使用AVAudioConverter Swift将AAC解码为PCM格式

16

如何使用AVAudioConverter、AVAudioCompressedBuffer和AVAudioPCMBuffer在Swift上将AAC转换为PCM?

在2015年的WWDC 507会议上,宣布AVAudioConverter可以对PCM缓冲区进行编码和解码,展示了编码示例,但没有展示解码示例。我尝试着解码,但是好像有些问题,我不知道是什么原因:(

调用:

//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

这是用于转换的代码:

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)
    }
}

AVAudioPCMBuffer的结果数据中包含零。 而且我在消息中看到了错误:

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

变量数据的维度是什么?我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。 - matiastofteby
当然是 Mono! :) - Vladimir Prigarin
1个回答

10
您的尝试存在一些问题:
1. 在将数据转换为AVAudioCompressedBuffer时,您未设置多个数据包描述。您需要创建它们,因为AAC数据包大小是可变的。您可以从原始AAC缓冲区中复制它们,或通过手动解析数据(痛苦)或使用AudioFileStream api来解析它们。
2. 您一遍又一遍地重新创建AVAudioConverter,每个缓冲区都会丢弃它们的状态。例如,AAC编码器出于自己的原因需要在开始重现音频之前添加2112帧的静音,因此重新创建转换器会使您得到大量的静音。
3. 您一遍又一遍地向AVAudioConverter的输入块呈现相同的缓冲区。您应该只呈现每个缓冲区一次。
4. 32000比特率不起作用(对我来说)
这就是我现在能想到的全部内容。请尝试以下修改您的代码,并像这样调用它:
(附言:我将一些单声道更改为立体声,以便可以在我的Mac上播放往返缓冲区,其麦克风输入奇怪地是立体声-您可能需要将其改回)
(附言2:显然正在进行某种往返/串行化/反序列化尝试,但您到底想做什么?您想将AAC音频从一个设备流式传输到另一个设备吗?因为使用像AVPlayer这样的其他API播放生成的流可能比自己处理数据包更容易)
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 { $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)")
    }
}

1
你好!感谢您的关注和回答!这是用于从设备流式传输音频的,AVPlayer 和 FileStreamApi 在这种情况下不会有帮助。我找到了解决方案并发现了上面代码的主要问题:压缩缓冲区和 PCM 缓冲区的设置不兼容。此外,您是正确的,压缩缓冲区的包大小不正确。比特率 32000 可以工作,但在我的情况下只能使用单声道。为什么您的代码无法工作.. 嗯.. 这很奇怪。转换器具有可用比特率的属性,也许缓冲区设置会获取其他可用比特率。稍后我会分享我的代码和描述。 - Vladimir Prigarin
你能展示一下你是怎么做的吗?也许可以在一个新问题中问一下? - Rhythmic Fistman
你的压缩数据比原始PCM数据小吗?在我的情况下,如果我将比特率设置为92kbps,则压缩缓冲区大于原始缓冲区。如果我将比特率设置为32kbbps,则压缩缓冲区较小,但仅减小约30%。我认为我一定做对了什么,因为如果我将压缩缓冲区流式传输到另一个设备,它确实可以播放。 - Paul
1
我认为这是可以的,尽管我上周遇到了这段代码并认为 maximumPacketSize 不应该是一个常量,而应该是 lpcmToAACAudioConverter.maximumOutputPacketSize - Rhythmic Fistman
1
AACDecoder.cpp:189:Deserialize出现的修复方法是什么?这些错误是随机出现的。 - Bhuvanendra Pratap Maurya
显示剩余11条评论

网页内容由stack overflow 提供, 点击上面的
可以查看英文原文,
原文链接