我正在尝试让 AudioKit 将麦克风通过管道传输到 Google 的 Speech-to-Text API，如 here 所示但我不完全确定该怎么做。

要为 Speech-to-Text 引擎准备音频，您需要设置编码并将其作为 block 传递。在 Google 使用的示例中，他们使用了 Apple 的 AVFoundation，但我想使用 AudioKit，因此我可以执行一些预处理，例如削减低振幅等。

我认为正确的方法是使用 Tap:

首先，我应该通过以下方式匹配格式:

var asbd = AudioStreamBasicDescription()
asbd.mSampleRate = 16000.0
asbd.mFormatID = kAudioFormatLinearPCM
asbd.mFormatFlags = kAudioFormatFlagIsSignedInteger | kAudioFormatFlagIsPacked
asbd.mBytesPerPacket = 2
asbd.mFramesPerPacket = 1
asbd.mBytesPerFrame = 2
asbd.mChannelsPerFrame = 1
asbd.mBitsPerChannel = 16

AudioKit.format = AVAudioFormat(streamDescription: &asbd)!

然后创建一个水龙头，例如:

open class TestTap {
    internal let bufferSize: UInt32 = 1_024

    @objc public init(_ input: AKNode?) {
        input?.avAudioNode.installTap(onBus: 0, bufferSize: bufferSize, format: AudioKit.format) { buffer, _ in

         // do work here

        }
    }
}

但我无法确定处理这些数据的正确方法，这些数据将通过方法 streamAudioData 发送到 Google Speech-to-Text API。实时使用 AudioKit 但也许我正在以错误的方式解决这个问题？

更新:

我已经创建了一个 Tap:

open class TestTap {

    internal var audioData =  NSMutableData()
    internal let bufferSize: UInt32 = 1_024

    func toData(buffer: AVAudioPCMBuffer) -> NSData {
        let channelCount = 2  // given PCMBuffer channel count is
        let channels = UnsafeBufferPointer(start: buffer.floatChannelData, count: channelCount)
        return NSData(bytes: channels[0], length:Int(buffer.frameCapacity * buffer.format.streamDescription.pointee.mBytesPerFrame))
    }

    @objc public init(_ input: AKNode?) {

        input?.avAudioNode.installTap(onBus: 0, bufferSize: bufferSize, format: AudioKit.format) { buffer, _ in
            self.audioData.append(self.toData(buffer: buffer) as Data)

            // We recommend sending samples in 100ms chunks (from Google)
            let chunkSize: Int /* bytes/chunk */ = Int(0.1 /* seconds/chunk */
                * AudioKit.format.sampleRate /* samples/second */
                * 2 /* bytes/sample */ )

            if self.audioData.length > chunkSize {
                SpeechRecognitionService
                    .sharedInstance
                    .streamAudioData(self.audioData,
                                     completion: { response, error in
                                        if let error = error {
                                            print("ERROR: \(error.localizedDescription)")
                                            SpeechRecognitionService.sharedInstance.stopStreaming()
                                        } else if let response = response {
                                            print(response)
                                        }
                    })
                self.audioData = NSMutableData()
            }

        }
    }
}

在 viewDidLoad: 中，我正在设置 AudioKit:

AKSettings.sampleRate = 16_000
AKSettings.bufferLength = .shortest

但是，Google 提示:

错误:音频数据传输速度过快。请实时传输音频数据。

我已经尝试更改多个参数，例如 block 大小，但无济于事。

最佳答案

我找到了解决方案 here .

我的 Tap 的最终代码是:

open class GoogleSpeechToTextStreamingTap {

internal var converter: AVAudioConverter!

@objc public init(_ input: AKNode?, sampleRate: Double = 16000.0) {

    let format = AVAudioFormat(commonFormat: AVAudioCommonFormat.pcmFormatInt16, sampleRate: sampleRate, channels: 1, interleaved: false)!

    self.converter = AVAudioConverter(from: AudioKit.format, to: format)
    self.converter?.sampleRateConverterAlgorithm = AVSampleRateConverterAlgorithm_Normal
    self.converter?.sampleRateConverterQuality = .max

    let sampleRateRatio = AKSettings.sampleRate / sampleRate
    let inputBufferSize = 4410 //  100ms of 44.1K = 4410 samples.

    input?.avAudioNode.installTap(onBus: 0, bufferSize: AVAudioFrameCount(inputBufferSize), format: nil) { buffer, time in

        let capacity = Int(Double(buffer.frameCapacity) / sampleRateRatio)
        let bufferPCM16 = AVAudioPCMBuffer(pcmFormat: format, frameCapacity: AVAudioFrameCount(capacity))!

        var error: NSError? = nil
        self.converter?.convert(to: bufferPCM16, error: &error) { inNumPackets, outStatus in
            outStatus.pointee = AVAudioConverterInputStatus.haveData
            return buffer
        }

        let channel = UnsafeBufferPointer(start: bufferPCM16.int16ChannelData!, count: 1)
        let data = Data(bytes: channel[0], count: capacity * 2)

        SpeechRecognitionService
            .sharedInstance
            .streamAudioData(data,
                             completion: { response, error in
                                if let error = error {
                                    print("ERROR: \(error.localizedDescription)")
                                    SpeechRecognitionService.sharedInstance.stopStreaming()
                                } else if let response = response {
                                    print(response)
                                }
            })
    }
}

关于ios - 将 AudioKit 麦克风连接到 Google Speech-to-Text，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/47596430/