzimuths) % numberOfAzimuths;
else if (m_azimuthIndex > desiredAzimuthIndex)
m_azimuthIndex = (m_azimuthIndex + 1) % numberOfAzimuths;
} else {
if (m_azimuthIndex < desiredAzimuthIndex)
m_azimuthIndex = (m_azimuthIndex + 1) % numberOfAzimuths;
else if (m_azimuthIndex > desiredAzimuthIndex)
m_azimuthIndex = (m_azimuthIndex - 1 + numberOfAzimuths) % numberOfAzimuths;
}
}
// Get the HRTFKernels and interpolated delays.
HRTFKernel* kernelL;
HRTFKernel* kernelR;
double frameDelayL;
double frameDelayR;
database->getKernelsFromAzimuthElevation(azimuthBlend, m_azimuthIndex, elevation, kernelL, kernelR, frameDelayL, frameDelayR);
ASSERT(kernelL && kernelR);
if (!kernelL || !kernelR) {
outputBus->zero();
return;
}
ASSERT(frameDelayL / sampleRate() < MaxDelayTimeSeconds && frameDelayR / sampleRate() < MaxDelayTimeSeconds);
// Calculate the source and destination pointers for the current segment.
unsigned offset = segment * framesPerSegment;
const float* segmentSourceL = sourceL + offset;
const float* segmentSourceR = sourceR + offset;
float* segmentDestinationL = destinationL + offset;
float* segmentDestinationR = destinationR + offset;
// First run through delay lines for inter-aural time difference.
m_delayLineL.setDelayFrames(frameDelayL);
m_delayLineR.setDelayFrames(frameDelayR);
m_delayLineL.process(segmentSourceL, segmentDestinationL, framesPerSegment);
m_delayLineR.process(segmentSourceR, segmentDestinationR, framesPerSegment);
// Now do the convolutions in-place.
m_convolverL.process(kernelL->fftFrame(), segmentDestinationL, segmentDestinationL, framesPerSegment);
m_convolverR.process(kernelR->fftFrame(), segmentDestinationR, segmentDestinationR, framesPerSegment);
}
}
void HRTFPanner::pan(double desiredAzimuth, double elevation, const AudioChunk* inputBus, AudioChunk* outputBus)
{
unsigned numInputChannels =
inputBus->IsNull() ? 0 : inputBus->mChannelData.Length();
MOZ_ASSERT(numInputChannels <= 2);
MOZ_ASSERT(inputBus->mDuration == WEBAUDIO_BLOCK_SIZE);
bool isOutputGood = outputBus && outputBus->mChannelData.Length() == 2 && outputBus->mDuration == WEBAUDIO_BLOCK_SIZE;
MOZ_ASSERT(isOutputGood);
if (!isOutputGood) {
if (outputBus)
outputBus->SetNull(outputBus->mDuration);
return;
}
HRTFDatabase* database = m_databaseLoader->database();
if (!database) { // not yet loaded
outputBus->SetNull(outputBus->mDuration);
return;
}
// IRCAM HRTF azimuths values from the loaded database is reversed from the panner's notion of azimuth.
double azimuth = -desiredAzimuth;
bool isAzimuthGood = azimuth >= -180.0 && azimuth <= 180.0;
MOZ_ASSERT(isAzimuthGood);
if (!isAzimuthGood) {
outputBus->SetNull(outputBus->mDuration);
return;
}
// Normally, we'll just be dealing with mono sources.
// If we have a stereo input, implement stereo panning with left source processed by left HRTF, and right source by right HRTF.
// Get destination pointers.
float* destinationL =
static_cast<float*>(const_cast<void*>(outputBus->mChannelData[0]));
float* destinationR =
static_cast<float*>(const_cast<void*>(outputBus->mChannelData[1]));
double azimuthBlend;
int desiredAzimuthIndex = calculateDesiredAzimuthIndexAndBlend(azimuth, azimuthBlend);
// Initially snap azimuth and elevation values to first values encountered.
if (m_azimuthIndex1 == UninitializedAzimuth) {
m_azimuthIndex1 = desiredAzimuthIndex;
m_elevation1 = elevation;
}
if (m_azimuthIndex2 == UninitializedAzimuth) {
m_azimuthIndex2 = desiredAzimuthIndex;
m_elevation2 = elevation;
}
// Cross-fade / transition over a period of around 45 milliseconds.
// This is an empirical value tuned to be a reasonable trade-off between
// smoothness and speed.
const double fadeFrames = sampleRate() <= 48000 ? 2048 : 4096;
// Check for azimuth and elevation changes, initiating a cross-fade if needed.
if (!m_crossfadeX && m_crossfadeSelection == CrossfadeSelection1) {
if (desiredAzimuthIndex != m_azimuthIndex1 || elevation != m_elevation1) {
// Cross-fade from 1 -> 2
m_crossfadeIncr = 1 / fadeFrames;
m_azimuthIndex2 = desiredAzimuthIndex;
m_elevation2 = elevation;
}
}
if (m_crossfadeX == 1 && m_crossfadeSelection == CrossfadeSelection2) {
if (desiredAzimuthIndex != m_azimuthIndex2 || elevation != m_elevation2) {
// Cross-fade from 2 -> 1
m_crossfadeIncr = -1 / fadeFrames;
m_azimuthIndex1 = desiredAzimuthIndex;
m_elevation1 = elevation;
}
}
// Get the HRTFKernels and interpolated delays.
HRTFKernel* kernelL1;
HRTFKernel* kernelR1;
HRTFKernel* kernelL2;
HRTFKernel* kernelR2;
double frameDelayL1;
double frameDelayR1;
double frameDelayL2;
double frameDelayR2;
database->getKernelsFromAzimuthElevation(azimuthBlend, m_azimuthIndex1, m_elevation1, kernelL1, kernelR1, frameDelayL1, frameDelayR1);
database->getKernelsFromAzimuthElevation(azimuthBlend, m_azimuthIndex2, m_elevation2, kernelL2, kernelR2, frameDelayL2, frameDelayR2);
bool areKernelsGood = kernelL1 && kernelR1 && kernelL2 && kernelR2;
MOZ_ASSERT(areKernelsGood);
if (!areKernelsGood) {
outputBus->SetNull(outputBus->mDuration);
return;
}
MOZ_ASSERT(frameDelayL1 / sampleRate() < MaxDelayTimeSeconds && frameDelayR1 / sampleRate() < MaxDelayTimeSeconds);
MOZ_ASSERT(frameDelayL2 / sampleRate() < MaxDelayTimeSeconds && frameDelayR2 / sampleRate() < MaxDelayTimeSeconds);
// Crossfade inter-aural delays based on transitions.
double frameDelaysL[WEBAUDIO_BLOCK_SIZE];
double frameDelaysR[WEBAUDIO_BLOCK_SIZE];
{
float x = m_crossfadeX;
float incr = m_crossfadeIncr;
for (unsigned i = 0; i < WEBAUDIO_BLOCK_SIZE; ++i) {
frameDelaysL[i] = (1 - x) * frameDelayL1 + x * frameDelayL2;
frameDelaysR[i] = (1 - x) * frameDelayR1 + x * frameDelayR2;
x += incr;
}
}
// First run through delay lines for inter-aural time difference.
m_delayLine.Write(*inputBus);
// "Speakers" means a mono input is read into both outputs (with possibly
// different delays).
m_delayLine.ReadChannel(frameDelaysL, outputBus, 0,
ChannelInterpretation::Speakers);
m_delayLine.ReadChannel(frameDelaysR, outputBus, 1,
ChannelInterpretation::Speakers);
m_delayLine.NextBlock();
bool needsCrossfading = m_crossfadeIncr;
// Have the convolvers render directly to the final destination if we're not cross-fading.
float* convolutionDestinationL1 = needsCrossfading ? m_tempL1.Elements() : destinationL;
float* convolutionDestinationR1 = needsCrossfading ? m_tempR1.Elements() : destinationR;
float* convolutionDestinationL2 = needsCrossfading ? m_tempL2.Elements() : destinationL;
float* convolutionDestinationR2 = needsCrossfading ? m_tempR2.Elements() : destinationR;
// Now do the convolutions.
// Note that we avoid doing convolutions on both sets of convolvers if we're not currently cross-fading.
if (m_crossfadeSelection == CrossfadeSelection1 || needsCrossfading) {
m_convolverL1.process(kernelL1->fftFrame(), destinationL, convolutionDestinationL1, WEBAUDIO_BLOCK_SIZE);
m_convolverR1.process(kernelR1->fftFrame(), destinationR, convolutionDestinationR1, WEBAUDIO_BLOCK_SIZE);
}
if (m_crossfadeSelection == CrossfadeSelection2 || needsCrossfading) {
m_convolverL2.process(kernelL2->fftFrame(), destinationL, convolutionDestinationL2, WEBAUDIO_BLOCK_SIZE);
m_convolverR2.process(kernelR2->fftFrame(), destinationR, convolutionDestinationR2, WEBAUDIO_BLOCK_SIZE);
}
if (needsCrossfading) {
// Apply linear cross-fade.
float x = m_crossfadeX;
float incr = m_crossfadeIncr;
for (unsigned i = 0; i < WEBAUDIO_BLOCK_SIZE; ++i) {
destinationL[i] = (1 - x) * convolutionDestinationL1[i] + x * convolutionDestinationL2[i];
destinationR[i] = (1 - x) * convolutionDestinationR1[i] + x * convolutionDestinationR2[i];
x += incr;
}
// Update cross-fade value from local.
m_crossfadeX = x;
if (m_crossfadeIncr > 0 && fabs(m_crossfadeX - 1) < m_crossfadeIncr) {
// We've fully made the crossfade transition from 1 -> 2.
m_crossfadeSelection = CrossfadeSelection2;
m_crossfadeX = 1;
m_crossfadeIncr = 0;
} else if (m_crossfadeIncr < 0 && fabs(m_crossfadeX) < -m_crossfadeIncr) {
// We've fully made the crossfade transition from 2 -> 1.
m_crossfadeSelection = CrossfadeSelection1;
m_crossfadeX = 0;
m_crossfadeIncr = 0;
}
}
}
