我有一个MacOS Swift应用程序，可以处理从麦克风录制的音频数据。麦克风具有立体声功能，但我只能录制单声道数据。
在下面的代码中，如果我let alwaysMono = true，func setup()报告 Activity 格式为立体声，但将其覆盖为单声道。一切都与单声道输入流一起工作。
如果我let alwaysMono = false，setup()将nChannels设置为2。但是captureOutput不会获取任何数据。从UnsafeMutableAudioBufferListPointer返回的AudioBuffer始终具有nil mData。如果我不检查nil mData，程序将崩溃。
如何获得完整的立体声输入？
编辑:在captureOutput中，CMSampleBufferGetAudioBufferListWithRetainedBlockBuffer返回错误代码-12737，它对应于kCMSampleBufferError_ArrayTooSmall。我已经检查了传递给captureOutput的sampleBuffer arg，但看不到任何明显的错误。但是我不知道要寻找什么。
另一个编辑:我使用内置的单声道麦克风对代码进行了测试，令我惊讶的是它还认为它是立体声的，这表明我获取和使用AVCaptureDevice.activeFormat的方式显然存在问题。我不知道从这里去哪里。
class Recorder: NSObject, AVCaptureAudioDataOutputSampleBufferDelegate {
let alwaysMono = false
var nChannels:UInt32 = 1
let session : AVCaptureSession!
static let realTimeQueue = DispatchQueue(label: "com.myapp.realtime",
qos: DispatchQoS( qosClass:DispatchQoS.QoSClass.userInitiated, relativePriority: 0 ))
override init() {
session = AVCaptureSession()
super.init()
}
static var recorder:Recorder?
static func record() ->Bool {
if recorder == nil {
recorder = Recorder()
if !recorder!.setup(callback:record) {
recorder = nil
return false
}
}
realTimeQueue.async {
if !recorder!.session.isRunning {
recorder!.session.startRunning()
}
}
return true
}
static func pause() {
recorder!.session.stopRunning()
}
func setup( callback:@escaping (()->Bool)) -> Bool {
let device = AVCaptureDevice.default( for: AVMediaType.audio )
if device == nil { return false }
if let format = Recorder.getActiveFormat() {
nChannels = format.mChannelLayoutTag == kAudioChannelLayoutTag_Stereo ? 2 : 1
print("active format is \((nChannels==2) ? "Stereo" : "Mono")")
if alwaysMono {
print( "Overriding to mono" )
nChannels = 1
}
}
if #available(OSX 10.14, *) {
let status = AVCaptureDevice.authorizationStatus( for:AVMediaType.audio )
if status == .notDetermined {
AVCaptureDevice.requestAccess(for: AVMediaType.audio ){ granted in
_ = callback()
}
return false
} else if status != .authorized {
return false
}
}
var input : AVCaptureDeviceInput
do {
try device!.lockForConfiguration()
try input = AVCaptureDeviceInput( device: device! )
device!.unlockForConfiguration()
} catch {
device!.unlockForConfiguration()
return false
}
let output = AVCaptureAudioDataOutput()
output.setSampleBufferDelegate(self, queue: Intonia.realTimeQueue)
let settings = [
AVFormatIDKey: kAudioFormatLinearPCM,
AVNumberOfChannelsKey : nChannels,
AVSampleRateKey : 44100,
AVLinearPCMBitDepthKey : 16,
AVLinearPCMIsFloatKey : false
] as [String : Any]
output.audioSettings = settings
session.beginConfiguration()
if !session.canAddInput( input ) {
return false
}
session.addInput( input )
if !session.canAddOutput( output ) {
return false
}
session.addOutput( output )
session.commitConfiguration()
return true
}
func getActiveFormat() -> AudioFormatListItem? {
if #available(OSX 10.15, *) {
let device = AVCaptureDevice.default( for: AVMediaType.audio )
if device == nil { return nil }
let list = device!.activeFormat.formatDescription.audioFormatList
if list.count < 1 { return nil }
return list[0]
}
return nil
}
func captureOutput(_ captureOutput: AVCaptureOutput,
didOutput sampleBuffer: CMSampleBuffer,
from connection: AVCaptureConnection){
var buffer: CMBlockBuffer? = nil
var audioBufferList = AudioBufferList(
mNumberBuffers: 1,
mBuffers: AudioBuffer(mNumberChannels: nChannels, mDataByteSize: 0, mData: nil)
)
CMSampleBufferGetAudioBufferListWithRetainedBlockBuffer(
sampleBuffer,
bufferListSizeNeededOut: nil,
bufferListOut: &audioBufferList,
bufferListSize: MemoryLayout<AudioBufferList>.size,
blockBufferAllocator: nil,
blockBufferMemoryAllocator: nil,
flags: UInt32(kCMSampleBufferFlag_AudioBufferList_Assure16ByteAlignment),
blockBufferOut: &buffer
)
let abl = UnsafeMutableAudioBufferListPointer(&audioBufferList)
for buff in abl {
if buff.mData != nil {
let count = Int(buff.mDataByteSize)/MemoryLayout<Int16>.size
let samples = UnsafeMutablePointer<Int16>(OpaquePointer(buff.mData))
process(samples:samples!, count:count)
} else {
print("No data!")
}
}
}
func process( samples: UnsafeMutablePointer<Int16>, count: Int ) {
let firstValue = samples[0]
print( "\(count) values received, first is \(firstValue)" )
}
}
最佳答案
这是一个有很多问题出在哪里的问题。首先，这取决于您使用的麦克风。是Mac上的一台吗？如果是这样，那么通常是单声道。但是，您可以使自己成为一种变通办法，以测试它是否有效，并且不依赖于always:bool。尝试将其录制两次，使用单声道拍摄第一个 channel ，然后使用第二个 channel 进行第二次录制，并使用不同的“加倍”代码进行录制。
我看到的第二件事可能是在设置功能中显式键入立体声 channel ，以确保它获取其2个 channel ，并始终使用带有显式== true或false语句的alwaysMono。看看您是否可以在代码期间同时打印一些 channel 信息，以便您确切地知道哪里出了问题。
关于swift - 捕获立体声音频数据，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/64126896/