Objective c 文本到语音和语音到文本识别-->；自我认识正在发生
我想开发一个应该支持语音对文本和文本对语音的应用程序 i） Speech to Text（语音到文本）-过程-我使用了Speech to Text（语音到文本）的语音框架，每当我打开一个应用程序，如果我开始说话，该应用程序应该能够识别语音并将语音转换为文本。这很有效 ii）文本到语音-程序-我使用过AVFoundation和MediaPlayer库，如果用户按下播放按钮，则应将文本（即屏幕上出现的任何内容）转换为语音。立即工作 这就是我面临的问题 在处理文本到语音的过程中，语音识别器识别播放的声音并在文本框中再次打印单词 示例-如果我说“你好，早上好”它正在文本框中打印，然后如果我按播放按钮，它正在播放一个声音“你好，早上好”，但此时语音到文本识别识别识别这个声音，我指的是自我识别，它正在打印“你好，早上好” 我想在处理文本到语音过程时停止语音到文本过程 为此，我在播放语音时停止了语音识别请求 这是密码Objective c 文本到语音和语音到文本识别-->；自我认识正在发生,objective-c,speech-recognition,text-to-speech,speech-to-text,Objective C,Speech Recognition,Text To Speech,Speech To Text,我想开发一个应该支持语音对文本和文本对语音的应用程序 i） Speech to Text（语音到文本）-过程-我使用了Speech to Text（语音到文本）的语音框架，每当我打开一个应用程序，如果我开始说话，该应用程序应该能够识别语音并将语音转换为文本。这很有效 ii）文本到语音-程序-我使用过AVFoundation和MediaPlayer库，如果用户按下播放按钮，则应将文本（即屏幕上出现的任何内容）转换为语音。立即工作 这就是我面临的问题 在处理文本到语音的过程中，语音识别器识别播放的声
@implementation ViewController
{
SFSpeechAudioBufferRecognitionRequest *recognitionRequest;
SFSpeechRecognitionTask *recognitionTask;
AVAudioEngine *audioEngine;
NSMutableArray *speechStringsArray;
BOOL SpeechToText;
NSString* resultString;
NSString *str ;
NSString *searchString;
NSString *textToSpeak;
}
- (void)viewDidLoad {
[super viewDidLoad];
//Speech To Text ****
speechStringsArray = [[NSMutableArray alloc]init];
// Initialize background audio session
NSError *error = NULL;
AVAudioSession *session = [AVAudioSession sharedInstance];
[session setCategory:AVAudioSessionCategoryPlayback error:&error];
if(error) {
NSLog(@"@error: %@", error);
}
[session setActive:YES error:&error];
if (error) {
NSLog(@"@error: %@", error);
}
// Enabled remote controls
[[UIApplication sharedApplication] beginReceivingRemoteControlEvents];
// Voice setup
self.voicePicker.delegate = self;
self.voice = [AVSpeechSynthesisVoice voiceWithLanguage:@"en-us"];
self.voices = [NSMutableArray arrayWithObjects:
@{@"voice" : @"en-us", @"label" : @"American English (Female)"},
@{@"voice" : @"en-au", @"label" : @"Australian English (Female)"},
@{@"voice" : @"en-gb", @"label" : @"British English (Male)"},
@{@"voice" : @"en-ie", @"label" : @"Irish English (Female)"},
@{@"voice" : @"en-za", @"label" : @"South African English (Female)"},
nil];
// Synthesizer setup
self.synthesizer = [[AVSpeechSynthesizer alloc] init];
self.synthesizer.delegate = self;
// UITextView delegate
self.textView.delegate = self;
// This notifcation is generated from the AppDelegate applicationDidBecomeActive method to make sure that if the play or pause button is updated in the background then the button will be updated in the toolbar
[[NSNotificationCenter defaultCenter] addObserver:self selector:@selector(updateToolbar) name:@"updateToolbar" object:nil];
}
-(void)viewDidAppear:(BOOL)animated
{
self.speechRecognizer = [[SFSpeechRecognizer alloc]initWithLocale:[NSLocale localeWithLocaleIdentifier:@"en-US en-UK"]];
self.speechRecognizer.delegate = self;
audioEngine = [[AVAudioEngine alloc]init];
[SFSpeechRecognizer requestAuthorization:^(SFSpeechRecognizerAuthorizationStatus authStatus) {
switch (authStatus) {
case SFSpeechRecognizerAuthorizationStatusAuthorized:
//User gave access to speech recognition
NSLog(@"Authorized");
[self start_record];
break;
case SFSpeechRecognizerAuthorizationStatusDenied:
//User denied access to speech recognition
NSLog(@"AuthorizationStatusDenied");
break;
case SFSpeechRecognizerAuthorizationStatusRestricted:
//Speech recognition restricted on this device
NSLog(@"AuthorizationStatusRestricted");
break;
case SFSpeechRecognizerAuthorizationStatusNotDetermined:
//Speech recognition not yet authorized
break;
default:
NSLog(@"Default");
break;
}
}];
//MARK : Interface Builder Actions
}
- (IBAction)handleSpeedStepper:(UIStepper *)sender
{
double speedValue = self.speedStepper.value;
[self.speedValueLabel setText:[NSString stringWithFormat:@"%.1f", speedValue]];
}
- (IBAction)handlePitchStepper:(UIStepper *)sender
{
double pitchValue = self.pitchStepper.value;
[self.pitchValueLabel setText:[NSString stringWithFormat:@"%.1f", pitchValue]];
}
NSError * outError;
AVAudioSession *audioSession = [AVAudioSession sharedInstance];
[audioSession setCategory:AVAudioSessionCategoryPlayAndRecord error:&outError];
[audioSession setMode:AVAudioSessionModeMeasurement error:&outError];
[audioSession setActive:YES withOptions:AVAudioSessionSetActiveOptionNotifyOthersOnDeactivation error:&outError];
recognitionRequest = [[SFSpeechAudioBufferRecognitionRequest alloc]init];
AVAudioInputNode *inputNode = audioEngine.inputNode;
if (recognitionRequest == nil) {
NSLog(@"Unable to created a SFSpeechAudioBufferRecognitionRequest object");
}
if (inputNode == nil) {
NSLog(@"Audio engine has no input node ");}
//configure request so that results are returned before audio recording is finished
[recognitionRequest setShouldReportPartialResults:YES];
// A recognition task represents a speech recognition session.
//We keep a reference to the task so that it can be cancelled .
recognitionTask = [self.speechRecognizer recognitionTaskWithRequest:recognitionRequest resultHandler:^(SFSpeechRecognitionResult * result, NSError * error1) {
BOOL isFinal = false;
if ((result = result)) {
NSString *speech = result.bestTranscription.formattedString;
NSLog(@"the speech:%@",speech);
// coding for fixing append string issue
for (int i = 0 ;i <speechStringsArray.count;i++)
{
str = [speechStringsArray objectAtIndex:i];
NSRange range = [speech rangeOfString:str options:NSCaseInsensitiveSearch];
NSLog(@"found: %@", (range.location != NSNotFound) ? @"Yes" : @"No");
if (range.location != NSNotFound) {
resultString = [speech stringByReplacingCharactersInRange:range withString:@""];
speech = resultString;
NSLog(@" the result is : %@",resultString);
}
}
//specific functions - space for second word
if (resultString.length>0) {
self.textView.text = [NSString stringWithFormat:@"%@%@",self.textView.text,resultString];
[speechStringsArray addObject:resultString]; }
//specific function space for first word -Working fine
else
{
[speechStringsArray addObject:speech];
self.textView.text = speech;
}
}
NSLog(@" array %@",speechStringsArray);
isFinal = result.isFinal;
}
if (error1 != nil || isFinal) {
[audioEngine stop];
[inputNode removeTapOnBus:0];
recognitionRequest = nil;
recognitionTask = nil;
[self start_record];
}}];
AVAudioFormat *recordingFormat = [inputNode outputFormatForBus:0];
[inputNode installTapOnBus:0 bufferSize:1024 format:recordingFormat block:^(AVAudioPCMBuffer * _Nonnull buffer, AVAudioTime * _Nonnull when){
[recognitionRequest appendAudioPCMBuffer:buffer];}
];
NSError *error1;
[audioEngine prepare];
[audioEngine startAndReturnError:&error1];}
- (void)speakUtterance
{
NSLog(@"speakUtterance");
didStartSpeaking = NO;
textToSpeak = [NSString stringWithFormat:@"%@", self.textView.text];
AVSpeechUtterance *utterance = [[AVSpeechUtterance alloc] initWithString:textToSpeak];
utterance.rate = self.speedStepper.value;
utterance.pitchMultiplier = self.pitchStepper.value;
utterance.voice = self.voice;
[self.synthesizer speakUtterance:utterance];
[self displayBackgroundMediaFields];
}
- (void)displayBackgroundMediaFields
{
MPMediaItemArtwork *artwork = [[MPMediaItemArtwork alloc] initWithImage:[UIImage imageNamed:@"Play"]];
NSDictionary *info = @{ MPMediaItemPropertyTitle: self.textView.text,
MPMediaItemPropertyAlbumTitle: @"TextToSpeech App",
MPMediaItemPropertyArtwork: artwork};
[MPNowPlayingInfoCenter defaultCenter].nowPlayingInfo = info;
}
- (void)updateToolbar
{
if (self.synthesizer.speaking && !self.synthesizer.paused) {
[self updateToolbarWithButton:@"pause"];
}
else {
[self updateToolbarWithButton:@"play"];
}}
- (void)updateToolbarWithButton:(NSString *)buttonType
{
//stopping the speech to text process
if (audioEngine.isRunning) {
[audioEngine stop];
[recognitionRequest endAudio];
}
NSLog(@"updateToolbarWithButton: %@", buttonType);
UIBarButtonItem *audioControl;
if ([buttonType isEqualToString:@"play"]) {
// Play
audioControl = [[UIBarButtonItem alloc]initWithBarButtonSystemItem:UIBarButtonSystemItemPlay target:self action:@selector(handlePlayPauseButton:)];
}
else {
// Pause
audioControl = [[UIBarButtonItem alloc]initWithBarButtonSystemItem:UIBarButtonSystemItemPause target:self action:@selector(handlePlayPauseButton:)];
}
UIBarButtonItem *flexibleItem = [[UIBarButtonItem alloc] initWithBarButtonSystemItem:UIBarButtonSystemItemFlexibleSpace target:nil action:nil];
[self.toolbar setItems:@[flexibleItem, audioControl, flexibleItem]];
}
- (void)remoteControlReceivedWithEvent:(UIEvent *)receivedEvent
{
NSLog(@"receivedEvent: %@", receivedEvent);
if (receivedEvent.type == UIEventTypeRemoteControl) {
switch (receivedEvent.subtype) {
case UIEventSubtypeRemoteControlPlay:
NSLog(@"UIEventSubtypeRemoteControlPlay");
if (self.synthesizer.speaking) {
[self.synthesizer continueSpeaking];
}
else {
[self speakUtterance];
}
break;
case UIEventSubtypeRemoteControlPause:
NSLog(@"pause - UIEventSubtypeRemoteControlPause");
if (self.pauseSettingSegmentedControl.selectedSegmentIndex == 0) {
// Pause immediately
[self.synthesizer pauseSpeakingAtBoundary:AVSpeechBoundaryImmediate];
}
else {
// Pause at end of current word
[self.synthesizer pauseSpeakingAtBoundary:AVSpeechBoundaryWord];
}
break;
case UIEventSubtypeRemoteControlTogglePlayPause:
if (self.synthesizer.paused) {
NSLog(@"UIEventSubtypeRemoteControlTogglePlayPause");
[self.synthesizer continueSpeaking];
}
else {
NSLog(@"UIEventSubtypeRemoteControlTogglePlayPause");
if (self.pauseSettingSegmentedControl.selectedSegmentIndex == 0) {
// Pause immediately
[self.synthesizer pauseSpeakingAtBoundary:AVSpeechBoundaryImmediate];
}
else {
// Pause at end of current word
[self.synthesizer pauseSpeakingAtBoundary:AVSpeechBoundaryWord];
}
}
break;
case UIEventSubtypeRemoteControlNextTrack:
NSLog(@"UIEventSubtypeRemoteControlNextTrack - appropriate for playlists");
break;
case UIEventSubtypeRemoteControlPreviousTrack:
NSLog(@"UIEventSubtypeRemoteControlPreviousTrack - appropriatefor playlists");
break;
default:
break;
}
}
}
不要初始化ViewDidLoad中的所有内容。当您点击按钮将文本转换为语音时，此时将语音转换为文本对象为nil，并将代理设置为nil。反之亦然。谢谢@Nilesh Jha，我遇到了类似TextToSpeech的错误[2069:915956]***由于未捕获的异常“com.apple.coreaudio.avfaudio”而终止应用程序，原因：“必需条件为false:NULL！=engine”，在停止语音引擎时，我已将识别对象设置为nil请帮助我执行此操作。在停止引擎之前是否将对象设置为nil？如果（audioEngine.isRunning）{NSLog(@“正在运行”）；[audioEngine停止]；[inputNode removeTapOnBus:0]；[recognitionRequest endAudio]；recognitionRequest=nil；recognitionTask=nil；}我已经这样做了，只需检查一下audioEngine是否分配了该时间..在调用stop方法之前给出一个断点..最好在audioEngine=[[AVAudioEngine alloc]init]；viewDidLoad中输入这行代码。您好agal Sivamanoj先生，请告诉我如何将音频转换为文本目标cdid您得到答案了吗？
NSError * outError;
AVAudioSession *audioSession = [AVAudioSession sharedInstance];
[audioSession setCategory:AVAudioSessionCategoryPlayAndRecord error:&outError];
[audioSession setMode:AVAudioSessionModeMeasurement error:&outError];
[audioSession setActive:YES withOptions:AVAudioSessionSetActiveOptionNotifyOthersOnDeactivation error:&outError];
recognitionRequest = [[SFSpeechAudioBufferRecognitionRequest alloc]init];
AVAudioInputNode *inputNode = audioEngine.inputNode;
if (recognitionRequest == nil) {
NSLog(@"Unable to created a SFSpeechAudioBufferRecognitionRequest object");
}
if (inputNode == nil) {
NSLog(@"Audio engine has no input node ");}
//configure request so that results are returned before audio recording is finished
[recognitionRequest setShouldReportPartialResults:YES];
// A recognition task represents a speech recognition session.
//We keep a reference to the task so that it can be cancelled .
recognitionTask = [self.speechRecognizer recognitionTaskWithRequest:recognitionRequest resultHandler:^(SFSpeechRecognitionResult * result, NSError * error1) {
BOOL isFinal = false;
if ((result = result)) {
NSString *speech = result.bestTranscription.formattedString;
NSLog(@"the speech:%@",speech);
// coding for fixing append string issue
for (int i = 0 ;i <speechStringsArray.count;i++)
{
str = [speechStringsArray objectAtIndex:i];
NSRange range = [speech rangeOfString:str options:NSCaseInsensitiveSearch];
NSLog(@"found: %@", (range.location != NSNotFound) ? @"Yes" : @"No");
if (range.location != NSNotFound) {
resultString = [speech stringByReplacingCharactersInRange:range withString:@""];
speech = resultString;
NSLog(@" the result is : %@",resultString);
}
}
//specific functions - space for second word
if (resultString.length>0) {
self.textView.text = [NSString stringWithFormat:@"%@%@",self.textView.text,resultString];
[speechStringsArray addObject:resultString]; }
//specific function space for first word -Working fine
else
{
[speechStringsArray addObject:speech];
self.textView.text = speech;
}
}
NSLog(@" array %@",speechStringsArray);
isFinal = result.isFinal;
}
if (error1 != nil || isFinal) {
[audioEngine stop];
[inputNode removeTapOnBus:0];
recognitionRequest = nil;
recognitionTask = nil;
[self start_record];
}}];
AVAudioFormat *recordingFormat = [inputNode outputFormatForBus:0];
[inputNode installTapOnBus:0 bufferSize:1024 format:recordingFormat block:^(AVAudioPCMBuffer * _Nonnull buffer, AVAudioTime * _Nonnull when){
[recognitionRequest appendAudioPCMBuffer:buffer];}
];
NSError *error1;
[audioEngine prepare];
[audioEngine startAndReturnError:&error1];}
- (void)speakUtterance
{
NSLog(@"speakUtterance");
didStartSpeaking = NO;
textToSpeak = [NSString stringWithFormat:@"%@", self.textView.text];
AVSpeechUtterance *utterance = [[AVSpeechUtterance alloc] initWithString:textToSpeak];
utterance.rate = self.speedStepper.value;
utterance.pitchMultiplier = self.pitchStepper.value;
utterance.voice = self.voice;
[self.synthesizer speakUtterance:utterance];
[self displayBackgroundMediaFields];
}
- (void)displayBackgroundMediaFields
{
MPMediaItemArtwork *artwork = [[MPMediaItemArtwork alloc] initWithImage:[UIImage imageNamed:@"Play"]];
NSDictionary *info = @{ MPMediaItemPropertyTitle: self.textView.text,
MPMediaItemPropertyAlbumTitle: @"TextToSpeech App",
MPMediaItemPropertyArtwork: artwork};
[MPNowPlayingInfoCenter defaultCenter].nowPlayingInfo = info;
}
- (void)updateToolbar
{
if (self.synthesizer.speaking && !self.synthesizer.paused) {
[self updateToolbarWithButton:@"pause"];
}
else {
[self updateToolbarWithButton:@"play"];
}}
- (void)updateToolbarWithButton:(NSString *)buttonType
{
//stopping the speech to text process
if (audioEngine.isRunning) {
[audioEngine stop];
[recognitionRequest endAudio];
}
NSLog(@"updateToolbarWithButton: %@", buttonType);
UIBarButtonItem *audioControl;
if ([buttonType isEqualToString:@"play"]) {
// Play
audioControl = [[UIBarButtonItem alloc]initWithBarButtonSystemItem:UIBarButtonSystemItemPlay target:self action:@selector(handlePlayPauseButton:)];
}
else {
// Pause
audioControl = [[UIBarButtonItem alloc]initWithBarButtonSystemItem:UIBarButtonSystemItemPause target:self action:@selector(handlePlayPauseButton:)];
}
UIBarButtonItem *flexibleItem = [[UIBarButtonItem alloc] initWithBarButtonSystemItem:UIBarButtonSystemItemFlexibleSpace target:nil action:nil];
[self.toolbar setItems:@[flexibleItem, audioControl, flexibleItem]];
}
- (void)remoteControlReceivedWithEvent:(UIEvent *)receivedEvent
{
NSLog(@"receivedEvent: %@", receivedEvent);
if (receivedEvent.type == UIEventTypeRemoteControl) {
switch (receivedEvent.subtype) {
case UIEventSubtypeRemoteControlPlay:
NSLog(@"UIEventSubtypeRemoteControlPlay");
if (self.synthesizer.speaking) {
[self.synthesizer continueSpeaking];
}
else {
[self speakUtterance];
}
break;
case UIEventSubtypeRemoteControlPause:
NSLog(@"pause - UIEventSubtypeRemoteControlPause");
if (self.pauseSettingSegmentedControl.selectedSegmentIndex == 0) {
// Pause immediately
[self.synthesizer pauseSpeakingAtBoundary:AVSpeechBoundaryImmediate];
}
else {
// Pause at end of current word
[self.synthesizer pauseSpeakingAtBoundary:AVSpeechBoundaryWord];
}
break;
case UIEventSubtypeRemoteControlTogglePlayPause:
if (self.synthesizer.paused) {
NSLog(@"UIEventSubtypeRemoteControlTogglePlayPause");
[self.synthesizer continueSpeaking];
}
else {
NSLog(@"UIEventSubtypeRemoteControlTogglePlayPause");
if (self.pauseSettingSegmentedControl.selectedSegmentIndex == 0) {
// Pause immediately
[self.synthesizer pauseSpeakingAtBoundary:AVSpeechBoundaryImmediate];
}
else {
// Pause at end of current word
[self.synthesizer pauseSpeakingAtBoundary:AVSpeechBoundaryWord];
}
}
break;
case UIEventSubtypeRemoteControlNextTrack:
NSLog(@"UIEventSubtypeRemoteControlNextTrack - appropriate for playlists");
break;
case UIEventSubtypeRemoteControlPreviousTrack:
NSLog(@"UIEventSubtypeRemoteControlPreviousTrack - appropriatefor playlists");
break;
default:
break;
}
}
}
- (NSInteger)numberOfComponentsInPickerView:(UIPickerView *)pickerView
{
return 1;
}
- (NSInteger)pickerView:(UIPickerView *)pickerView numberOfRowsInComponent:(NSInteger)component
{
return self.voices.count;
}
- (UIView *)pickerView:(UIPickerView *)pickerView viewForRow:(NSInteger)row forComponent:(NSInteger)component reusingView:(UIView *)view
{
UILabel *rowLabel = [[UILabel alloc] init];
NSDictionary *voice = [self.voices objectAtIndex:row];
rowLabel.text = [voice objectForKey:@"label"];
return rowLabel;
}
- (void)pickerView:(UIPickerView *)pickerView didSelectRow: (NSInteger)row inComponent:(NSInteger)component
{
NSDictionary *voice = [self.voices objectAtIndex:row];
NSLog(@"new picker voice selected with label: %@", [voice objectForKey:@"label"]);
self.voice = [AVSpeechSynthesisVoice voiceWithLanguage:[voice objectForKey:@"voice"]];
}
- (void)speechSynthesizer:(AVSpeechSynthesizer *)synthesizer didFinishSpeechUtterance:(AVSpeechUtterance *)utterance
{
// This is a workaround of a bug. When we change the voice the first time the speech utterence is set fails silently. We check that the method willSpeakRangeOfSpeechString is called and set didStartSpeaking to YES there. If this method is not called (silent fail) then we simply request to speak again.
if (!didStartSpeaking) {
[self speakUtterance];
}
else {
[self updateToolbarWithButton:@"play"];
NSLog(@"the text are:%@",self.textView.text);
}}
- (void)speechSynthesizer:(AVSpeechSynthesizer *)synthesizer willSpeakRangeOfSpeechString:(NSRange)characterRange utterance:(AVSpeechUtterance *)utterance
{
didStartSpeaking = YES;
//[self setTextViewTextWithColoredCharacterRange:characterRange];
}
#pragma mark UITextViewDelegate Methods
- (BOOL)textView:(UITextView *)textView shouldChangeTextInRange:(NSRange)range replacementText:(NSString *)text {
if([text isEqualToString:@"\n"]) {
[textView resignFirstResponder];
return NO;
}
return YES;
}