用于音频测量的 Swift AVFoundation 计时信息
Posted
技术标签:
【中文标题】用于音频测量的 Swift AVFoundation 计时信息【英文标题】：Swift AVFoundation timing info for audio measurements 【发布时间】：2019-08-11 10:51:06 【问题描述】：我正在创建一个应用程序，它将通过播放一些激励数据并记录麦克风输入来进行音频测量，然后分析数据。
我无法计算初始化和启动音频引擎所花费的时间，因为这每次都不同，并且还取决于所使用的硬件等。
所以，我有一个音频引擎并安装了 Tap the hardware input，输入 1 是麦克风录音，输入 2 是参考输入（也来自硬件）。输出在物理上是 Y-Split 并反馈到输入 2。
应用程序初始化引擎，播放刺激音频加上 1 秒的静音（以留出传播时间让麦克风记录整个信号），然后停止并关闭引擎。
我将两个输入缓冲区写为一个 WAV 文件，这样我就可以将它导入到现有的 DAW 中。目视检查信号。我可以看到每次我进行测量时，两个信号之间的时间差都是不同的（尽管麦克风没有移动并且硬件保持不变）。我假设这与硬件的延迟、初始化引擎所需的时间以及设备分配任务的方式有关。
我尝试在每个 installTap 函数上使用第一个缓冲区回调的 mach_absolute_time 来捕获绝对时间，然后减去两者，我可以看到每次调用都会有很大的不同：
class newAVAudioEngine
var engine = AVAudioEngine()
var audioBuffer = AVAudioPCMBuffer()
var running = true
var in1Buf:[Float]=Array(repeating:0, count:totalRecordSize)
var in2Buf:[Float]=Array(repeating:0, count:totalRecordSize)
var buf1current:Int = 0
var buf2current:Int = 0
var in1firstRun:Bool = false
var in2firstRun:Bool = false
var in1StartTime = 0
var in2startTime = 0
func measure(inputSweep:SweepFilter) -> measurement
initializeEngine(inputSweep: inputSweep)
while running == true
let measureResult = measurement.init(meas: meas,ref: ref)
return measureResult
func initializeEngine(inputSweep:SweepFilter)
buf1current = 0
buf2current = 0
in1StartTime = 0
in2startTime = 0
in1firstRun = true
in2firstRun = true
in1Buf = Array(repeating:0, count:totalRecordSize)
in2Buf = Array(repeating:0, count:totalRecordSize)
engine.stop()
engine.reset()
engine = AVAudioEngine()
let srcNode = AVAudiosourceNode _, _, frameCount, AudioBufferList -> OSStatus in
let ablPointer = UnsafeMutableAudioBufferListPointer(AudioBufferList)
if (Int(frameCount) + time) <= inputSweep.stimulus.count
for frame in 0..<Int(frameCount)
let value = inputSweep.stimulus[frame + time]
for buffer in ablPointer
let buf: UnsafeMutableBufferPointer<Float> = UnsafeMutableBufferPointer(buffer)
buf[frame] = value
time += Int(frameCount)
return noErr
else
for frame in 0..<Int(frameCount)
let value = 0
for buffer in ablPointer
let buf: UnsafeMutableBufferPointer<Float> = UnsafeMutableBufferPointer(buffer)
buf[frame] = Float(value)
return noErr
let format = engine.outputNode.inputFormat(forBus: 0)
let stimulusFormat = AVAudioFormat(commonFormat: format.commonFormat,
sampleRate: Double(sampleRate),
channels: 1,
interleaved: format.isInterleaved)
do
try AVAudioSession.sharedInstance().setCategory(.playAndRecord)
let ioBufferDuration = 128.0 / 44100.0
try AVAudioSession.sharedInstance().setPreferredIOBufferDuration(ioBufferDuration)
catch
assertionFailure("AVAudioSession setup failed")
let input = engine.inputNode
let inputFormat = input.inputFormat(forBus: 0)
print("InputNode Format is \(inputFormat)")
engine.attach(srcNode)
engine.connect(srcNode, to: engine.mainMixerNode, format: stimulusFormat)
if internalRefLoop == true
srcNode.installTap(onBus: 0, bufferSize: 1024, format: stimulusFormat, block: (buffer: AVAudioPCMBuffer!, time: AVAudioTime!) -> Void in
if self.in2firstRun == true
var info = mach_timebase_info()
mach_timebase_info(&info)
let currentTime = mach_absolute_time()
let nanos = currentTime * UInt64(info.numer) / UInt64(info.denom)
self.in2startTime = Int(nanos)
self.in2firstRun = false
do
let floatData = buffer.floatChannelData?.pointee
for frame in 0..<buffer.frameLength
if (self.buf2current + Int(frame)) < totalRecordSize
self.in2Buf[self.buf2current + Int(frame)] = floatData![Int(frame)]
self.buf2current += Int(buffer.frameLength)
if (self.numberOfSamples + Int(buffer.frameLength)) <= totalRecordSize
try self.stimulusFile.write(from: buffer)
self.numberOfSamples += Int(buffer.frameLength) else
self.engine.stop()
self.running = false
catch
print(NSString(string: "write failed"))
)
let micAudioConverter = AVAudioConverter(from: inputFormat, to: stimulusFormat!)
var micChannelMap:[NSNumber] = [0,-1]
micAudioConverter?.channelMap = micChannelMap
let refAudioConverter = AVAudioConverter(from: inputFormat, to: stimulusFormat!)
var refChannelMap:[NSNumber] = [1,-1]
refAudioConverter?.channelMap = refChannelMap
//Measurement Tap
engine.inputNode.installTap(onBus: 0, bufferSize: 1024, format: inputFormat, block: (buffer2: AVAudioPCMBuffer!, time: AVAudioTime!) -> Void in
//print(NSString(string:"writing"))
if self.in1firstRun == true
var info = mach_timebase_info()
mach_timebase_info(&info)
let currentTime = mach_absolute_time()
let nanos = currentTime * UInt64(info.numer) / UInt64(info.denom)
self.in1StartTime = Int(nanos)
self.in1firstRun = false
do
let micConvertedBuffer = AVAudioPCMBuffer(pcmFormat: stimulusFormat!, frameCapacity: buffer2.frameCapacity)
let micInputBlock: AVAudioConverterInputBlock = inNumPackets, outStatus in
outStatus.pointee = AVAudioConverterInputStatus.haveData
return buffer2
var error: NSError? = nil
//let status = audioConverter.convert(to: convertedBuffer!, error: &error, withInputFrom: inputBlock)
let status = micAudioConverter?.convert(to: micConvertedBuffer!, error: &error, withInputFrom: micInputBlock)
//print(status)
let floatData = micConvertedBuffer?.floatChannelData?.pointee
for frame in 0..<micConvertedBuffer!.frameLength
if (self.buf1current + Int(frame)) < totalRecordSize
self.in1Buf[self.buf1current + Int(frame)] = floatData![Int(frame)]
if (self.buf1current + Int(frame)) >= totalRecordSize
self.engine.stop()
self.running = false
self.buf1current += Int(micConvertedBuffer!.frameLength)
try self.measurementFile.write(from: micConvertedBuffer!)
catch
print(NSString(string: "write failed"))
if internalRefLoop == false
if self.in2firstRun == true
var info = mach_timebase_info()
mach_timebase_info(&info)
let currentTime = mach_absolute_time()
let nanos = currentTime * UInt64(info.numer) / UInt64(info.denom)
self.in2startTime = Int(nanos)
self.in2firstRun = false
do
let refConvertedBuffer = AVAudioPCMBuffer(pcmFormat: stimulusFormat!, frameCapacity: buffer2.frameCapacity)
let refInputBlock: AVAudioConverterInputBlock = inNumPackets, outStatus in
outStatus.pointee = AVAudioConverterInputStatus.haveData
return buffer2
var error: NSError? = nil
let status = refAudioConverter?.convert(to: refConvertedBuffer!, error: &error, withInputFrom: refInputBlock)
//print(status)
let floatData = refConvertedBuffer?.floatChannelData?.pointee
for frame in 0..<refConvertedBuffer!.frameLength
if (self.buf2current + Int(frame)) < totalRecordSize
self.in2Buf[self.buf2current + Int(frame)] = floatData![Int(frame)]
if (self.numberOfSamples + Int(buffer2.frameLength)) <= totalRecordSize
self.buf2current += Int(refConvertedBuffer!.frameLength)
try self.stimulusFile.write(from: refConvertedBuffer!) else
self.engine.stop()
self.running = false
catch
print(NSString(string: "write failed"))
)
assert(engine.inputNode != nil)
running = true
try! engine.start()
所以上面的方法是我的整个班级。目前 installTap 上的每个缓冲区调用都将输入直接写入 WAV 文件。这就是我每次都可以看到两个最终结果不同的地方。我尝试添加 startTime 变量并减去两者，但结果仍然不同。
我是否需要考虑到我的输出也会有可能因每次调用而异的延迟？如果是这样，我如何将这个时间添加到等式中？我正在寻找的是两个输入和输出都具有相对时间，以便我可以比较它们。只要我能确定结束通话时间，不同的硬件延迟不会有太大影响。
【问题讨论】：
【参考方案1】：如果您正在进行实时测量，您可能希望使用AVAudioSinkNode 而不是 Tap。 Sink 节点是新的，并与您正在使用的 AVAudioSourceNode 一起引入。安装 Tap 后，您将无法获得精确的计时。
【讨论】：
以上是关于用于音频测量的 Swift AVFoundation 计时信息的主要内容，如果未能解决你的问题，请参考以下文章
Swift 4 AVFoundation - 同时录制多个音频源