iOS中 語音辨識功能／語音轉文字教程具體解釋 韓俊強的部落格

標籤：delegate   self   項目   res   link   val   nil   分享   nts   

原文地址：http://blog.csdn.net/qq_31810357/article/details/51111702

前言：近期研究了一下語音辨識，從百度語音辨識到訊飛語音辨識；首先說一下個人針對兩者的看法，訊飛毫無疑問比較專業。識別率也非常高真對語音辨識是比較精準的，可是非常多開發人員和我一樣期望離線識別，而訊飛離線是收費的；請求次數來講。兩者都能夠申請高配額，針對使用者較多的差點兒都一樣。

基於免費而且支援離線我選擇了百度離線語音辨識。比較簡單，UI設計多一點，以下寫一下教程：

1.首先：須要的庫

2.我是自己定義的UI所以以功能實現為主（標頭檔）

// 標頭檔#import "BDVRCustomRecognitonViewController.h"#import "BDVRClientUIManager.h"#import "WBVoiceRecordHUD.h"#import "BDVRViewController.h"#import "MyViewController.h"#import "BDVRSConfig.h"

3.須要知道的功能：能用到的例如以下：

//－－－－－－－－－－－－－－－－－－－類方法－－－－－－－－－－－－－－－－－－－－－－－－// 建立語音辨識客戶對像，該對像是個單例+ (BDVoiceRecognitionClient *)sharedInstance;// 釋放語音辨識用戶端對像+ (void)releaseInstance;//－－－－－－－－－－－－－－－－－－－識別方法－－－－－－－－－－－－－－－－－－－－－－－// 推斷能否夠錄音- (BOOL)isCanRecorder;// 開始語音辨識，須要實現MVoiceRecognitionClientDelegate代理方法。並傳入實現對像監聽事件// 傳回值參考 TVoiceRecognitionStartWorkResult- (int)startVoiceRecognition:(id<MVoiceRecognitionClientDelegate>)aDelegate;// 說完了，使用者主動完畢錄音時調用- (void)speakFinish;// 結束本次語音辨識- (void)stopVoiceRecognition;/** * @brief 擷取當前識別的採樣率 * * @return 採樣率(16000/8000) */- (int)getCurrentSampleRate;/** * @brief 得到當前識別模式(deprecated) * * @return 當前識別模式 */- (int)getCurrentVoiceRecognitionMode __attribute__((deprecated));/** * @brief 設定當前識別模式(deprecated)。請使用-(void)setProperty:(TBDVoiceRecognitionProperty)property; * * @param 識別模式 * * @return 是否設定成功 */- (void)setCurrentVoiceRecognitionMode:(int)aMode __attribute__((deprecated));// 設定識別類型- (void)setProperty:(TBDVoiceRecognitionProperty)property __attribute__((deprecated));// 擷取當前識別類型- (int)getRecognitionProperty __attribute__((deprecated));// 設定識別類型列表, 除EVoiceRecognitionPropertyInput和EVoiceRecognitionPropertySong外// 能夠識別類型複合- (void)setPropertyList: (NSArray*)prop_list;// cityID僅對EVoiceRecognitionPropertyMap識別類型有效- (void)setCityID: (NSInteger)cityID;// 擷取當前識別類型列表- (NSArray*)getRecognitionPropertyList;//－－－－－－－－－－－－－－－－－－－提示音－－－－－－－－－－－－－－－－－－－－－－－// 播放提示音。默覺得播放,錄音開始，錄音結束提示音// BDVoiceRecognitionClientResources/Tone// record_start.caf   錄音開始音效檔// record_end.caf     錄音結束音效檔// 聲音資源須要加到項目project裡。使用者可替換資源檔，檔案名稱不能夠變，建音提示音不宜過長，0。5秒左右。// aTone 取值參考 TVoiceRecognitionPlayTones，如沒有找到檔案。則返回ＮＯ- (BOOL)setPlayTone:(int)aTone isPlay:(BOOL)aIsPlay;

4.錄音button相關動畫（我自己定義的，大家能夠借鑒）

// 錄音button相關@property (nonatomic, weak, readonly) UIButton *holdDownButton;// 說話button/** *  是否取消錄音 */@property (nonatomic, assign, readwrite) BOOL isCancelled;/** *  是否正在錄音 */@property (nonatomic, assign, readwrite) BOOL isRecording;/** *  當錄音button被按下所觸發的事件，這時候是開始錄音 */- (void)holdDownButtonTouchDown;/** *  當手指在錄音button範圍之外離開螢幕所觸發的事件。這時候是取消錄音 */- (void)holdDownButtonTouchUpOutside;/** *  當手指在錄音button範圍之內離開螢幕所觸發的事件，這時候是完畢錄音 */- (void)holdDownButtonTouchUpInside;/** *  當手指滑動到錄音button的範圍之外所觸發的事件 */- (void)holdDownDragOutside;

5.初始化系統UI

#pragma mark - layout subViews UI/** *  依據正常顯示和高亮狀態建立一個button對象 * *  @param image   正常顯示圖 *  @param hlImage 高亮顯示圖 * *  @return 返回button對象 */- (UIButton *)createButtonWithImage:(UIImage *)image HLImage:(UIImage *)hlImage ;- (void)holdDownDragInside;- (void)createInitView; // 建立初始化介面。播放提示音時會用到- (void)createRecordView;  // 建立錄音介面- (void)createRecognitionView; // 建立識別介面- (void)createErrorViewWithErrorType:(int)aStatus; // 在識別view中顯示具體錯誤資訊- (void)createRunLogWithStatus:(int)aStatus; // 在狀態view中顯示具體狀態資訊- (void)finishRecord:(id)sender; // 使用者點擊完畢動作- (void)cancel:(id)sender; // 使用者點擊取消動作- (void)startVoiceLevelMeterTimer;- (void)freeVoiceLevelMeterTimerTimer;

6.最重要的部分

// 錄音完畢 [[BDVoiceRecognitionClient sharedInstance] speakFinish];

// 取消錄音[[BDVoiceRecognitionClient sharedInstance] stopVoiceRecognition];

7.兩個代理方法

- (void)VoiceRecognitionClientWorkStatus:(int)aStatus obj:(id)aObj{    switch (aStatus)    {        case EVoiceRecognitionClientWorkStatusFlushData: // 連續上屏中間結果        {            NSString *text = [aObj objectAtIndex:0];                        if ([text length] > 0)            {//                [clientSampleViewController logOutToContinusManualResut:text];                                UILabel *clientWorkStatusFlushLabel = [[UILabel alloc]initWithFrame:CGRectMake(kScreenWidth/2 - 100,64,200,60)];                clientWorkStatusFlushLabel.text = text;                clientWorkStatusFlushLabel.textAlignment = NSTextAlignmentCenter;                clientWorkStatusFlushLabel.font = [UIFont systemFontOfSize:18.0f];                clientWorkStatusFlushLabel.numberOfLines = 0;                clientWorkStatusFlushLabel.backgroundColor = [UIColor whiteColor];                [self.view addSubview:clientWorkStatusFlushLabel];                            }            break;        }        case EVoiceRecognitionClientWorkStatusFinish: // 識別正常完畢並獲得結果        {[self createRunLogWithStatus:aStatus];                        if ([[BDVoiceRecognitionClient sharedInstance] getRecognitionProperty] != EVoiceRecognitionPropertyInput)            {                //  搜尋模式下的結果為數組，示範範例為                // ["公園", "公元"]                NSMutableArray *audioResultData = (NSMutableArray *)aObj;                NSMutableString *tmpString = [[NSMutableString alloc] initWithString:@""];                                for (int i=0; i < [audioResultData count]; i++)                {                    [tmpString appendFormat:@"%@\r\n",[audioResultData objectAtIndex:i]];                }                                clientSampleViewController.resultView.text = nil;                [clientSampleViewController logOutToManualResut:tmpString];                            }            else            {                NSString *tmpString = [[BDVRSConfig sharedInstance] composeInputModeResult:aObj];                [clientSampleViewController logOutToContinusManualResut:tmpString];                            }                       if (self.view.superview)            {                [self.view removeFromSuperview];            }                        break;        }        case EVoiceRecognitionClientWorkStatusReceiveData:        {            // 此狀態僅僅有在輸入模式下使用            // 輸入模式下的結果為帶信賴度的結果，示比例如以下：            //  [            //      [            //         {            //             "百度" = "0.6055192947387695";            //         },            //         {            //             "擺渡" = "0.3625582158565521";            //         },            //      ]            //      [            //         {            //             "一下" = "0.7665404081344604";            //         }            //      ],            //   ]//臨時關掉 -- 否則影響跳轉結果//            NSString *tmpString = [[BDVRSConfig sharedInstance] composeInputModeResult:aObj];//            [clientSampleViewController logOutToContinusManualResut:tmpString];                        break;        }        case EVoiceRecognitionClientWorkStatusEnd: // 使用者說話完畢，等待server返回識別結果        {[self createRunLogWithStatus:aStatus];            if ([BDVRSConfig sharedInstance].voiceLevelMeter)            {                [self freeVoiceLevelMeterTimerTimer];            }            [self createRecognitionView];                        break;        }        case EVoiceRecognitionClientWorkStatusCancel:        {                        if ([BDVRSConfig sharedInstance].voiceLevelMeter)             {                [self freeVoiceLevelMeterTimerTimer];            }            [self createRunLogWithStatus:aStatus];                          if (self.view.superview)             {                [self.view removeFromSuperview];            }            break;        }        case EVoiceRecognitionClientWorkStatusStartWorkIng: // 識別庫開始識別工作，使用者能夠說話        {            if ([BDVRSConfig sharedInstance].playStartMusicSwitch) // 假設播放了提示音。此時再給使用者提示能夠說話            {                [self createRecordView];            }                        if ([BDVRSConfig sharedInstance].voiceLevelMeter)  // 開啟語音音量監聽            {                [self startVoiceLevelMeterTimer];            }            [self createRunLogWithStatus:aStatus];             break;        }case EVoiceRecognitionClientWorkStatusNone:case EVoiceRecognitionClientWorkPlayStartTone:case EVoiceRecognitionClientWorkPlayStartToneFinish:case EVoiceRecognitionClientWorkStatusStart:case EVoiceRecognitionClientWorkPlayEndToneFinish:case EVoiceRecognitionClientWorkPlayEndTone:{[self createRunLogWithStatus:aStatus];break;}        case EVoiceRecognitionClientWorkStatusNewRecordData:        {            break;        }        default:        {[self createRunLogWithStatus:aStatus];            if ([BDVRSConfig sharedInstance].voiceLevelMeter)             {                [self freeVoiceLevelMeterTimerTimer];            }            if (self.view.superview)             {                [self.view removeFromSuperview];            }             break;        }    }}

- (void)VoiceRecognitionClientNetWorkStatus:(int) aStatus{    switch (aStatus)     {        case EVoiceRecognitionClientNetWorkStatusStart:        {[self createRunLogWithStatus:aStatus];            [[UIApplication sharedApplication] setNetworkActivityIndicatorVisible:YES];            break;           }        case EVoiceRecognitionClientNetWorkStatusEnd:        {[self createRunLogWithStatus:aStatus];[[UIApplication sharedApplication] setNetworkActivityIndicatorVisible:NO];            break;           }              }}

8.錄音button的一些操作

#pragma mark ------ 關於button操作的一些事情-------- (void)holdDownButtonTouchDown {    // 開始動畫    _disPlayLink = [CADisplayLink displayLinkWithTarget:self selector:@selector(delayAnimation)];    _disPlayLink.frameInterval = 40;    [_disPlayLink addToRunLoop:[NSRunLoop currentRunLoop] forMode:NSDefaultRunLoopMode];        self.isCancelled = NO;    self.isRecording = NO;     // 開始語音辨識功能，之前必須實現MVoiceRecognitionClientDelegate協議中的VoiceRecognitionClientWorkStatus:obj方法    int startStatus = -1;    startStatus = [[BDVoiceRecognitionClient sharedInstance] startVoiceRecognition:self];    if (startStatus != EVoiceRecognitionStartWorking) // 建立失敗則報告錯誤    {        NSString *statusString = [NSString stringWithFormat:@"%d",startStatus];        [self performSelector:@selector(firstStartError:) withObject:statusString afterDelay:0.3];  // 延遲0.3秒。以便能在出錯時正常刪除view        return;    }    // "按住說話－鬆開搜尋"提示    [voiceImageStr removeFromSuperview];    voiceImageStr = [[UIImageView alloc]initWithFrame:CGRectMake(kScreenWidth/2 - 40, kScreenHeight - 153, 80, 33)];    voiceImageStr.backgroundColor = [UIColor colorWithPatternImage:[UIImage imageNamed:@"searchVoice"]];    [self.view addSubview:voiceImageStr];   }- (void)holdDownButtonTouchUpOutside {    // 結束動畫    [self.view.layer removeAllAnimations];    [_disPlayLink invalidate];    _disPlayLink = nil;        // 取消錄音    [[BDVoiceRecognitionClient sharedInstance] stopVoiceRecognition];        if (self.view.superview)    {        [self.view removeFromSuperview];    }}- (void)holdDownButtonTouchUpInside {    // 結束動畫    [self.view.layer removeAllAnimations];    [_disPlayLink invalidate];    _disPlayLink = nil;        [[BDVoiceRecognitionClient sharedInstance] speakFinish];}- (void)holdDownDragOutside {        //假設已經開始錄音了, 才須要做拖曳出去的動作, 否則僅僅要切換 isCancelled, 不讓錄音開始.    if (self.isRecording) {//        if ([self.delegate respondsToSelector:@selector(didDragOutsideAction)]) {//            [self.delegate didDragOutsideAction];//        }    } else {        self.isCancelled = YES;    }}#pragma mark - layout subViews UI- (UIButton *)createButtonWithImage:(UIImage *)image HLImage:(UIImage *)hlImage {    UIButton *button = [[UIButton alloc] initWithFrame:CGRectMake(kScreenWidth/2 -36, kScreenHeight - 120, 72, 72)];        if (image)        [button setBackgroundImage:image forState:UIControlStateNormal];    if (hlImage)        [button setBackgroundImage:hlImage forState:UIControlStateHighlighted];        return button;}#pragma mark ----------- 動畫部分 ------------ (void)startAnimation{    CALayer *layer = [[CALayer alloc] init];    layer.cornerRadius = [UIScreen mainScreen].bounds.size.width/2;    layer.frame = CGRectMake(0, 0, layer.cornerRadius * 2, layer.cornerRadius * 2);    layer.position = CGPointMake([UIScreen mainScreen].bounds.size.width/2,[UIScreen mainScreen].bounds.size.height - 84);    //    self.view.layer.position;    UIColor *color = [UIColor colorWithRed:arc4random()%10*0.1 green:arc4random()%10*0.1 blue:arc4random()%10*0.1 alpha:1];    layer.backgroundColor = color.CGColor;    [self.view.layer addSublayer:layer];        CAMediaTimingFunction *defaultCurve = [CAMediaTimingFunction functionWithName:kCAMediaTimingFunctionDefault];        _animaTionGroup = [CAAnimationGroup animation];    _animaTionGroup.delegate = self;    _animaTionGroup.duration = 2;    _animaTionGroup.removedOnCompletion = YES;    _animaTionGroup.timingFunction = defaultCurve;        CABasicAnimation *scaleAnimation = [CABasicAnimation animationWithKeyPath:@"transform.scale.xy"];    scaleAnimation.fromValue = @0.0;    scaleAnimation.toValue = @1.0;    scaleAnimation.duration = 2;        CAKeyframeAnimation *opencityAnimation = [CAKeyframeAnimation animationWithKeyPath:@"opacity"];    opencityAnimation.duration = 2;    opencityAnimation.values = @[@0.8,@0.4,@0];    opencityAnimation.keyTimes = @[@0,@0.5,@1];    opencityAnimation.removedOnCompletion = YES;        NSArray *animations = @[scaleAnimation,opencityAnimation];    _animaTionGroup.animations = animations;    [layer addAnimation:_animaTionGroup forKey:nil];        [self performSelector:@selector(removeLayer:) withObject:layer afterDelay:1.5];}- (void)removeLayer:(CALayer *)layer{    [layer removeFromSuperlayer];}- (void)delayAnimation{    [self startAnimation];}

完畢以上操作，就大功告成了！

溫馨提示：

1.因為是語音辨識，須要用到麥克風相關許可權。模擬器會爆12個錯誤。使用真機能夠解決；

2.涉及到授權檔案相關並不複雜，projectBundle Identifier僅僅須要設定百度的離線授權一致就可以。例如以：

終於效果例如以下：

有不懂或不明確的地方能夠微博聯絡我：

iOS開發人員交流群：446310206

iOS中 語音辨識功能／語音轉文字教程具體解釋 韓俊強的部落格