Question

我正在实施以下教程：Speech To Text

我正在使用AVAudioEngine录制音频并使用SFSpeechRecognizer实现语音到文本。这里的教程使用一个开始和停止录制的按钮将语音引导到文本。

当应用程序获得权限时，我正在viewDidAppear开始录制。但经过几秒钟的沉默，我无法找到任何办法停止录音。以下是我的代码：

import UIKit
import Speech

public class ViewController: UIViewController, SFSpeechRecognizerDelegate {
// MARK: Properties

private let speechRecognizer = SFSpeechRecognizer(locale: Locale(identifier: "en-US"))!

private var recognitionRequest: SFSpeechAudioBufferRecognitionRequest?

private var recognitionTask: SFSpeechRecognitionTask?

private let audioEngine = AVAudioEngine()

@IBOutlet var textView : UILabel!

@IBOutlet var recordButton : UIButton!


public override func viewDidLoad() {
    super.viewDidLoad()

    recordButton.isEnabled = false
}

override public func viewDidAppear(_ animated: Bool) {
    speechRecognizer.delegate = self

    SFSpeechRecognizer.requestAuthorization { authStatus in
        /*
         The callback may not be called on the main thread. Add an
         operation to the main queue to update the record button's state.
         */
        OperationQueue.main.addOperation {
            switch authStatus {
            case .authorized:
                self.recordButton.isEnabled = true
                try! self.startRecording()
                self.recordButton.setTitle("Stop recording", for: [])


            case .denied:
                self.recordButton.isEnabled = false
                self.recordButton.setTitle("User denied access to speech recognition", for: .disabled)

            case .restricted:
                self.recordButton.isEnabled = false
                self.recordButton.setTitle("Speech recognition restricted on this device", for: .disabled)

            case .notDetermined:
                self.recordButton.isEnabled = false
                self.recordButton.setTitle("Speech recognition not yet authorized", for: .disabled)
            }
        }
    }
}

@IBAction func recordButtonTapped() {
    if audioEngine.isRunning {
        audioEngine.stop()
        recognitionRequest?.endAudio()
        recordButton.isEnabled = false
        recordButton.setTitle("Start Recording", for: [])
    } else {
        try! startRecording()
        recordButton.setTitle("Stop recording", for: [])
    }
}

private func startRecording() throws {

    // Cancel the previous task if it's running.
    if let recognitionTask = recognitionTask {
        recognitionTask.cancel()
        self.recognitionTask = nil
    }

    let audioSession = AVAudioSession.sharedInstance()
    try audioSession.setCategory(AVAudioSessionCategoryRecord)
    try audioSession.setMode(AVAudioSessionModeMeasurement)
    try audioSession.setActive(true, with: .notifyOthersOnDeactivation)

    recognitionRequest = SFSpeechAudioBufferRecognitionRequest()

    guard let inputNode = audioEngine.inputNode else { fatalError("Audio engine has no input node") }
    guard let recognitionRequest = recognitionRequest else { fatalError("Unable to created a SFSpeechAudioBufferRecognitionRequest object") }

    // Configure request so that results are returned before audio recording is finished
    recognitionRequest.shouldReportPartialResults = true

    // A recognition task represents a speech recognition session.
    // We keep a reference to the task so that it can be cancelled.
    recognitionTask = speechRecognizer.recognitionTask(with: recognitionRequest) { result, error in
        var isFinal = false

        if let result = result {
            self.textView.text = result.bestTranscription.formattedString
            isFinal = result.isFinal
        }

        if error != nil || isFinal {
            self.audioEngine.stop()
            inputNode.removeTap(onBus: 0)

            self.recognitionRequest = nil
            self.recognitionTask = nil

            self.recordButton.isEnabled = true
        }
    }

    let recordingFormat = inputNode.outputFormat(forBus: 0)
    inputNode.installTap(onBus: 0, bufferSize: 1024, format: recordingFormat) { (buffer: AVAudioPCMBuffer, when: AVAudioTime) in
        self.recognitionRequest?.append(buffer)
    }

    audioEngine.prepare()

    try audioEngine.start()

    textView.text = "(Go ahead, I'm listening)"
}

// MARK: SFSpeechRecognizerDelegate

public func speechRecognizer(_ speechRecognizer: SFSpeechRecognizer, availabilityDidChange available: Bool) {
    if available {
        recordButton.isEnabled = true
        recordButton.setTitle("Start Recording", for: [])
    } else {
        recordButton.isEnabled = false
        recordButton.setTitle("Recognition not available", for: .disabled)
    }
}

// MARK: Interface Builder actions


}

该应用程序非常棒。但我希望实现在X秒静音时停止audioEngine。

Answer 1

可能使用指定间隔的计时器，并且每次获得语音输入时都会失效。

您创建了一个计时器，该计时器始终使自身无效，并在用户说话时在其上创建一个新计时器。当用户停止说话时，时间到达结束并完成

示例：

class text {
var timer:Timer?
   func startRecording() { createTimer(4) }

   func whileRecording() { createTimer(1) }

   func createTimer(_ interval:Double) {
       timer?.invalidate()
       timer =   Timer.scheduledTimer(withTimeInterval: interval, repeats: false) { (_) in
           if self.audioEngine.isRunning {
               self.stopRecording()
           }
       }
   }

}

在X秒静音后停止录音

1 个答案: