一、介绍

以前做过讯飞语音识别，比较简单，识别率很不错，但是它的识别时间是有限制的，最多60秒。可是有的时候我们需要更长的识别时间，例如朗诵古诗等功能。当然讯飞语音也是可以通过曲线救国来实现，就是每达到60秒时识别停止就立即重新开启，每次结束拼接录音。这么做，显然是麻烦的，百度语音解决了这个问题，它最近上线了长语音识别技术，可以不受时间限制，还是非常棒的。这次，我就专门抽成一个工具类使用，包括语音识别，录音拼接，录音播放、进度刷新，具体如何集成SDK看官方文档，我就不废话了，直接介绍如何使用我的这个工具类。

 

 

二、依赖

因为语音录制格式是pcm格式的，我使用lame静态库将其转成了mp3格式。

下载路径参考我的博客，有具体的介绍：

 

 

三、代码

SJVoiceTransform.h

#import 
      
       @interface SJVoiceTransform : NSObject/** *  根据路径将pcm文件转化为MP3 * *  @param docPath docment路径 */+(NSString *)stransformToMp3ByUrlWithUrl:(NSString *)docPath;@end
      

SJVoiceTransform.m

#import "SJVoiceTransform.h"#import "lame.h"@interface SJVoiceTransform()//@property (strong , nonatomic)NSString * path;//存放音频沙河路径@end@implementation SJVoiceTransform+(NSString *)stransformToMp3ByUrlWithUrl:(NSString *)docPath{    NSString *pathUrl = [NSString stringWithFormat:@"%@",docPath];//存储录音pcm格式音频地址    NSString * mp3Url = pathUrl;    NSString *mp3FilePath = [docPath stringByAppendingString:@".mp3"];//存放Mp3地址    if (!mp3Url || !mp3FilePath) {        return 0;    }    @try {        unsigned long read, write;        FILE *pcm = fopen([mp3Url cStringUsingEncoding:1], "rb"); //source 被转换的音频文件位置        //音频不能为空        if (!pcm) {            return nil;        }        fseek(pcm, 4*1024, SEEK_CUR); //skip file header        FILE *mp3 = fopen([mp3FilePath cStringUsingEncoding:1], "wb"); //output 输出生成的Mp3文件位置        const int PCM_SIZE = 8192;        const int MP3_SIZE = 8192;        short int pcm_buffer[PCM_SIZE*2];        unsigned char mp3_buffer[MP3_SIZE];        lame_t lame = lame_init();        lame_set_num_channels(lame,1);        lame_set_in_samplerate(lame, 8000.0); //11025.0        //lame_set_VBR(lame, vbr_default);        lame_set_brate(lame, 8);        lame_set_mode(lame, 3);        lame_set_quality(lame, 2);//        lame_init_params(lame);        do {            read = fread(pcm_buffer, 2*sizeof(short int), PCM_SIZE, pcm);            if (read == 0)                write = lame_encode_flush(lame, mp3_buffer, MP3_SIZE);            else                write = lame_encode_buffer_interleaved(lame, pcm_buffer, read, mp3_buffer, MP3_SIZE);            fwrite(mp3_buffer, write, 1, mp3);        } while (read != 0);        lame_close(lame);        fclose(mp3);        fclose(pcm);    }    @catch (NSException *exception) {        NSLog(@"%@",[exception description]);    }    @finally {        NSLog(@"MP3生成成功: %@",mp3FilePath);    }    return mp3FilePath;}@end

BDHelper.h

////  BDHelper.h//  BDRecognizer////  Created by 夏远全 on 2017/11/14.//  Copyright © 2017年 夏远全. All rights reserved.#import 
      
       #import 
       
        #import 
        
         #import 
         
          @protocol BDHelperDelegate 
          
           @optional-(void)recognitionPartialResult:(NSString *)recognitionResult; //中间结果-(void)recognitionFinalResult:(NSString *)recognitionResult;   //最终结果-(void)recognitionError:(NSError *)error;                      //识别错误-(void)updateProgress:(CGFloat)progress duration:(int)duration;//更新播放进度-(void)updateReadingTime:(int)readingTime;//更新朗诵时间-(void)recognitionRecordFinishedPlay;//语音识别录音播放完成@end@interface BDHelper : NSObject/** 代理 */@property (nonatomic,   weak) id
           
             delegate;/** 播放器 */@property (nonatomic, strong) AVAudioPlayer *audioPlayer;/** 文件路径 */@property (nonatomic, copy) NSString *audioFilePath;/** 创建对象 @param voiceFileName 录音文件名 @return 实例 */+(BDHelper *)sharedBDHelperWithVoiceFileName:(NSString *)voiceFileName;/** 开始语音识别 */- (void)startLongSpeechRecognition;/** 结束语音识别 */- (void)endLongSpeechRecognition;/** 播放识别语音 */-(void)playListenningRecognition;/** 暂停语音播放 */-(void)pauseListenningRecognition;/** @param isNeedDeleteFilePath 是否需要移除缓存的音频文件 销毁播放器 */-(void)didRemoveAudioPlayer:(BOOL)isNeedDeleteFilePath;/** 启动计时器，累计朗诵时间 */- (void)beginStatisticsReadingTime;/** 销毁计时器 */- (void)endStatisticsReadingTime;@end
           
          
         
        
       
      

BDHelper.m

////  BDHelper.m//  BDRecognizer////  Created by 夏远全 on 2017/11/14.//  Copyright © 2017年 夏远全. All rights reserved.//#import "BDHelper.h"#import "SJVoiceTransform.h"#if !TARGET_IPHONE_SIMULATOR#import "BDSEventManager.h"#import "BDSASRDefines.h"#import "BDSASRParameters.h"/// "请在官网新建应用，配置包名，并在此填写应用的 api key, secret key, appid(即appcode)"static NSString* const API_KEY    =     @"BxLweqmGUxxxxxxxxxxxxxx";static NSString* const SECRET_KEY = @"rhUIXG4gXmxxxxxxxxxxxxxx";static NSString* const APP_ID     =     @"81xxxxx";@interface BDHelper()
      
       @property (nonatomic, strong) BDSEventManager      *asrEventManager;@property (nonatomic, strong) CADisplayLink        *progressLink;@property (nonatomic, strong) NSTimer              *readingTimer;@property (nonatomic, strong) NSMutableData        *mutabelData;@property (nonatomic, strong) NSFileHandle         *fileHandler;@property (nonatomic,   copy) NSString             *voiceFileName;@end#endif@implementation BDHelper#if !TARGET_IPHONE_SIMULATOR+(BDHelper *)sharedBDHelperWithVoiceFileName:(NSString *)voiceFileName{    BDHelper *helper = [[self alloc] init];    helper.voiceFileName = voiceFileName;    [helper setupDefalutValue];    return helper;}-(void)setupDefalutValue{    self.asrEventManager = [BDSEventManager createEventManagerWithName:BDS_ASR_NAME];    [self configVoiceRecognitionClient];    NSLog(@"current sdk version: %@", [self.asrEventManager libver]);    }#pragma mark - public: Method- (void)startLongSpeechRecognition{        //移除播放器    [self didRemoveAudioPlayer:NO];        //设置录音路径    if (!_audioFilePath) {        [self pcmFilePathConfig];    }        //启动识别服务    [self beginStatisticsReadingTime];    [self.asrEventManager sendCommand:BDS_ASR_CMD_START];}- (void)endLongSpeechRecognition{        //关闭识别服务    [self endStatisticsReadingTime];    [self.asrEventManager sendCommand:BDS_ASR_CMD_STOP];    [self.fileHandler writeData:self.mutabelData];    self.mutabelData = nil;    }-(void)playListenningRecognition{        //避免重复点击    if (_audioPlayer && _audioPlayer.isPlaying) {        return;    }        //直接播放    if (_audioPlayer && !_audioPlayer.isPlaying) {        [_audioPlayer play];         _progressLink.paused = NO;        return;    }        //播放识别语音(pcm格式转成mp3格式)    NSString *mp3Path = [SJVoiceTransform stransformToMp3ByUrlWithUrl:_audioFilePath];    if (!mp3Path) {        return;    }    //初始化播放器    _audioPlayer = [[AVAudioPlayer alloc]initWithContentsOfURL:[NSURL fileURLWithPath:mp3Path] error:NULL];    _audioPlayer.volume = 1;    _audioPlayer.delegate = self;    [[AVAudioSession sharedInstance] setCategory:AVAudioSessionCategoryPlayback error:nil];    [[AVAudioSession sharedInstance] setActive:YES error:nil];    [_audioPlayer prepareToPlay];    [_audioPlayer play];    _progressLink = [CADisplayLink displayLinkWithTarget:self selector:@selector(updateProgressValue)];    [_progressLink addToRunLoop:[NSRunLoop currentRunLoop] forMode:NSRunLoopCommonModes];}-(void)pauseListenningRecognition{    //暂停播放    if (_audioPlayer && _audioPlayer.isPlaying) {        [_audioPlayer pause];        _progressLink.paused = YES;    }}#pragma mark - event-(void)updateProgressValue{        //更新播放进度    int duration = round(_audioPlayer.duration);    if (self.delegate && [self.delegate respondsToSelector:@selector(updateProgress:duration:)]) {        [self.delegate updateProgress:_audioPlayer.currentTime/_audioPlayer.duration duration:duration];    }}-(void)startReadingTimer{        //累计朗诵时间    if (self.delegate && [self.delegate respondsToSelector:@selector(updateReadingTime:)]) {        [self.delegate updateReadingTime:1];    }}#pragma mark - Private: Configuration- (void)configVoiceRecognitionClient {        // ---- 设置DEBUG_LOG的级别    [self.asrEventManager setParameter:@(EVRDebugLogLevelTrace) forKey:BDS_ASR_DEBUG_LOG_LEVEL];        // ---- 配置API_KEY 和 SECRET_KEY 和 APP_ID    [self.asrEventManager setParameter:@[API_KEY, SECRET_KEY] forKey:BDS_ASR_API_SECRET_KEYS];    [self.asrEventManager setParameter:APP_ID forKey:BDS_ASR_OFFLINE_APP_CODE];        // ---- 配置端点检测（二选一）    [self configModelVAD];    //[self configDNNMFE];        // ---- 语义与标点 -----    [self enableNLU];    [self enablePunctuation];        // ---- 长语音请务必开启本地VAD -----    [self.asrEventManager setParameter:@(YES) forKey:BDS_ASR_ENABLE_LONG_SPEECH];    [self.asrEventManager setParameter:@(YES) forKey:BDS_ASR_ENABLE_LOCAL_VAD];        // ---- 录音文件路径 -----    [self pcmFilePathConfig];        // ---- 设置代理 -----    [self.asrEventManager setDelegate:self];    [self.asrEventManager setParameter:nil forKey:BDS_ASR_AUDIO_FILE_PATH];    [self.asrEventManager setParameter:nil forKey:BDS_ASR_AUDIO_INPUT_STREAM];}- (void)pcmFilePathConfig{    [self configFileHandler:self.voiceFileName];    _audioFilePath = [self getFilePath:self.voiceFileName];}- (void)enableNLU {        // ---- 开启语义理解 -----    [self.asrEventManager setParameter:@(YES) forKey:BDS_ASR_ENABLE_NLU];    [self.asrEventManager setParameter:@"15361" forKey:BDS_ASR_PRODUCT_ID];}- (void)enablePunctuation {        // ---- 开启标点输出 -----    [self.asrEventManager setParameter:@(NO) forKey:BDS_ASR_DISABLE_PUNCTUATION];        // ---- 普通话标点 -----    [self.asrEventManager setParameter:@"1537" forKey:BDS_ASR_PRODUCT_ID];}- (void)configModelVAD {    NSString *modelVAD_filepath = [[NSBundle mainBundle] pathForResource:@"bds_easr_basic_model" ofType:@"dat"];    [self.asrEventManager setParameter:modelVAD_filepath forKey:BDS_ASR_MODEL_VAD_DAT_FILE];    [self.asrEventManager setParameter:@(YES) forKey:BDS_ASR_ENABLE_MODEL_VAD];}- (void)configDNNMFE {        NSString *mfe_dnn_filepath = [[NSBundle mainBundle] pathForResource:@"bds_easr_mfe_dnn" ofType:@"dat"];    NSString *cmvn_dnn_filepath = [[NSBundle mainBundle] pathForResource:@"bds_easr_mfe_cmvn" ofType:@"dat"];    [self.asrEventManager setParameter:mfe_dnn_filepath forKey:BDS_ASR_MFE_DNN_DAT_FILE];    [self.asrEventManager setParameter:cmvn_dnn_filepath forKey:BDS_ASR_MFE_CMVN_DAT_FILE];        //自定义静音时长（单位：每帧10ms）    //[self.asrEventManager setParameter:@(500) forKey:BDS_ASR_MFE_MAX_SPEECH_PAUSE];    //[self.asrEventManager setParameter:@(501) forKey:BDS_ASR_MFE_MAX_WAIT_DURATION];}#pragma mark - MVoiceRecognitionClientDelegate- (void)VoiceRecognitionClientWorkStatus:(int)workStatus obj:(id)aObj {        switch (workStatus) {        case EVoiceRecognitionClientWorkStatusNewRecordData: {            /// 录音数据回调、NSData-原始音频数据，此处可以用来存储录音            NSData *originData = (NSData *)aObj;            [self.mutabelData appendData:originData];            break;        }        case EVoiceRecognitionClientWorkStatusStartWorkIng: {            /// 识别工作开始，开始采集及处理数据            NSDictionary *logDic = [self parseLogToDic:aObj];            NSLog(@"%@",[NSString stringWithFormat:@"CALLBACK: start vr, log: %@\n", logDic]);            break;        }        case EVoiceRecognitionClientWorkStatusStart: {            /// 检测到用户开始说话            NSLog(@"CALLBACK: detect voice start point.\n");            break;        }        case EVoiceRecognitionClientWorkStatusEnd: {            /// 本地声音采集结束            NSLog(@"CALLBACK: detect voice end point.\n");            break;        }        case EVoiceRecognitionClientWorkStatusFlushData: {            /// 连续上屏、NSDictionary-中间结果            NSString *result = [self getDescriptionForDic:aObj];            NSLog(@"%@",[NSString stringWithFormat:@"CALLBACK: partial result -%@.\n\n" ,result]);            NSMutableString *recognitionResult = [aObj[@"results_recognition"] firstObject];            if (self.delegate && [self.delegate respondsToSelector:@selector(recognitionPartialResult:)]) {                [self.delegate recognitionPartialResult:recognitionResult];            }            break;        }        case EVoiceRecognitionClientWorkStatusFinish: {            /// 语音识别功能完成，服务器返回正确结果、NSDictionary-最终识别结果            NSString *result = [self getDescriptionForDic:aObj];            NSLog(@"%@",[NSString stringWithFormat:@"CALLBACK: final result - %@.\n\n",result]);                        NSString *recognitionResult = [aObj[@"results_recognition"] firstObject];            if (self.delegate && [self.delegate respondsToSelector:@selector(recognitionFinalResult:)]) {                [self.delegate recognitionFinalResult:recognitionResult];            }            break;        }        case EVoiceRecognitionClientWorkStatusMeterLevel: {            /// 当前音量回调、NSNumber:int-当前音量            NSLog(@"-------voice volume:%d-------",[aObj intValue]);            break;        }        case EVoiceRecognitionClientWorkStatusCancel: {            /// 用户主动取消            NSLog(@"CALLBACK: user press cancel.\n");            break;        }        case EVoiceRecognitionClientWorkStatusError: {            /// 发生错误 NSError-错误信息            NSLog(@"%@", [NSString stringWithFormat:@"CALLBACK: encount error - %@.\n", (NSError *)aObj]);            if (self.delegate && [self.delegate respondsToSelector:@selector(recognitionError:)]) {                [self.delegate recognitionError:(NSError *)aObj];            }            break;        }        case EVoiceRecognitionClientWorkStatusLoaded: {            /// 离线引擎加载完成            NSLog(@"CALLBACK: offline engine loaded.\n");            break;        }        case EVoiceRecognitionClientWorkStatusUnLoaded: {            /// 离线引擎卸载完成            NSLog(@"CALLBACK: offline engine unLoaded.\n");            break;        }        case EVoiceRecognitionClientWorkStatusChunkThirdData: {            /// CHUNK: 识别结果中的第三方数据  NSData            NSLog(@"%@",[NSString stringWithFormat:@"CALLBACK: Chunk 3-party data length: %lu\n", (unsigned long)[(NSData *)aObj length]]);            break;        }        case EVoiceRecognitionClientWorkStatusChunkNlu: {            /// CHUNK: 识别结果中的语义结果  NSData            NSString *nlu = [[NSString alloc] initWithData:(NSData *)aObj encoding:NSUTF8StringEncoding];            NSLog(@"%@",[NSString stringWithFormat:@"CALLBACK: Chunk NLU data: %@\n", nlu]);            break;        }        case EVoiceRecognitionClientWorkStatusChunkEnd: {            /// CHUNK: 识别过程结束 NSString            NSLog(@"%@",[NSString stringWithFormat:@"CALLBACK: Chunk end, sn: %@.\n", aObj]);            break;        }        case EVoiceRecognitionClientWorkStatusFeedback: {            /// Feedback: 识别过程反馈的打点数据 NSString            NSDictionary *logDic = [self parseLogToDic:aObj];            NSLog(@"%@",[NSString stringWithFormat:@"CALLBACK Feedback: %@\n", logDic]);            break;        }        case EVoiceRecognitionClientWorkStatusRecorderEnd: {            /// 录音机关闭，页面跳转需检测此时间，规避状态条 (iOS)            NSLog(@"CALLBACK: recorder closed.\n");            break;        }        case EVoiceRecognitionClientWorkStatusLongSpeechEnd: {            /// 长语音结束状态            NSLog(@"CALLBACK: Long Speech end.\n");            [self endLongSpeechRecognition];            break;        }        default:            break;    }}#pragma mark - AVAudioPlayerDelegate-(void)audioPlayerDidFinishPlaying:(AVAudioPlayer *)player successfully:(BOOL)flag{    if (flag) {        if (self.delegate && [self.delegate respondsToSelector:@selector(recognitionRecordFinishedPlay)]) {            [self.delegate recognitionRecordFinishedPlay];        }    }}#pragma mark - public: Method-(void)didRemoveAudioPlayer:(BOOL)isNeedDeleteFilePath{        [_audioPlayer  stop];    [_progressLink invalidate];    _audioPlayer = nil;    _progressLink = nil;        if (isNeedDeleteFilePath) {        [[NSFileManager defaultManager] removeItemAtPath:_audioFilePath error:nil];        _audioFilePath = nil;    }}- (void)beginStatisticsReadingTime{    [self.readingTimer fire];}- (void)endStatisticsReadingTime{    if (self.readingTimer.isValid) {        [self.readingTimer invalidate];        self.readingTimer = nil;    }}#pragma mark - private: Method- (NSDictionary *)parseLogToDic:(NSString *)logString{    NSArray *tmp = NULL;    NSMutableDictionary *logDic = [[NSMutableDictionary alloc] initWithCapacity:3];    NSArray *items = [logString componentsSeparatedByString:@"&"];    for (NSString *item in items) {        tmp = [item componentsSeparatedByString:@"="];        if (tmp.count == 2) {            [logDic setObject:tmp.lastObject forKey:tmp.firstObject];        }    }    return logDic;}- (NSString *)getDescriptionForDic:(NSDictionary *)dic {    if (dic) {        return [[NSString alloc] initWithData:[NSJSONSerialization dataWithJSONObject:dic                                                                              options:NSJSONWritingPrettyPrinted                                                                                error:nil]                                     encoding:NSUTF8StringEncoding];    }    return nil;}#pragma mark - Private: File- (NSString *)getFilePath:(NSString *)fileName {    NSArray *paths = NSSearchPathForDirectoriesInDomains(NSDocumentDirectory, NSUserDomainMask, YES);    if (paths && [paths count]) {        return [[paths objectAtIndex:0] stringByAppendingPathComponent:fileName];    } else {        return nil;    }}- (void)configFileHandler:(NSString *)fileName {    self.fileHandler = [self createFileHandleWithName:fileName isAppend:NO];}- (NSFileHandle *)createFileHandleWithName:(NSString *)aFileName isAppend:(BOOL)isAppend {        NSFileHandle *fileHandle = nil;    NSString *fileName = [self getFilePath:aFileName];    int fd = -1;    if (fileName) {        if ([[NSFileManager defaultManager] fileExistsAtPath:fileName]&& !isAppend) {            [[NSFileManager defaultManager] removeItemAtPath:fileName error:nil];        }        int flags = O_WRONLY | O_APPEND | O_CREAT;        fd = open([fileName fileSystemRepresentation], flags, 0644);    }    if (fd != -1) {        fileHandle = [[NSFileHandle alloc] initWithFileDescriptor:fd closeOnDealloc:YES];    }    return fileHandle;}#pragma mark - lazy load-(NSMutableData *)mutabelData{    if (!_mutabelData) {        _mutabelData = [NSMutableData data];    }    return _mutabelData;}-(NSTimer *)readingTimer{    if (!_readingTimer) {        _readingTimer = [NSTimer scheduledTimerWithTimeInterval:1.0 target:self selector:@selector(startReadingTimer) userInfo:nil repeats:YES];        [[NSRunLoop currentRunLoop] addTimer:_readingTimer forMode:UITrackingRunLoopMode];    }    return _readingTimer;}#endif@end
      

 

 

四、注意

百度语音SDK只支持armv6、armv7的真机架构，不支持x86_64模拟器架构。

 

 

五、如何在模拟器下开发

办法：

1、首先将涉及到百度语音的代码全部采用宏定义注释掉，如：

#if !TARGET_IPHONE_SIMULATOR// 语音相关调用// self.asrEventManager = [BDSEventManager createEventManagerWithName:BDS_ASR_NAME];// 其他调用#endif

2、（重点要处理的地方）切换到模拟时，将libBaiduSpeechSDK.a静态包从Linked Frameworks and Librarise删掉(切换到真机时，再将libBaiduSpeechSDK.a导入进来就行)