Swift中的聲音

Question

我目前在Swift中製作的應用程序將幫助盲人使用這一綜合解決方案導航世界。我正在尋找一個應用程序的通用函數，當被調用時，它將立即開始錄製，傾聽用戶說出的內容，一旦用戶停止說話，它將自動停止錄製，將錄製內容轉換爲字符串，然後返回它。該功能應該可以在單個視圖控制器中多次使用。

我一直在使用從這篇文章的技術嘗試，並沒有奏效：https://medium.com/ios-os-x-development/speech-recognition-with-swift-in-ios-10-50d5f4e59c48

的記錄將被收集的建築物或建築物中的房間的名稱，所以它並不需要是錄製時間非常長 - 即使是5秒鐘的設定時間也可以工作。我希望能像Speech一樣使用像Siri這樣的框架，但如果它更好地工作，我並不反對使用像Watson這樣的外部框架。請幫忙！

Answer 1

有一個美麗的Appcoda教程here，完全適合這一點。

這是他們用來用語音結果更新文本字段的代碼。將文本字段中的文本引導到用於處理結果的任何變量/函數中並不困難。

// 
// ViewController.swift 
// Siri 
// 
// Created by Sahand Edrisian on 7/14/16. 
// Copyright © 2016 Sahand Edrisian. All rights reserved. 
// 

import UIKit 
import Speech 

class ViewController: UIViewController, SFSpeechRecognizerDelegate { 

    @IBOutlet weak var textView: UITextView! 
    @IBOutlet weak var microphoneButton: UIButton! 

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

    private var recognitionRequest: SFSpeechAudioBufferRecognitionRequest? 
    private var recognitionTask: SFSpeechRecognitionTask? 
    private let audioEngine = AVAudioEngine() 

    override func viewDidLoad() { 
     super.viewDidLoad() 

     microphoneButton.isEnabled = false 

     speechRecognizer.delegate = self 

     SFSpeechRecognizer.requestAuthorization { (authStatus) in 

      var isButtonEnabled = false 

      switch authStatus { 
      case .authorized: 
       isButtonEnabled = true 

      case .denied: 
       isButtonEnabled = false 
       print("User denied access to speech recognition") 

      case .restricted: 
       isButtonEnabled = false 
       print("Speech recognition restricted on this device") 

      case .notDetermined: 
       isButtonEnabled = false 
       print("Speech recognition not yet authorized") 
      } 

      OperationQueue.main.addOperation() { 
       self.microphoneButton.isEnabled = isButtonEnabled 
      } 
     } 
    } 

    @IBAction func microphoneTapped(_ sender: AnyObject) { 
     if audioEngine.isRunning { 
      audioEngine.stop() 
      recognitionRequest?.endAudio() 
      microphoneButton.isEnabled = false 
      microphoneButton.setTitle("Start Recording", for: .normal) 
     } else { 
      startRecording() 
      microphoneButton.setTitle("Stop Recording", for: .normal) 
     } 
    } 

    func startRecording() { 

     if recognitionTask != nil { //1 
      recognitionTask?.cancel() 
      recognitionTask = nil 
     } 

     let audioSession = AVAudioSession.sharedInstance() //2 
     do { 
      try audioSession.setCategory(AVAudioSessionCategoryRecord) 
      try audioSession.setMode(AVAudioSessionModeMeasurement) 
      try audioSession.setActive(true, with: .notifyOthersOnDeactivation) 
     } catch { 
      print("audioSession properties weren't set because of an error.") 
     } 

     recognitionRequest = SFSpeechAudioBufferRecognitionRequest() //3 

     guard let inputNode = audioEngine.inputNode else { 
      fatalError("Audio engine has no input node") 
     } //4 

     guard let recognitionRequest = recognitionRequest else { 
      fatalError("Unable to create an SFSpeechAudioBufferRecognitionRequest object") 
     } //5 

     recognitionRequest.shouldReportPartialResults = true //6 

     recognitionTask = speechRecognizer.recognitionTask(with: recognitionRequest, resultHandler: { (result, error) in //7 

      var isFinal = false //8 

      if result != nil { 

       self.textView.text = result?.bestTranscription.formattedString //9 
       isFinal = (result?.isFinal)! 
      } 

      if error != nil || isFinal { //10 
       self.audioEngine.stop() 
       inputNode.removeTap(onBus: 0) 

       self.recognitionRequest = nil 
       self.recognitionTask = nil 

       self.microphoneButton.isEnabled = true 
      } 
     }) 

     let recordingFormat = inputNode.outputFormat(forBus: 0) //11 
     inputNode.installTap(onBus: 0, bufferSize: 1024, format: recordingFormat) { (buffer, when) in 
      self.recognitionRequest?.append(buffer) 
     } 

     audioEngine.prepare() //12 

     do { 
      try audioEngine.start() 
     } catch { 
      print("audioEngine couldn't start because of an error.") 
     } 

     textView.text = "Say something, I'm listening!" 

    } 

    func speechRecognizer(_ speechRecognizer: SFSpeechRecognizer, availabilityDidChange available: Bool) { 
     if available { 
      microphoneButton.isEnabled = true 
     } else { 
      microphoneButton.isEnabled = false 
     } 
    } 
}