AudioUnitaudio发生器在每个音调结束时给我一个唧唧声
我正在为旧的GWBasic PLAY命令创build一个老派的音乐模拟器。 为此，我有一个音源和音乐播放器。 在演奏的每一个音符之间，我都会听到唧唧喳喳的声音。 以下是我的两个类：
ToneGen.h
#import <Foundation/Foundation.h> @interface ToneGen : NSObject @property (nonatomic) id delegate; @property (nonatomic) double frequency; @property (nonatomic) double sampleRate; @property (nonatomic) double theta; - (void)play:(float)ms; - (void)play; - (void)stop; @end
ToneGen.m
#import <AudioUnit/AudioUnit.h> #import "ToneGen.h" OSStatus RenderTone( void *inRefCon, AudioUnitRenderActionFlags *ioActionFlags, const AudioTimeStamp *inTimeStamp, UInt32 inBusNumber, UInt32 inNumberFrames, AudioBufferList *ioData); void ToneInterruptionListener(void *inClientData, UInt32 inInterruptionState); @interface ToneGen() @property (nonatomic) AudioComponentInstance toneUnit; @property (nonatomic) NSTimer *timer; - (void)createToneUnit; @end @implementation ToneGen @synthesize toneUnit = _toneUnit; @synthesize timer = _timer; @synthesize delegate = _delegate; @synthesize frequency = _frequency; @synthesize sampleRate = _sampleRate; @synthesize theta = _theta; - (id) init { self = [super init]; if (self) { self.sampleRate = 44100; self.frequency = 1440.0f; return self; } return nil; } - (void)play:(float)ms { [self play]; self.timer = [NSTimer scheduledTimerWithTimeInterval:(ms / 100) target:self selector:@selector(stop) userInfo:nil repeats:NO]; [[NSRunLoop mainRunLoop] addTimer:self.timer forMode:NSRunLoopCommonModes]; } - (void)play { if (!self.toneUnit) { [self createToneUnit]; // Stop changing parameters on the unit OSErr err = AudioUnitInitialize(self.toneUnit); if (err) DLog(@"Error initializing unit"); // Start playback err = AudioOutputUnitStart(self.toneUnit); if (err) DLog(@"Error starting unit"); } } - (void)stop { [self.timer invalidate]; self.timer = nil; if (self.toneUnit) { AudioOutputUnitStop(self.toneUnit); AudioUnitUninitialize(self.toneUnit); AudioComponentInstanceDispose(self.toneUnit); self.toneUnit = nil; } if(self.delegate && [self.delegate respondsToSelector:@selector(toneStop)]) { [self.delegate performSelector:@selector(toneStop)]; } } - (void)createToneUnit { AudioComponentDescription defaultOutputDescription; defaultOutputDescription.componentType = kAudioUnitType_Output; defaultOutputDescription.componentSubType = kAudioUnitSubType_DefaultOutput; defaultOutputDescription.componentManufacturer = kAudioUnitManufacturer_Apple; defaultOutputDescription.componentFlags = 0; defaultOutputDescription.componentFlagsMask = 0; // Get the default playback output unit AudioComponent defaultOutput = AudioComponentFindNext(NULL, &defaultOutputDescription); if (!defaultOutput) DLog(@"Can't find default output"); // Create a new unit based on this that we'll use for output OSErr err = AudioComponentInstanceNew(defaultOutput, &_toneUnit); if (err) DLog(@"Error creating unit"); // Set our tone rendering function on the unit AURenderCallbackStruct input; input.inputProc = RenderTone; input.inputProcRefCon = (__bridge void*)self; err = AudioUnitSetProperty(self.toneUnit, kAudioUnitProperty_SetRenderCallback, kAudioUnitScope_Input, 0, &input, sizeof(input)); if (err) DLog(@"Error setting callback"); // Set the format to 32 bit, single channel, floating point, linear PCM const int four_bytes_per_float = 4; const int eight_bits_per_byte = 8; AudioStreamBasicDescription streamFormat; streamFormat.mSampleRate = self.sampleRate; streamFormat.mFormatID = kAudioFormatLinearPCM; streamFormat.mFormatFlags = kAudioFormatFlagsNativeFloatPacked | kAudioFormatFlagIsNonInterleaved; streamFormat.mBytesPerPacket = four_bytes_per_float; streamFormat.mFramesPerPacket = 1; streamFormat.mBytesPerFrame = four_bytes_per_float; streamFormat.mChannelsPerFrame = 1; streamFormat.mBitsPerChannel = four_bytes_per_float * eight_bits_per_byte; err = AudioUnitSetProperty (self.toneUnit, kAudioUnitProperty_StreamFormat, kAudioUnitScope_Input, 0, &streamFormat, sizeof(AudioStreamBasicDescription)); if (err) DLog(@"Error setting stream format"); } @end OSStatus RenderTone( void *inRefCon, AudioUnitRenderActionFlags *ioActionFlags, const AudioTimeStamp *inTimeStamp, UInt32 inBusNumber, UInt32 inNumberFrames, AudioBufferList *ioData) { // Fixed amplitude is good enough for our purposes const double amplitude = 0.25; // Get the tone parameters out of the view controller ToneGen *toneGen = (__bridge ToneGen *)inRefCon; double theta = toneGen.theta; double theta_increment = 2.0 * M_PI * toneGen.frequency / toneGen.sampleRate; // This is a mono tone generator so we only need the first buffer const int channel = 0; Float32 *buffer = (Float32 *)ioData->mBuffers[channel].mData; // Generate the samples for (UInt32 frame = 0; frame < inNumberFrames; frame++) { buffer[frame] = sin(theta) * amplitude; theta += theta_increment; if (theta > 2.0 * M_PI) { theta -= 2.0 * M_PI; } } // Store the theta back in the view controller toneGen.theta = theta; return noErr; } void ToneInterruptionListener(void *inClientData, UInt32 inInterruptionState) { ToneGen *toneGen = (__bridge ToneGen *)inClientData; [toneGen stop]; }
Music.h
#import <Foundation/Foundation.h> @interface Music : NSObject - (void) play:(NSString *)music; - (void) stop; @end
Music.m
#import "Music.h" #import "ToneGen.h" @interface Music() @property (nonatomic, readonly) ToneGen *toneGen; @property (nonatomic, assign) int octive; @property (nonatomic, assign) int tempo; @property (nonatomic, assign) int length; @property (nonatomic, strong) NSData *music; @property (nonatomic, assign) int dataPos; @property (nonatomic, assign) BOOL isPlaying; - (void)playNote; @end @implementation Music @synthesize toneGen = _toneGen; - (ToneGen*)toneGen { if (_toneGen == nil) { _toneGen = [[ToneGen alloc] init]; _toneGen.delegate = self; } return _toneGen; } @synthesize octive = _octive; - (void)setOctive:(int)octive { // Sinity Check if (octive < 0) octive = 0; if (octive > 6) octive = 6; _octive = octive; } @synthesize tempo = _tempo; - (void)setTempo:(int)tempo { // Sinity Check if (tempo < 30) tempo = 30; if (tempo > 255) tempo = 255; _tempo = tempo; } @synthesize length = _length; - (void)setLength:(int)length { // Sinity Check if (length < 1) length = 1; if (length > 64) length = 64; _length = length; } @synthesize music = _music; @synthesize dataPos = _dataPos; @synthesize isPlaying = _isPlaying; - (id)init { self = [super init]; if (self) { self.octive = 4; self.tempo = 120; self.length = 1; return self; } return nil; } - (void) play:(NSString *)music { DLog(@"%@", music); self.music = [[music stringByReplacingOccurrencesOfString:@"+" withString:@"#"] dataUsingEncoding: NSASCIIStringEncoding]; self.dataPos = 0; self.isPlaying = YES; [self playNote]; } - (void)stop { self.isPlaying = NO; } - (void)playNote { if (!self.isPlaying) return; if (self.dataPos > self.music.length || self.music.length == 0) { self.isPlaying = NO; return; } unsigned char *data = (unsigned char*)[self.music bytes]; unsigned int code = (unsigned int)data[self.dataPos]; self.dataPos++; switch (code) { case 65: // A case 66: // B case 67: // C case 68: // D case 69: // E case 70: // F case 71: // G { // Peak at the next char to look for sharp or flat bool sharp = NO; bool flat = NO; if (self.dataPos < self.music.length) { unsigned int peak = (unsigned int)data[self.dataPos]; if (peak == 35) // # { self.dataPos++; sharp = YES; } else if (peak == 45) // - { self.dataPos++; flat = YES; } } // Peak ahead for a length changes bool look = YES; int count = 0; int newLength = 0; while (self.dataPos < self.music.length && look) { unsigned int peak = (unsigned int)data[self.dataPos]; if (peak >= 48 && peak <= 57) { peak -= 48; int n = (count * 10); if (n == 0) { n = 1; } newLength += peak * n; self.dataPos++; } else { look = NO; } } // Pick the note length int length = self.length; if (newLength != 0) { DLog(@"InlineLength: %d", newLength); length = newLength; } // Create the note string NSString *note = [NSString stringWithFormat:@"%c", code]; if (sharp) note = [note stringByAppendingFormat:@"#"]; else if (flat) note = [note stringByAppendingFormat:@"-"]; // Set the tone generator freq [self setFreq:[self getNoteNumber:note]]; // Play the note [self.toneGen play:(self.tempo / length)]; } break; case 76: // L (length) { bool look = YES; int newLength = 0; while (self.dataPos < self.music.length && look) { unsigned int peak = (unsigned int)data[self.dataPos]; if (peak >= 48 && peak <= 57) { peak -= 48; newLength = newLength * 10 + peak; self.dataPos++; } else { look = NO; } } self.length = newLength; DLog(@"Length: %d", self.length); [self playNote]; } break; case 79: // O (octive) { bool look = YES; int newOctive = 0; while (self.dataPos < self.music.length && look) { unsigned int peak = (unsigned int)data[self.dataPos]; if (peak >= 48 && peak <= 57) { peak -= 48; newOctive = newOctive * 10 + peak; self.dataPos++; } else { look = NO; } } self.octive = newOctive; DLog(@"Octive: %d", self.self.octive); [self playNote]; } break; case 84: // T (tempo) { bool look = YES; int newTempo = 0; while (self.dataPos < self.music.length && look) { unsigned int peak = (unsigned int)data[self.dataPos]; if (peak >= 48 && peak <= 57) { peak -= 48; newTempo = newTempo * 10 + peak; self.dataPos++; } else { look = NO; } } self.tempo = newTempo; DLog(@"Tempo: %d", self.self.tempo); [self playNote]; } break; default: [self playNote]; break; } } - (int)getNoteNumber:(NSString*)note { note = [note uppercaseString]; DLog(@"%@", note); if ([note isEqualToString:@"A"]) return 0; else if ([note isEqualToString:@"A#"] || [note isEqualToString:@"B-"]) return 1; else if ([note isEqualToString:@"B"] || [note isEqualToString:@"C-"]) return 2; else if ([note isEqualToString:@"C"] || [note isEqualToString:@"B#"]) return 3; else if ([note isEqualToString:@"C#"] || [note isEqualToString:@"D-"]) return 4; else if ([note isEqualToString:@"D"]) return 5; else if ([note isEqualToString:@"D#"] || [note isEqualToString:@"E-"]) return 6; else if ([note isEqualToString:@"E"] || [note isEqualToString:@"F-"]) return 7; else if ([note isEqualToString:@"F"] || [note isEqualToString:@"E#"]) return 8; else if ([note isEqualToString:@"F#"] || [note isEqualToString:@"G-"]) return 9; else if ([note isEqualToString:@"G"]) return 10; else if ([note isEqualToString:@"G#"]) return 11; } - (void)setFreq:(int)note { float a = powf(2, self.octive); float b = powf(1.059463, note); float freq = roundf((275.0 * a * b) / 10); self.toneGen.frequency = freq; } - (void)toneStop { [self playNote]; } @end
玩小调创build一个Music对象，并播放…
[self.music play:@"T180 DF#A L2 A L4 O4 AA P4 F#F# P4 O3 D DF#A L2 A L4 O4 AA P4 GG P4 O3 C#C#EB L2 B L4 O4 BB P4 GG P4 O3 C#C#EB L2 B L4 O4 BB P4 F+F+ P4 O3 DDF#A L2 O4 D L4 O5 DD P4O4 AA P4 O3 DDF#A L2 O4 D L4 O5 DD P4O4 BB P4 EEG L8 B P8 ML B1 L4 MN G#A ML L3 O5 F#1L4 MN D O4 F# ML L2 F# MN L4 E ML L2 B MN L4 AD P8 D8 D4"];
任何想法如何消除音符之间的啁啾？
我认为在音符之间停止audio输出的位是罪魁祸首：
if (self.toneUnit) { AudioOutputUnitStop(self.toneUnit); AudioUnitUninitialize(self.toneUnit); AudioComponentInstanceDispose(self.toneUnit); self.toneUnit = nil; }
只要让音调单位保持活跃状态，你就不会唧唧喳喳。 您需要一些其他的方式来产生沉默，可能通过让RenderTone继续运行，但生成零幅度。
我能够消除因频率变化而产生的轻微啁啾声，使幅度衰减到无，更新频率，并再次消失。 这当然是老式的电脑音箱所不能做到的（除了less数几个人再次快速切换音箱），但是如果没有了啁啾声，那么很快就会失去老派的效果。
这是我的衰落RenderTone函数（目前使用邪恶的全局variables）：
double currentFrequency=0; double currentSampleRate=0; double currentAmplitude=0; OSStatus RenderTone( void *inRefCon, AudioUnitRenderActionFlags *ioActionFlags, const AudioTimeStamp *inTimeStamp, UInt32 inBusNumber, UInt32 inNumberFrames, AudioBufferList *ioData) { // Fixed amplitude is good enough for our purposes const double amplitude = 0.5; // Get the tone parameters out of the view controller ToneGen *toneGen = (__bridge ToneGen *)inRefCon; double theta = toneGen.theta; BOOL fadingOut = NO; if ((currentFrequency != toneGen.frequency) || (currentSampleRate != toneGen.sampleRate)) { if (currentAmplitude > DBL_EPSILON) { fadingOut = YES; } else { currentFrequency = toneGen.frequency; currentSampleRate = toneGen.sampleRate; } } double theta_increment = 2.0 * M_PI * currentFrequency /currentSampleRate; // This is a mono tone generator so we only need the first buffer const int channel = 0; Float32 *buffer = (Float32 *)ioData->mBuffers[channel].mData; // Generate the samples for (UInt32 frame = 0; frame < inNumberFrames; frame++) { buffer[frame] = sin(theta) * currentAmplitude; //NSLog(@"amplitude = %f", currentAmplitude); theta += theta_increment; if (theta > 2.0 * M_PI) { theta -= 2.0 * M_PI; } if (fadingOut) { if (currentAmplitude > 0) { currentAmplitude -= 0.001; if (currentAmplitude < 0) currentAmplitude = 0; } } else { if (currentAmplitude < amplitude) { currentAmplitude += 0.001; if (currentAmplitude > amplitude) currentAmplitude = amplitude; } } } // Store the theta back in the view controller toneGen.theta = theta; return noErr; }
那个小唧唧通常是math的人造物。 耳朵主要分析频域中的input信号。 例如，频率为220赫兹的稳定的正弦波听起来像是A.然而，当你的正弦波是不稳定的时候，还有其他的频率出现在边界上。 尤其是，由于突然开始或停止声音的频率很高，所以会有一些stream行音乐。
我用合成器解决这个问题的方法 （在Javascript中，不是Obj-C，但这里的概念是相同的）是在超过300个样本中淡化声音，并且将声音从300多个样本中淡出在笔记closures。 根本没有办法真正消除边界效应，除非没有边界，但即使是一个微小而难以觉察的衰落也会使边界效应难以察觉。