【问题标题】:Decode AAC to PCM format using AVAudioConverter Swift使用 AVAudioConverter Swift 将 AAC 解码为 PCM 格式
【发布时间】:2018-12-23 21:37:36
【问题描述】:

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 缓冲区进行编码和解码,显示了编码示例,但没有显示解码示例。 我尝试解码,但有些东西不起作用。我不知道是什么:(

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

【问题讨论】:

  • 可变数据的维度是多少?我只是在想,如果您将立体声音频文件传递给解析器,那么您的 PCMFormat() 函数将失败,因为它将尝试仅返回一个通道。
  • @matiasofteby 当然是单声道! :)

标签: ios avfoundation aac avaudiopcmbuffer avaudioconverter


【解决方案1】:

您的尝试存在一些问题:

  1. 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 数据包的大小是可变的。您可以从原始 AAC 缓冲区复制它们,也可以手动(哎哟)或使用 AudioFileStream api 从数据中解析它们。

  2. 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 编码器出于个人原因需要添加 2112 帧的静音,然后它才能开始重现您的音频,因此重新创建转换器会让您获得很多静音。

  3. 您一遍又一遍地向AVAudioConverter 的输入块提供相同的缓冲区。每个缓冲区只应显示一次。

  4. 32000 的比特率不起作用(对我来说)

这就是我现在能想到的。尝试对您的代码进行以下修改,而不是现在这样调用:

(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的是立体声 - 你可能需要把它改回来)

(pps 显然这里正在进行某种往返/序列化/反序列化尝试,但你到底想做什么?你想将 AAC 音频从一个设备流式传输到另一个设备吗?因为它可能更容易让另一个 API,如 AVPlayer 播放生成的流,而不是自己处理数据包)

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 { $0.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)")
    }
}

【讨论】:

  • 嗨!感谢您的关注和您的回答!它用于从设备到设备的流式音频, - AVPlayer 和 FileStreamApi 对这种情况没有帮助。我找到了上面代码的解决方案和主要问题:压缩缓冲区和 pcm 缓冲区的设置不兼容。此外,您是对的,压缩缓冲区的包大小不正确。比特率 32000 可以工作,但在我的情况下是单声道。为什么在您的代码中不起作用..嗯..很奇怪。转换器有一个可用比特率的属性,也许缓冲区的设置会获得其他可用的比特率。稍后我将分享我的代码和描述。
  • 在您的代码中,我看到压缩缓冲区的大小不正确。缓冲区会比原始 PCM 缓冲区大 - 这不好:)
  • 我猜 32000 不起作用,因为我使用的是立体声麦克风。糟糕,是的,缓冲区大小并没有那么大,我已将其改回您最初估计的 8*768。
  • 认为没关系,尽管我上周遇到了这段代码并认为 . maximumPacketSize 不应该是常数,应该是 lpcmToAACAudioConverter.maximumOutputPacketSize
  • AACDecoder.cpp:189:Deserialize: 输入缓冲区中的位太少的修复方法是什么?随机出现。
猜你喜欢
  • 1970-01-01
  • 2013-02-02
  • 2012-04-18
  • 1970-01-01
  • 1970-01-01
  • 2014-03-15
  • 2021-08-02
  • 2010-11-18
  • 2019-06-27
相关资源
最近更新 更多