带有AVAudioConverterInputBlock的AVAudioConverter在处理后出现音频卡顿

Question

我正在尝试将音频缓冲区转换为不同的格式，并且我使用的是AVAudioConverter。当您具有相同的采样率并且不需要使用AVAudioConverterInputBlock时，AVAudioConverter可以完成这项工作。

但是如果我处理相同的采样率，我的音频数据就会出现奇怪的卡顿。我有一种感觉，我没有很好地处理输入块。输出中有重复两到三次的单词。下面是完整的方法：

func sendAudio(audioFile: URL, completionHandler: @escaping (Bool, Bool, Data?)->Void) {

    createSession(){ sessionUrl, observeURL, session in
        let file = try! AVAudioFile(forReading: audioFile)
        let formatOfAudio = file.processingFormat
        self.engine = AVAudioEngine()
        guard let input = self.engine.inputNode else {
            print("no input")
            return
        }
        //The audio in format in this case is: <AVAudioFormat 0x61800009d010:  2 ch,  44100 Hz, Float32, non-inter>
        let formatIn = formatOfAudio
        let formatOut = AVAudioFormat(commonFormat: .pcmFormatInt16, sampleRate: 16000, channels: 1, interleaved: true)
        let mixer = AVAudioMixerNode()
        self.engine.attach(mixer)
        mixer.volume = 0.0
        self.engine.attach(self.audioPlayerNode)
        self.engine.connect(self.audioPlayerNode, to: mixer, format: formatIn)
        self.engine.connect(input, to: mixer, format: input.outputFormat(forBus: 0))
        self.engine.connect(mixer, to: self.engine.mainMixerNode, format: formatIn)
        let audioConverter = AVAudioConverter(from: formatIn, to: formatOut)
        mixer.installTap(onBus: 0, bufferSize: 32000, format: formatIn, block: {
            (buffer: AVAudioPCMBuffer!, time: AVAudioTime!) -> Void in
                let convertedBuffer = AVAudioPCMBuffer(pcmFormat: formatOut, frameCapacity: buffer.frameCapacity)
                let inputBlock: AVAudioConverterInputBlock = { inNumPackets, outStatus in
                    outStatus.pointee = AVAudioConverterInputStatus.haveData
                    return buffer
                }
                var error: NSError? = nil
                let status = audioConverter.convert(to: convertedBuffer, error: &error, withInputFrom: inputBlock)
                let myData = convertedBuffer.toData()
                completionHandler(true, false, myData)
        })
        self.audioPlayerNode.scheduleFile(file, at: nil){
            self.delayWithSeconds(3.0){
            self.engine.stop()
            mixer.removeTap(onBus: 0)
            completionHandler(true, true, nil)
            }
        }
        do {
            try self.engine.start()
        } catch {
            print(error)
        }
        self.audioPlayerNode.play()
    }
}

有什么想法吗？我从一个Apple slide sample上得到了这段代码

// Create an input block that’s called when converter needs input
let inputBlock : AVAudioConverterInputBlock = {inNumPackets, outStatus in 
    if (<no_data_available>) {   
        outStatus.memory = AVAudioConverterInputStatus.NoDataNow; 
        return nil;  
    } else if (<end_of_stream>) {   
        outStatus.memory = AVAudioConverterInputStatus.EndOfStream; 
        return nil;  
    } else {
        ..outStatus.memory = AVAudioConverterInputStatus.HaveData;   
        return inBuffer; // fill and return input buffer 
    }  
}

Answer 1

对于任何发现这一点的人来说，实际的潜在原因是对AVAudioConverterInputBlock的不正确使用。目标缓冲区容量并不重要，只要它足够大，但是该块将被重复调用，直到目标缓冲区被填满。

如果您的源缓冲区包含ABC，它将用ABCABCABC...填充目标缓冲区。然后，如果你通过管道来实时回放，这些块会被随机截取以适应回放时间，导致这种奇怪的爆裂。

实际的解决方案是，将缓冲区提交到转换器后，将AVAudioConverterInputStatus正确设置为.noDataNow。请注意，返回.endOfStream将永远锁定转换器对象。

var gotData = false
self.converter.convert(to: convertedBuffer, error: nil, withInputFrom: { (_, outStatus) -> AVAudioBuffer? in
    if gotData {
        outStatus.pointee = .noDataNow
        return nil
    }
    gotData = true
    outStatus.pointee = .haveData
    return inputBuffer
})            

Answer 2

所以我相信我已经弄明白了。转换的缓冲器帧容量必须除以被转换的采样率的比率。所以，完整的答案看起来像这样：

func sendAudio(audioFile: URL, completionHandler: @escaping (Bool, Bool, Data?)->Void) {

    createSession(){ sessionUrl, observeURL, session in
        let file = try! AVAudioFile(forReading: audioFile)
        let formatOfAudio = file.processingFormat
        self.engine = AVAudioEngine()
        guard let input = self.engine.inputNode else {
            print("no input")
            return
        }
        //The audio in format in this case is: <AVAudioFormat 0x61800009d010:  2 ch,  44100 Hz, Float32, non-inter>
        let formatIn = formatOfAudio
        let formatOut = AVAudioFormat(commonFormat: .pcmFormatInt16, sampleRate: 16000, channels: 1, interleaved: true)
        let mixer = AVAudioMixerNode()
        self.engine.attach(mixer)
        mixer.volume = 0.0
        self.engine.attach(self.audioPlayerNode)
        self.engine.connect(self.audioPlayerNode, to: mixer, format: formatIn)
        self.engine.connect(input, to: mixer, format: input.outputFormat(forBus: 0))
        self.engine.connect(mixer, to: self.engine.mainMixerNode, format: formatIn)
        let audioConverter = AVAudioConverter(from: formatIn, to: formatOut)
        //Here is where I adjusted for the sample rate. It's hard coded here, but you would want to adjust so that you're dividing the input sample rate by your chosen sample rate.
        let sampleRateConversionRatio: Float = 44100.0/16000.0

        mixer.installTap(onBus: 0, bufferSize: 32000, format: formatIn, block: {
        (buffer: AVAudioPCMBuffer!, time: AVAudioTime!) -> Void in
                //And this is where you set the appropriate capacity!
                let capacity = UInt32(Float(buffer.frameCapacity)/ratio)
                let convertedBuffer = AVAudioPCMBuffer(pcmFormat: formatOut, frameCapacity: capacity)
                let inputBlock: AVAudioConverterInputBlock = { inNumPackets, outStatus in
                    outStatus.pointee = AVAudioConverterInputStatus.haveData
                    return buffer
                }
                var error: NSError? = nil
                let status = audioConverter.convert(to: convertedBuffer, error: &error, withInputFrom: inputBlock)
                let myData = convertedBuffer.toData()
                completionHandler(true, false, myData)
        })
        self.audioPlayerNode.scheduleFile(file, at: nil){
            self.delayWithSeconds(3.0){
            self.engine.stop()
            mixer.removeTap(onBus: 0)
            completionHandler(true, true, nil)
            }
        }
        do {
            try self.engine.start()
        } catch {
            print(error)
        }
        self.audioPlayerNode.play()
    }
}