我正在使用 iOS 10 内置语音识别来破解一个小项目。我使用设备的麦克风有工作结果,我的语音被非常准确地识别。
我的问题是每个可用的部分转录都会调用识别任务回调,我希望它检测到人停止说话并调用isFinal
属性设置为 true 的回调。它没有发生 - 应用程序正在无限期地收听。
是否SFSpeechRecognizer
能够检测到句子的结尾?
这是我的代码 - 它基于互联网上的示例,它主要是从麦克风源识别所需的样板。我通过添加识别对其进行了修改taskHint
。我也设置shouldReportPartialResults
为false,但似乎已被忽略。
func startRecording() {
if recognitionTask != nil {
recognitionTask?.cancel()
recognitionTask = nil
}
let audioSession = AVAudioSession.sharedInstance()
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()
recognitionRequest?.shouldReportPartialResults = false
recognitionRequest?.taskHint = .search
guard let inputNode = audioEngine.inputNode else {
fatalError("Audio engine has no input node")
}
guard let recognitionRequest = recognitionRequest else {
fatalError("Unable to create an SFSpeechAudioBufferRecognitionRequest object")
}
recognitionRequest.shouldReportPartialResults = true
recognitionTask = speechRecognizer?.recognitionTask(with: recognitionRequest, resultHandler: { (result, error) in
var isFinal = false
if result != nil {
print("RECOGNIZED \(result?.bestTranscription.formattedString)")
self.transcriptLabel.text = result?.bestTranscription.formattedString
isFinal = (result?.isFinal)!
}
if error != nil || isFinal {
self.state = .Idle
self.audioEngine.stop()
inputNode.removeTap(onBus: 0)
self.recognitionRequest = nil
self.recognitionTask = nil
self.micButton.isEnabled = true
self.say(text: "OK. Let me see.")
}
})
let recordingFormat = inputNode.outputFormat(forBus: 0)
inputNode.installTap(onBus: 0, bufferSize: 1024, format: recordingFormat) { (buffer, when) in
self.recognitionRequest?.append(buffer)
}
audioEngine.prepare()
do {
try audioEngine.start()
} catch {
print("audioEngine couldn't start because of an error.")
}
transcriptLabel.text = "Say something, I'm listening!"
state = .Listening
}