使用 AVAudioConverter 将 AAC 解码为 PCM 格式 Swift
Decode AAC to PCM format using AVAudioConverter Swift
如何在 Swift 上使用 AVAudioConverter、AVAudioCompressedBuffer 和 AVAudioPCMBuffer 将 AAC 转换为 PCM？
在WWDC 2015上，507 Session说，AVAudioConverter可以对PCM buffer进行编码和解码，展示了编码示例，但没有展示解码示例。
我试过解码，但有些东西不起作用。我不知道什么:(
来电：
//buffer - it's AVAudioPCMBuffer from AVAudioInputNode(AVAudioEngine)
let aacBuffer = AudioBufferConverter.convertToAAC(from: buffer, error: nil) //has data
let data = Data(bytes: aacBuffer!.data, count: Int(aacBuffer!.byteLength)) //has data
let aacReverseBuffer = AudioBufferConverter.convertToAAC(from: data) //has data
let pcmReverseBuffer = AudioBufferConverter.convertToPCM(from: aacBuffer2!, error: nil) //zeros data. data object exist, but filled by zeros
转换代码：
class AudioBufferFormatHelper {
static func PCMFormat() -> AVAudioFormat? {
return AVAudioFormat(commonFormat: .pcmFormatFloat32, sampleRate: 44100, channels: 1, interleaved: false)
}
static func AACFormat() -> AVAudioFormat? {
var outDesc = AudioStreamBasicDescription(
mSampleRate: 44100,
mFormatID: kAudioFormatMPEG4AAC,
mFormatFlags: 0,
mBytesPerPacket: 0,
mFramesPerPacket: 0,
mBytesPerFrame: 0,
mChannelsPerFrame: 1,
mBitsPerChannel: 0,
mReserved: 0)
let outFormat = AVAudioFormat(streamDescription: &outDesc)
return outFormat
}
}
class AudioBufferConverter {
static func convertToAAC(from buffer: AVAudioBuffer, error outError: NSErrorPointer) -> AVAudioCompressedBuffer? {
let outputFormat = AudioBufferFormatHelper.AACFormat()
let outBuffer = AVAudioCompressedBuffer(format: outputFormat!, packetCapacity: 8, maximumPacketSize: 768)
self.convert(from: buffer, to: outBuffer, error: outError)
return outBuffer
}
static func convertToPCM(from buffer: AVAudioBuffer, error outError: NSErrorPointer) -> AVAudioPCMBuffer? {
let outputFormat = AudioBufferFormatHelper.PCMFormat()
guard let outBuffer = AVAudioPCMBuffer(pcmFormat: outputFormat!, frameCapacity: 4410) else {
return nil
}
outBuffer.frameLength = 4410
self.convert(from: buffer, to: outBuffer, error: outError)
return outBuffer
}
static func convertToAAC(from data: Data) -> AVAudioCompressedBuffer? {
let nsData = NSData(data: data)
let inputFormat = AudioBufferFormatHelper.AACFormat()
let buffer = AVAudioCompressedBuffer(format: inputFormat!, packetCapacity: 8, maximumPacketSize: 768)
buffer.byteLength = UInt32(data.count)
buffer.packetCount = 8
buffer.data.copyMemory(from: nsData.bytes, byteCount: nsData.length)
buffer.packetDescriptions!.pointee.mDataByteSize = 4
return buffer
}
private static func convert(from sourceBuffer: AVAudioBuffer, to destinationBuffer: AVAudioBuffer, error outError: NSErrorPointer) {
//init converter
let inputFormat = sourceBuffer.format
let outputFormat = destinationBuffer.format
let converter = AVAudioConverter(from: inputFormat, to: outputFormat)
converter!.bitRate = 32000
let inputBlock : AVAudioConverterInputBlock = { inNumPackets, outStatus in
outStatus.pointee = AVAudioConverterInputStatus.haveData
return sourceBuffer
}
_ = converter!.convert(to: destinationBuffer, error: outError, withInputFrom: inputBlock)
}
}
结果 AVAudioPCMBuffer 的数据为零。
在消息中我看到错误：
AACDecoder.cpp:192:Deserialize: Unmatched number of channel elements in payload
AACDecoder.cpp:220:DecodeFrame: Error deserializing packet
[ac] ACMP4AACBaseDecoder.cpp:1337:ProduceOutputBufferList: (0x14f81b840) Error decoding packet 1: err = -1, packet length: 0
AACDecoder.cpp:192:Deserialize: Unmatched number of channel elements in payload
AACDecoder.cpp:220:DecodeFrame: Error deserializing packet
[ac] ACMP4AACBaseDecoder.cpp:1337:ProduceOutputBufferList: (0x14f81b840) Error decoding packet 3: err = -1, packet length: 0
AACDecoder.cpp:192:Deserialize: Unmatched number of channel elements in payload
AACDecoder.cpp:220:DecodeFrame: Error deserializing packet
[ac] ACMP4AACBaseDecoder.cpp:1337:ProduceOutputBufferList: (0x14f81b840) Error decoding packet 5: err = -1, packet length: 0
AACDecoder.cpp:192:Deserialize: Unmatched number of channel elements in payload
AACDecoder.cpp:220:DecodeFrame: Error deserializing packet
[ac] ACMP4AACBaseDecoder.cpp:1337:ProduceOutputBufferList: (0x14f81b840) Error decoding packet 7: err = -1, packet length: 0
您的尝试存在一些问题：
您在转换数据时没有设置 多个 数据包描述 -> AVAudioCompressedBuffer。您需要创建它们，因为 AAC 数据包的大小可变。您可以从原始 AAC 缓冲区复制它们，或者手动（哎哟）或使用 AudioFileStream api.
你一遍又一遍地重新创建你的 AVAudioConverters - 每个缓冲区一次，丢弃它们的状态。例如AAC 编码器出于其自身原因需要添加 2112 帧静音才能重现您的音频，因此重新创建转换器会让您完全静音。
你一遍又一遍地向 AVAudioConverter 的输入块呈现相同的缓冲区。您应该只显示每个缓冲区一次。
32000 的比特率不工作（对我来说）
我现在能想到的就是这些了。尝试对您的代码进行以下修改，而不是您现在这样调用：
(p.s。我将一些单声道更改为立体声，这样我就可以在我的 mac 上播放往返缓冲区，它的麦克风输入奇怪地是立体声 - 你可能需要将其改回)
(p.p.s 显然这里正在进行某种往返/serialising/deserialising 尝试，但你到底想做什么？你想从一台设备流式传输 AAC 音频到另一个？因为让另一个 API 如 AVPlayer 播放结果流而不是自己处理数据包可能更容易）
let aacBuffer = AudioBufferConverter.convertToAAC(from: buffer, error: nil)!
let data = Data(bytes: aacBuffer.data, count: Int(aacBuffer.byteLength))
let packetDescriptions = Array(UnsafeBufferPointer(start: aacBuffer.packetDescriptions, count: Int(aacBuffer.packetCount)))
let aacReverseBuffer = AudioBufferConverter.convertToAAC(from: data, packetDescriptions: packetDescriptions)!
// was aacBuffer2
let pcmReverseBuffer = AudioBufferConverter.convertToPCM(from: aacReverseBuffer, error: nil)
class AudioBufferFormatHelper {
static func PCMFormat() -> AVAudioFormat? {
return AVAudioFormat(commonFormat: .pcmFormatFloat32, sampleRate: 44100, channels: 1, interleaved: false)
}
static func AACFormat() -> AVAudioFormat? {
var outDesc = AudioStreamBasicDescription(
mSampleRate: 44100,
mFormatID: kAudioFormatMPEG4AAC,
mFormatFlags: 0,
mBytesPerPacket: 0,
mFramesPerPacket: 0,
mBytesPerFrame: 0,
mChannelsPerFrame: 1,
mBitsPerChannel: 0,
mReserved: 0)
let outFormat = AVAudioFormat(streamDescription: &outDesc)
return outFormat
}
}
class AudioBufferConverter {
static var lpcmToAACConverter: AVAudioConverter! = nil
static func convertToAAC(from buffer: AVAudioBuffer, error outError: NSErrorPointer) -> AVAudioCompressedBuffer? {
let outputFormat = AudioBufferFormatHelper.AACFormat()
let outBuffer = AVAudioCompressedBuffer(format: outputFormat!, packetCapacity: 8, maximumPacketSize: 768)
//init converter once
if lpcmToAACConverter == nil {
let inputFormat = buffer.format
lpcmToAACConverter = AVAudioConverter(from: inputFormat, to: outputFormat!)
// print("available rates \(lpcmToAACConverter.applicableEncodeBitRates)")
// lpcmToAACConverter!.bitRate = 96000
lpcmToAACConverter.bitRate = 32000 // have end of stream problems with this, not sure why
}
self.convert(withConverter:lpcmToAACConverter, from: buffer, to: outBuffer, error: outError)
return outBuffer
}
static var aacToLPCMConverter: AVAudioConverter! = nil
static func convertToPCM(from buffer: AVAudioBuffer, error outError: NSErrorPointer) -> AVAudioPCMBuffer? {
let outputFormat = AudioBufferFormatHelper.PCMFormat()
guard let outBuffer = AVAudioPCMBuffer(pcmFormat: outputFormat!, frameCapacity: 4410) else {
return nil
}
//init converter once
if aacToLPCMConverter == nil {
let inputFormat = buffer.format
aacToLPCMConverter = AVAudioConverter(from: inputFormat, to: outputFormat!)
}
self.convert(withConverter: aacToLPCMConverter, from: buffer, to: outBuffer, error: outError)
return outBuffer
}
static func convertToAAC(from data: Data, packetDescriptions: [AudioStreamPacketDescription]) -> AVAudioCompressedBuffer? {
let nsData = NSData(data: data)
let inputFormat = AudioBufferFormatHelper.AACFormat()
let maximumPacketSize = packetDescriptions.map { [=10=].mDataByteSize }.max()!
let buffer = AVAudioCompressedBuffer(format: inputFormat!, packetCapacity: AVAudioPacketCount(packetDescriptions.count), maximumPacketSize: Int(maximumPacketSize))
buffer.byteLength = UInt32(data.count)
buffer.packetCount = AVAudioPacketCount(packetDescriptions.count)
buffer.data.copyMemory(from: nsData.bytes, byteCount: nsData.length)
buffer.packetDescriptions!.pointee.mDataByteSize = UInt32(data.count)
buffer.packetDescriptions!.initialize(from: packetDescriptions, count: packetDescriptions.count)
return buffer
}
private static func convert(withConverter: AVAudioConverter, from sourceBuffer: AVAudioBuffer, to destinationBuffer: AVAudioBuffer, error outError: NSErrorPointer) {
// input each buffer only once
var newBufferAvailable = true
let inputBlock : AVAudioConverterInputBlock = {
inNumPackets, outStatus in
if newBufferAvailable {
outStatus.pointee = .haveData
newBufferAvailable = false
return sourceBuffer
} else {
outStatus.pointee = .noDataNow
return nil
}
}
let status = withConverter.convert(to: destinationBuffer, error: outError, withInputFrom: inputBlock)
print("status: \(status.rawValue)")
}
}
如何在 Swift 上使用 AVAudioConverter、AVAudioCompressedBuffer 和 AVAudioPCMBuffer 将 AAC 转换为 PCM？
在WWDC 2015上，507 Session说，AVAudioConverter可以对PCM buffer进行编码和解码，展示了编码示例，但没有展示解码示例。 我试过解码，但有些东西不起作用。我不知道什么:(
来电：
//buffer - it's AVAudioPCMBuffer from AVAudioInputNode(AVAudioEngine)
let aacBuffer = AudioBufferConverter.convertToAAC(from: buffer, error: nil) //has data
let data = Data(bytes: aacBuffer!.data, count: Int(aacBuffer!.byteLength)) //has data
let aacReverseBuffer = AudioBufferConverter.convertToAAC(from: data) //has data
let pcmReverseBuffer = AudioBufferConverter.convertToPCM(from: aacBuffer2!, error: nil) //zeros data. data object exist, but filled by zeros
转换代码：
class AudioBufferFormatHelper {
static func PCMFormat() -> AVAudioFormat? {
return AVAudioFormat(commonFormat: .pcmFormatFloat32, sampleRate: 44100, channels: 1, interleaved: false)
}
static func AACFormat() -> AVAudioFormat? {
var outDesc = AudioStreamBasicDescription(
mSampleRate: 44100,
mFormatID: kAudioFormatMPEG4AAC,
mFormatFlags: 0,
mBytesPerPacket: 0,
mFramesPerPacket: 0,
mBytesPerFrame: 0,
mChannelsPerFrame: 1,
mBitsPerChannel: 0,
mReserved: 0)
let outFormat = AVAudioFormat(streamDescription: &outDesc)
return outFormat
}
}
class AudioBufferConverter {
static func convertToAAC(from buffer: AVAudioBuffer, error outError: NSErrorPointer) -> AVAudioCompressedBuffer? {
let outputFormat = AudioBufferFormatHelper.AACFormat()
let outBuffer = AVAudioCompressedBuffer(format: outputFormat!, packetCapacity: 8, maximumPacketSize: 768)
self.convert(from: buffer, to: outBuffer, error: outError)
return outBuffer
}
static func convertToPCM(from buffer: AVAudioBuffer, error outError: NSErrorPointer) -> AVAudioPCMBuffer? {
let outputFormat = AudioBufferFormatHelper.PCMFormat()
guard let outBuffer = AVAudioPCMBuffer(pcmFormat: outputFormat!, frameCapacity: 4410) else {
return nil
}
outBuffer.frameLength = 4410
self.convert(from: buffer, to: outBuffer, error: outError)
return outBuffer
}
static func convertToAAC(from data: Data) -> AVAudioCompressedBuffer? {
let nsData = NSData(data: data)
let inputFormat = AudioBufferFormatHelper.AACFormat()
let buffer = AVAudioCompressedBuffer(format: inputFormat!, packetCapacity: 8, maximumPacketSize: 768)
buffer.byteLength = UInt32(data.count)
buffer.packetCount = 8
buffer.data.copyMemory(from: nsData.bytes, byteCount: nsData.length)
buffer.packetDescriptions!.pointee.mDataByteSize = 4
return buffer
}
private static func convert(from sourceBuffer: AVAudioBuffer, to destinationBuffer: AVAudioBuffer, error outError: NSErrorPointer) {
//init converter
let inputFormat = sourceBuffer.format
let outputFormat = destinationBuffer.format
let converter = AVAudioConverter(from: inputFormat, to: outputFormat)
converter!.bitRate = 32000
let inputBlock : AVAudioConverterInputBlock = { inNumPackets, outStatus in
outStatus.pointee = AVAudioConverterInputStatus.haveData
return sourceBuffer
}
_ = converter!.convert(to: destinationBuffer, error: outError, withInputFrom: inputBlock)
}
}
结果 AVAudioPCMBuffer 的数据为零。 在消息中我看到错误：
AACDecoder.cpp:192:Deserialize: Unmatched number of channel elements in payload
AACDecoder.cpp:220:DecodeFrame: Error deserializing packet
[ac] ACMP4AACBaseDecoder.cpp:1337:ProduceOutputBufferList: (0x14f81b840) Error decoding packet 1: err = -1, packet length: 0
AACDecoder.cpp:192:Deserialize: Unmatched number of channel elements in payload
AACDecoder.cpp:220:DecodeFrame: Error deserializing packet
[ac] ACMP4AACBaseDecoder.cpp:1337:ProduceOutputBufferList: (0x14f81b840) Error decoding packet 3: err = -1, packet length: 0
AACDecoder.cpp:192:Deserialize: Unmatched number of channel elements in payload
AACDecoder.cpp:220:DecodeFrame: Error deserializing packet
[ac] ACMP4AACBaseDecoder.cpp:1337:ProduceOutputBufferList: (0x14f81b840) Error decoding packet 5: err = -1, packet length: 0
AACDecoder.cpp:192:Deserialize: Unmatched number of channel elements in payload
AACDecoder.cpp:220:DecodeFrame: Error deserializing packet
[ac] ACMP4AACBaseDecoder.cpp:1337:ProduceOutputBufferList: (0x14f81b840) Error decoding packet 7: err = -1, packet length: 0
您的尝试存在一些问题：
您在转换数据时没有设置 多个 数据包描述 ->
AVAudioCompressedBuffer。您需要创建它们，因为 AAC 数据包的大小可变。您可以从原始 AAC 缓冲区复制它们，或者手动（哎哟）或使用AudioFileStreamapi. 从您的数据中解析它们
你一遍又一遍地重新创建你的
AVAudioConverters - 每个缓冲区一次，丢弃它们的状态。例如AAC 编码器出于其自身原因需要添加 2112 帧静音才能重现您的音频，因此重新创建转换器会让您完全静音。你一遍又一遍地向
AVAudioConverter的输入块呈现相同的缓冲区。您应该只显示每个缓冲区一次。32000 的比特率不工作（对我来说）
我现在能想到的就是这些了。尝试对您的代码进行以下修改，而不是您现在这样调用：
(p.s。我将一些单声道更改为立体声，这样我就可以在我的 mac 上播放往返缓冲区，它的麦克风输入奇怪地是立体声 - 你可能需要将其改回)
(p.p.s 显然这里正在进行某种往返/serialising/deserialising 尝试，但你到底想做什么？你想从一台设备流式传输 AAC 音频到另一个？因为让另一个 API 如 AVPlayer 播放结果流而不是自己处理数据包可能更容易）
let aacBuffer = AudioBufferConverter.convertToAAC(from: buffer, error: nil)!
let data = Data(bytes: aacBuffer.data, count: Int(aacBuffer.byteLength))
let packetDescriptions = Array(UnsafeBufferPointer(start: aacBuffer.packetDescriptions, count: Int(aacBuffer.packetCount)))
let aacReverseBuffer = AudioBufferConverter.convertToAAC(from: data, packetDescriptions: packetDescriptions)!
// was aacBuffer2
let pcmReverseBuffer = AudioBufferConverter.convertToPCM(from: aacReverseBuffer, error: nil)
class AudioBufferFormatHelper {
static func PCMFormat() -> AVAudioFormat? {
return AVAudioFormat(commonFormat: .pcmFormatFloat32, sampleRate: 44100, channels: 1, interleaved: false)
}
static func AACFormat() -> AVAudioFormat? {
var outDesc = AudioStreamBasicDescription(
mSampleRate: 44100,
mFormatID: kAudioFormatMPEG4AAC,
mFormatFlags: 0,
mBytesPerPacket: 0,
mFramesPerPacket: 0,
mBytesPerFrame: 0,
mChannelsPerFrame: 1,
mBitsPerChannel: 0,
mReserved: 0)
let outFormat = AVAudioFormat(streamDescription: &outDesc)
return outFormat
}
}
class AudioBufferConverter {
static var lpcmToAACConverter: AVAudioConverter! = nil
static func convertToAAC(from buffer: AVAudioBuffer, error outError: NSErrorPointer) -> AVAudioCompressedBuffer? {
let outputFormat = AudioBufferFormatHelper.AACFormat()
let outBuffer = AVAudioCompressedBuffer(format: outputFormat!, packetCapacity: 8, maximumPacketSize: 768)
//init converter once
if lpcmToAACConverter == nil {
let inputFormat = buffer.format
lpcmToAACConverter = AVAudioConverter(from: inputFormat, to: outputFormat!)
// print("available rates \(lpcmToAACConverter.applicableEncodeBitRates)")
// lpcmToAACConverter!.bitRate = 96000
lpcmToAACConverter.bitRate = 32000 // have end of stream problems with this, not sure why
}
self.convert(withConverter:lpcmToAACConverter, from: buffer, to: outBuffer, error: outError)
return outBuffer
}
static var aacToLPCMConverter: AVAudioConverter! = nil
static func convertToPCM(from buffer: AVAudioBuffer, error outError: NSErrorPointer) -> AVAudioPCMBuffer? {
let outputFormat = AudioBufferFormatHelper.PCMFormat()
guard let outBuffer = AVAudioPCMBuffer(pcmFormat: outputFormat!, frameCapacity: 4410) else {
return nil
}
//init converter once
if aacToLPCMConverter == nil {
let inputFormat = buffer.format
aacToLPCMConverter = AVAudioConverter(from: inputFormat, to: outputFormat!)
}
self.convert(withConverter: aacToLPCMConverter, from: buffer, to: outBuffer, error: outError)
return outBuffer
}
static func convertToAAC(from data: Data, packetDescriptions: [AudioStreamPacketDescription]) -> AVAudioCompressedBuffer? {
let nsData = NSData(data: data)
let inputFormat = AudioBufferFormatHelper.AACFormat()
let maximumPacketSize = packetDescriptions.map { [=10=].mDataByteSize }.max()!
let buffer = AVAudioCompressedBuffer(format: inputFormat!, packetCapacity: AVAudioPacketCount(packetDescriptions.count), maximumPacketSize: Int(maximumPacketSize))
buffer.byteLength = UInt32(data.count)
buffer.packetCount = AVAudioPacketCount(packetDescriptions.count)
buffer.data.copyMemory(from: nsData.bytes, byteCount: nsData.length)
buffer.packetDescriptions!.pointee.mDataByteSize = UInt32(data.count)
buffer.packetDescriptions!.initialize(from: packetDescriptions, count: packetDescriptions.count)
return buffer
}
private static func convert(withConverter: AVAudioConverter, from sourceBuffer: AVAudioBuffer, to destinationBuffer: AVAudioBuffer, error outError: NSErrorPointer) {
// input each buffer only once
var newBufferAvailable = true
let inputBlock : AVAudioConverterInputBlock = {
inNumPackets, outStatus in
if newBufferAvailable {
outStatus.pointee = .haveData
newBufferAvailable = false
return sourceBuffer
} else {
outStatus.pointee = .noDataNow
return nil
}
}
let status = withConverter.convert(to: destinationBuffer, error: outError, withInputFrom: inputBlock)
print("status: \(status.rawValue)")
}
}