I'm following this Apple Sample Code and was wondering how it would be possible to clear the input buffer (ie. result in this case), so that the dictation restarts once a word has been said.
For example:
When a users says words, they are added to result.bestTranscription.formattedString then are appended. So if I said, "White", "Purple", "Yellow", result.bestTranscription.formattedString would look like "White Purple Yellow" and words would keep being appended until the buffer stops (~1min apparently). I was making an action happen when a word was spoken, so if you say "blue" for instance, I was checking to see if the buffer contains "blue" (or "Blue") and since it does, move on to the next activity and reset the buffer.
When I do that, however, I get this error:
2020-09-09 18:25:44.247575-0400 Test App[28460:1337362] [Utility] +[AFAggregator logDictationFailedWithError:] Error Domain=kAFAssistantErrorDomain Code=209 "(null)"
It works fine to stop the audio detection when it hears "blue", but as soon as I try to re-initialize the speech recognition code, it chokes. Below is my recognitionTask:
// Create a recognition task for the speech recognition session.
// Keep a reference to the task so that it can be canceled.
recognitionTask = speechRecognizer.recognitionTask(with: recognitionRequest) { result, error in
var isFinal = false
if let result = result {
// Update the text view with the results.
self.speechInput = result.bestTranscription.formattedString
isFinal = result.isFinal
print("Text \(result.bestTranscription.formattedString)")
}
if (result?.bestTranscription.formattedString.range(of:"blue") != nil) || (result?.bestTranscription.formattedString.range(of:"Blue") != nil) {
self.ColorView.backgroundColor = .random()
isFinal = true
}
if error != nil || isFinal {
// Stop recognizing speech if there is a problem.
self.audioEngine.stop()
self.recognitionRequest?.endAudio() // Necessary
inputNode.removeTap(onBus: 0)
self.recognitionRequest = nil
self.recognitionTask = nil
}
}
Here's the full code:
import UIKit
import Speech
private let audioEngine = AVAudioEngine()
extension CGFloat {
static func random() -> CGFloat {
return CGFloat(arc4random()) / CGFloat(UInt32.max)
}
}
extension UIColor {
static func random() -> UIColor {
return UIColor(
red: .random(),
green: .random(),
blue: .random(),
alpha: 1.0
)
}
}
class ViewController: UIViewController, SFSpeechRecognizerDelegate {
@IBOutlet var ColorView: UIView!
@IBOutlet weak var StartButton: UIButton!
private let speechRecognizer = SFSpeechRecognizer()!
private var recognitionRequest: SFSpeechAudioBufferRecognitionRequest?
private var recognitionTask: SFSpeechRecognitionTask?
private let audioEngine = AVAudioEngine()
private var speechInput: String = ""
override func viewDidLoad() {
super.viewDidLoad()
// Create and configure the speech recognition request.
recognitionRequest = SFSpeechAudioBufferRecognitionRequest()
guard let recognitionRequest = recognitionRequest else { fatalError("Unable to create a SFSpeechAudioBufferRecognitionRequest object") }
recognitionRequest.shouldReportPartialResults = true
// Do any additional setup after loading the view.
}
func start() {
// Cancel the previous task if it's running.
recognitionTask?.cancel()
self.recognitionTask = nil
// Configure the audio session for the app.
let audioSession = AVAudioSession.sharedInstance()
do {
try audioSession.setCategory(.record, mode: .measurement, options: .duckOthers)
} catch {}
do {
try audioSession.setActive(true, options: .notifyOthersOnDeactivation)
} catch {}
let inputNode = audioEngine.inputNode
// Create and configure the speech recognition request.
recognitionRequest = SFSpeechAudioBufferRecognitionRequest()
guard let recognitionRequest = recognitionRequest else { fatalError("Unable to create a SFSpeechAudioBufferRecognitionRequest object") }
recognitionRequest.shouldReportPartialResults = true
// Keep speech recognition data on device
if #available(iOS 13, *) {
recognitionRequest.requiresOnDeviceRecognition = false
}
// Create a recognition task for the speech recognition session.
// Keep a reference to the task so that it can be canceled.
recognitionTask = speechRecognizer.recognitionTask(with: recognitionRequest) { result, error in
var isFinal = false
if let result = result {
// Update the text view with the results.
self.speechInput = result.bestTranscription.formattedString
isFinal = result.isFinal
print("Text \(result.bestTranscription.formattedString)")
}
if (result?.bestTranscription.formattedString.range(of:"blue") != nil) || (result?.bestTranscription.formattedString.range(of:"Blue") != nil) {
self.ColorView.backgroundColor = .random()
isFinal = true
}
if error != nil || isFinal {
// Stop recognizing speech if there is a problem.
self.audioEngine.stop()
self.recognitionRequest?.endAudio() // Necessary
inputNode.removeTap(onBus: 0)
self.recognitionRequest = nil
self.recognitionTask = nil
self.start() //This chokes it
}
}
// Configure the microphone input.
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()
do {
try audioEngine.start()
} catch {}
// Let the user know to start talking.
//textView.text = "(Go ahead, I'm listening)"
}
override func viewDidAppear(_ animated: Bool) {
super.viewDidAppear(animated)
// Configure the SFSpeechRecognizer object already
// stored in a local member variable.
speechRecognizer.delegate = self
// Asynchronously make the authorization request.
SFSpeechRecognizer.requestAuthorization { authStatus in
// Divert to the app's main thread so that the UI
// can be updated.
OperationQueue.main.addOperation {
switch authStatus {
case .authorized:
self.ColorView.backgroundColor = .green
case .denied:
self.ColorView.backgroundColor = .red
case .restricted:
self.ColorView.backgroundColor = .orange
case .notDetermined:
self.ColorView.backgroundColor = .gray
default:
self.ColorView.backgroundColor = .random()
}
}
}
}
@IBAction func start(_ sender: Any) {
start()
}
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)
}
}
}
I'm sure there's something simple I'm missing, any advise?
