refirio.org

Memo

■SwiftUI+音声

【SwiftUI】AVFoundationでText to Speech - Qiita
https://qiita.com/mushroominger/items/5f4199d4eff8d2b4bc30

[Swift] AVSpeechSynthesizerで読み上げ機能を使ってみる | DevelopersIO
https://dev.classmethod.jp/articles/swfit-avspeechsynthesizer/■音声読み上げ

ContentView.swift
import SwiftUI
import AVFoundation

struct ContentView: View {
    @State private var language = "ja"
    @State private var text: String = ""

    var body: some View {
        VStack {
            Picker(selection: $language, label: Text("フルーツを選択")) {
                Text("日本語").tag("ja")
                Text("英語").tag("en")
            }
            .frame(width: 200, height: 100)
            
            //Text("選択値：\(language)")

            TextEditor(text: $text)
                .frame(width: UIScreen.main.bounds.width * 0.9, height: 200)
                .overlay(
                    RoundedRectangle(cornerRadius: 6)
                        .stroke(Color.gray, lineWidth: 1)
                )
                .padding()
            Button("読み上げる") {
                // 読み上げる内容
                let utterance = AVSpeechUtterance(string: text)
                // 言語
                if (language == "ja") {
                    utterance.voice = AVSpeechSynthesisVoice(language: "ja-JP")
                } else {
                    utterance.voice = AVSpeechSynthesisVoice(language: "en-US")
                }
                // 速度
                utterance.rate = 0.5
                //utterance.rate = 0.6
                // 高さ
                utterance.pitchMultiplier = 1.0
                //utterance.pitchMultiplier = 1.2
                // 読み上げ実行
                let synthesizer = AVSpeechSynthesizer()
                synthesizer.speak(utterance)
            }
            .padding()
            Spacer()
        }
    }
}

struct ContentView_Previews: PreviewProvider {
    static var previews: some View {
        ContentView()
    }
}
■音声認識

※検証中

Swiftでリアルタイム音声認識するための最小コード - Qiita
https://qiita.com/mishimay/items/71304f0aa2a313ad93ac

Swift でリアルタイム音声認識をするサンプルコード - iOS アプリケーション開発の基本 - Swift による iOS 開発入門
https://swift-ios.keicode.com/ios/speechrecognition-live.php

SpeechFrameworkで音声認識されなくなる問題 - 野生のプログラマZ
http://harumi.sakura.ne.jp/wordpress/2020/04/20/speechframework%E3%81%A7%E9%9F%B3%E5%A3%B0%E8%AA%8D%...

SwiftUIとSpeech Frameworkで動画の文字起こしアプリを作ってみる - Qiita
https://qiita.com/rymshm/items/5ea968acb686c53133c7

Info.plist にKey「Privacy - Microphone Usage Description」を追加し、Valueに「マイクを使用します。」と記載しておく
同様に「Privacy - Speech Recognition Usage Description」を追加し、Valueに「音声認識を使用します。」と記載しておく
ファイルの内容を直接確認すると、dictタグ内に以下が追加されている

Info.plist
    <key>NSMicrophoneUsageDescription</key>
    <string>マイクを使用します。</string>
    <key>NSSpeechRecognitionUsageDescription</key>
    <string>音声認識を使用します。</string>


ContentView.swift
import SwiftUI
import Speech

struct ContentView: View {
    private let speechRecognizer = SFSpeechRecognizer(locale: Locale(identifier: "ja-JP"))!
    @State private var recognitionRequest: SFSpeechAudioBufferRecognitionRequest?
    @State private var recognitionTask: SFSpeechRecognitionTask?
    private let audioEngine = AVAudioEngine()
    
    @State private var text: String = ""

    var body: some View {
        VStack {
            TextEditor(text: $text)
                .frame(width: UIScreen.main.bounds.width * 0.9, height: 200)
                .overlay(
                    RoundedRectangle(cornerRadius: 6)
                        .stroke(Color.gray, lineWidth: 1)
                )
                .padding()
            Button("音声認識開始") {
                try? start()
            }
            Button("音声認識終了") {
                stop()
            }
        }
        .onAppear() {
            SFSpeechRecognizer.requestAuthorization { (authStatus) in
            }
        }
    }
    
    private func start() throws {
        if let recognitionTask = recognitionTask {
            recognitionTask.cancel()
            self.recognitionTask = nil
        }

        let audioSession = AVAudioSession.sharedInstance()
        try audioSession.setCategory(.record, mode: .measurement, options: [])
        try audioSession.setActive(true, options: .notifyOthersOnDeactivation)

        let recognitionRequest = SFSpeechAudioBufferRecognitionRequest()
        self.recognitionRequest = recognitionRequest
        recognitionRequest.shouldReportPartialResults = true
        recognitionTask = speechRecognizer.recognitionTask(with: recognitionRequest, resultHandler: { (result, error) in
        //recognitionTask = speechRecognizer.recognitionTask(with: recognitionRequest) { [weak self] (result, error) in
            //guard let `self` = self else { return }

            var isFinal = false

            if let result = result {
                print(result.bestTranscription.formattedString)
                text = result.bestTranscription.formattedString
                isFinal = result.isFinal
            }

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

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

        audioEngine.prepare()
        try? audioEngine.start()
    }
    
    private func stop() {
        audioEngine.stop()
        recognitionRequest?.endAudio()
    }
}

struct ContentView_Previews: PreviewProvider {
    static var previews: some View {
        ContentView()
    }
}


「音声認識開始」ボタンを連続してタップするとアプリが止まる
認識中ならタップできないようにする仕組みが必要か
Memo

Advertisement
