大数据

iOS原生语音识别使用的正确姿势

语音识别技术这几年在移动App上的应用越来越广,各种第三方语音识别SDK也是层出不穷,例如科大讯飞、百度语音等,同时引入语音识别技术也是一个提高App逼格的好方法😁。所以今年的WWDC上,苹果开放了他的语音识别的API 视频在这。有了语音识别技术我们开发者就可以开发出像Siri这样炫酷的应用。这不,最近我们也要上这个功能,所以我调研一些这方面的东西。本文主要介绍iOS语音识别SDK的用法。

  • 首先需要在plist文件中申请语音识别和麦克风使用权限:

  • 引入头文件
    #import 
    #import 
  • 申请权限

    - (void)viewDidAppear:(BOOL)animated{
      [super viewDidAppear:animated];
      [SFSpeechRecognizer requestAuthorization:^(SFSpeechRecognizerAuthorizationStatus status) {
          dispatch_async(dispatch_get_main_queue(), ^{
              switch (status) {
                  case SFSpeechRecognizerAuthorizationStatusNotDetermined:
                      self.recordButton.enabled = NO;
                      [self.recordButton setTitle:@"语音识别未授权" forState:UIControlStateDisabled];
                      break;
                  case SFSpeechRecognizerAuthorizationStatusDenied:
                      self.recordButton.enabled = NO;
                      [self.recordButton setTitle:@"用户未授权使用语音识别" forState:UIControlStateDisabled];
                      break;
                  case SFSpeechRecognizerAuthorizationStatusRestricted:
                      self.recordButton.enabled = NO;
                      [self.recordButton setTitle:@"语音识别在这台设备上受到限制" forState:UIControlStateDisabled];
    
                      break;
                  case SFSpeechRecognizerAuthorizationStatusAuthorized:
                      self.recordButton.enabled = YES;
                      [self.recordButton setTitle:@"开始录音" forState:UIControlStateNormal];
                      break;
    
                  default:
                      break;
              }
    
          });
      }];
    }
  • 核心代码

    • 识别实时音频流,如下

      - (void)startRecording{
          if (_recognitionTask) {
             [_recognitionTask cancel];
              _recognitionTask = nil;
           }
      
      AVAudioSession *audioSession = [AVAudioSession sharedInstance];
      NSError *error;
      [audioSession setCategory:AVAudioSessionCategoryRecord error:&error];
      NSParameterAssert(!error);
      [audioSession setMode:AVAudioSessionModeMeasurement error:&error];
      NSParameterAssert(!error);
      [audioSession setActive:YES withOptions:AVAudioSessionSetActiveOptionNotifyOthersOnDeactivation error:&error];
      NSParameterAssert(!error);
      
      _recognitionRequest = [[SFSpeechAudioBufferRecognitionRequest alloc] init];
      AVAudioInputNode *inputNode = self.audioEngine.inputNode;
      NSAssert(inputNode, @"录入设备没有准备好");
      NSAssert(_recognitionRequest, @"请求初始化失败");
      _recognitionRequest.shouldReportPartialResults = YES;
      __weak typeof(self) weakSelf = self;
      _recognitionTask = [self.speechRecognizer recognitionTaskWithRequest:_recognitionRequest resultHandler:^(SFSpeechRecognitionResult * _Nullable result, NSError * _Nullable error) {
          __strong typeof(weakSelf) strongSelf = weakSelf;
          BOOL isFinal = NO;
          if (result) {
              strongSelf.resultStringLable.text = result.bestTranscription.formattedString;
              isFinal = result.isFinal;
          }
          if (error || isFinal) {
              [self.audioEngine stop];
              [inputNode removeTapOnBus:0];
              strongSelf.recognitionTask = nil;
              strongSelf.recognitionRequest = nil;
              strongSelf.recordButton.enabled = YES;
              [strongSelf.recordButton setTitle:@"开始录音" forState:UIControlStateNormal];
          }
      
      }];
      
      AVAudioFormat *recordingFormat = [inputNode outputFormatForBus:0];
      [inputNode installTapOnBus:0 bufferSize:1024 format:recordingFormat block:^(AVAudioPCMBuffer * _Nonnull buffer, AVAudioTime * _Nonnull when) {
          __strong typeof(weakSelf) strongSelf = weakSelf;
          if (strongSelf.recognitionRequest) {
              [strongSelf.recognitionRequest appendAudioPCMBuffer:buffer];
          }
      }];
      
      [self.audioEngine prepare];
      [self.audioEngine startAndReturnError:&error];
       NSParameterAssert(!error);
      self.resultStringLable.text = @"正在录音。。。";
      }
      - (SFSpeechRecognizer *)speechRecognizer{
      if (!_speechRecognizer) {
          //要为语音识别对象设置语言,这里设置的是中文
          NSLocale *local =[[NSLocale alloc] initWithLocaleIdentifier:@"zh_CN"];
      
          _speechRecognizer =[[SFSpeechRecognizer alloc] initWithLocale:local];
          _speechRecognizer.delegate = self;
      }
      return _speechRecognizer;
      }
    • 识别本地音频文件,如下
      - (IBAction)recognizeLocalAudioFile:(UIButton *)sender {   
      NSLocale *local =[[NSLocale alloc] initWithLocaleIdentifier:@"zh_CN"];
      SFSpeechRecognizer *localRecognizer =[[SFSpeechRecognizer alloc] initWithLocale:local];
      NSURL *url =[[NSBundle mainBundle] URLForResource:@"录音.m4a" withExtension:nil];
      if (!url) return;
      SFSpeechURLRecognitionRequest *res =[[SFSpeechURLRecognitionRequest alloc] initWithURL:url];
      [localRecognizer recognitionTaskWithRequest:res resultHandler:^(SFSpeechRecognitionResult * _Nullable result, NSError * _Nullable error) {
          if (error) {
              NSLog(@"语音识别解析失败,%@",error);
          }
          else
          {
              self.resultStringLable.text = result.bestTranscription.formattedString;
          }
      }];
      }
  • 注意
    • iOS语音识别Api只支持iOS10SDK以及以后的版本,开发工具至少要Xcode8.0。
    • 本文的Demo在这里下载,要看效果的话要在真机上运行。