我正在寻找如何绘制声音幅度。
我发现http://supermegaultragroovy.com/2009/10/06/drawing-waveforms/但我遇到了一些问题。如何获得表示音频的浮点值列表?
答案 0 :(得分:31)
谢谢大家。
我在这里找到了这个例子:Drawing waveform with AVAssetReader,改变它并开发了一个基于。
的新类此类返回UIImageView。
//.h file
#import <UIKit/UIKit.h>
@interface WaveformImageVew : UIImageView{
}
-(id)initWithUrl:(NSURL*)url;
- (NSData *) renderPNGAudioPictogramLogForAssett:(AVURLAsset *)songAsset;
@end
//.m file
#import "WaveformImageVew.h"
#define absX(x) (x<0?0-x:x)
#define minMaxX(x,mn,mx) (x<=mn?mn:(x>=mx?mx:x))
#define noiseFloor (-50.0)
#define decibel(amplitude) (20.0 * log10(absX(amplitude)/32767.0))
#define imgExt @"png"
#define imageToData(x) UIImagePNGRepresentation(x)
@implementation WaveformImageVew
-(id)initWithUrl:(NSURL*)url{
if(self = [super init]){
AVURLAsset * urlA = [AVURLAsset URLAssetWithURL:url options:nil];
[self setImage:[UIImage imageWithData:[self renderPNGAudioPictogramLogForAssett:urlA]]];
}
return self;
}
-(UIImage *) audioImageLogGraph:(Float32 *) samples
normalizeMax:(Float32) normalizeMax
sampleCount:(NSInteger) sampleCount
channelCount:(NSInteger) channelCount
imageHeight:(float) imageHeight {
CGSize imageSize = CGSizeMake(sampleCount, imageHeight);
UIGraphicsBeginImageContext(imageSize);
CGContextRef context = UIGraphicsGetCurrentContext();
CGContextSetFillColorWithColor(context, [UIColor blackColor].CGColor);
CGContextSetAlpha(context,1.0);
CGRect rect;
rect.size = imageSize;
rect.origin.x = 0;
rect.origin.y = 0;
CGColorRef leftcolor = [[UIColor whiteColor] CGColor];
CGColorRef rightcolor = [[UIColor redColor] CGColor];
CGContextFillRect(context, rect);
CGContextSetLineWidth(context, 1.0);
float halfGraphHeight = (imageHeight / 2) / (float) channelCount ;
float centerLeft = halfGraphHeight;
float centerRight = (halfGraphHeight*3) ;
float sampleAdjustmentFactor = (imageHeight/ (float) channelCount) / (normalizeMax - noiseFloor) / 2;
for (NSInteger intSample = 0 ; intSample < sampleCount ; intSample ++ ) {
Float32 left = *samples++;
float pixels = (left - noiseFloor) * sampleAdjustmentFactor;
CGContextMoveToPoint(context, intSample, centerLeft-pixels);
CGContextAddLineToPoint(context, intSample, centerLeft+pixels);
CGContextSetStrokeColorWithColor(context, leftcolor);
CGContextStrokePath(context);
if (channelCount==2) {
Float32 right = *samples++;
float pixels = (right - noiseFloor) * sampleAdjustmentFactor;
CGContextMoveToPoint(context, intSample, centerRight - pixels);
CGContextAddLineToPoint(context, intSample, centerRight + pixels);
CGContextSetStrokeColorWithColor(context, rightcolor);
CGContextStrokePath(context);
}
}
// Create new image
UIImage *newImage = UIGraphicsGetImageFromCurrentImageContext();
// Tidy up
UIGraphicsEndImageContext();
return newImage;
}
- (NSData *) renderPNGAudioPictogramLogForAssett:(AVURLAsset *)songAsset {
NSError * error = nil;
AVAssetReader * reader = [[AVAssetReader alloc] initWithAsset:songAsset error:&error];
AVAssetTrack * songTrack = [songAsset.tracks objectAtIndex:0];
NSDictionary* outputSettingsDict = [[NSDictionary alloc] initWithObjectsAndKeys:
[NSNumber numberWithInt:kAudioFormatLinearPCM],AVFormatIDKey,
// [NSNumber numberWithInt:44100.0],AVSampleRateKey, /*Not Supported*/
// [NSNumber numberWithInt: 2],AVNumberOfChannelsKey, /*Not Supported*/
[NSNumber numberWithInt:16],AVLinearPCMBitDepthKey,
[NSNumber numberWithBool:NO],AVLinearPCMIsBigEndianKey,
[NSNumber numberWithBool:NO],AVLinearPCMIsFloatKey,
[NSNumber numberWithBool:NO],AVLinearPCMIsNonInterleaved,
nil];
AVAssetReaderTrackOutput* output = [[AVAssetReaderTrackOutput alloc] initWithTrack:songTrack outputSettings:outputSettingsDict];
[reader addOutput:output];
[output release];
UInt32 sampleRate,channelCount;
NSArray* formatDesc = songTrack.formatDescriptions;
for(unsigned int i = 0; i < [formatDesc count]; ++i) {
CMAudioFormatDescriptionRef item = (CMAudioFormatDescriptionRef)[formatDesc objectAtIndex:i];
const AudioStreamBasicDescription* fmtDesc = CMAudioFormatDescriptionGetStreamBasicDescription (item);
if(fmtDesc ) {
sampleRate = fmtDesc->mSampleRate;
channelCount = fmtDesc->mChannelsPerFrame;
// NSLog(@"channels:%u, bytes/packet: %u, sampleRate %f",fmtDesc->mChannelsPerFrame, fmtDesc->mBytesPerPacket,fmtDesc->mSampleRate);
}
}
UInt32 bytesPerSample = 2 * channelCount;
Float32 normalizeMax = noiseFloor;
NSLog(@"normalizeMax = %f",normalizeMax);
NSMutableData * fullSongData = [[NSMutableData alloc] init];
[reader startReading];
UInt64 totalBytes = 0;
Float64 totalLeft = 0;
Float64 totalRight = 0;
Float32 sampleTally = 0;
NSInteger samplesPerPixel = sampleRate / 50;
while (reader.status == AVAssetReaderStatusReading){
AVAssetReaderTrackOutput * trackOutput = (AVAssetReaderTrackOutput *)[reader.outputs objectAtIndex:0];
CMSampleBufferRef sampleBufferRef = [trackOutput copyNextSampleBuffer];
if (sampleBufferRef){
CMBlockBufferRef blockBufferRef = CMSampleBufferGetDataBuffer(sampleBufferRef);
size_t length = CMBlockBufferGetDataLength(blockBufferRef);
totalBytes += length;
NSAutoreleasePool *wader = [[NSAutoreleasePool alloc] init];
NSMutableData * data = [NSMutableData dataWithLength:length];
CMBlockBufferCopyDataBytes(blockBufferRef, 0, length, data.mutableBytes);
SInt16 * samples = (SInt16 *) data.mutableBytes;
int sampleCount = length / bytesPerSample;
for (int i = 0; i < sampleCount ; i ++) {
Float32 left = (Float32) *samples++;
left = decibel(left);
left = minMaxX(left,noiseFloor,0);
totalLeft += left;
Float32 right;
if (channelCount==2) {
right = (Float32) *samples++;
right = decibel(right);
right = minMaxX(right,noiseFloor,0);
totalRight += right;
}
sampleTally++;
if (sampleTally > samplesPerPixel) {
left = totalLeft / sampleTally;
if (left > normalizeMax) {
normalizeMax = left;
}
// NSLog(@"left average = %f, normalizeMax = %f",left,normalizeMax);
[fullSongData appendBytes:&left length:sizeof(left)];
if (channelCount==2) {
right = totalRight / sampleTally;
if (right > normalizeMax) {
normalizeMax = right;
}
[fullSongData appendBytes:&right length:sizeof(right)];
}
totalLeft = 0;
totalRight = 0;
sampleTally = 0;
}
}
[wader drain];
CMSampleBufferInvalidate(sampleBufferRef);
CFRelease(sampleBufferRef);
}
}
NSData * finalData = nil;
if (reader.status == AVAssetReaderStatusFailed || reader.status == AVAssetReaderStatusUnknown){
// Something went wrong. Handle it.
}
if (reader.status == AVAssetReaderStatusCompleted){
// You're done. It worked.
NSLog(@"rendering output graphics using normalizeMax %f",normalizeMax);
UIImage *test = [self audioImageLogGraph:(Float32 *) fullSongData.bytes
normalizeMax:normalizeMax
sampleCount:fullSongData.length / (sizeof(Float32) * 2)
channelCount:2
imageHeight:100];
finalData = imageToData(test);
}
[fullSongData release];
[reader release];
return finalData;
}
@end
答案 1 :(得分:11)
一直在阅读你的问题并为此创建了一个控件。看起来像这样:
代码在这里:
https://github.com/fulldecent/FDWaveformView
在这里讨论:
https://www.cocoacontrols.com/controls/fdwaveformview
更新2015-01-29 :这个项目非常强大并且发布了一致的版本。感谢所有曝光的SO!
答案 2 :(得分:1)
这是我用来将音频数据(音频文件)转换为浮点表示并保存到数组中的代码。
-(void) PrintFloatDataFromAudioFile {
NSString * name = @"Filename"; //YOUR FILE NAME
NSString * source = [[NSBundle mainBundle] pathForResource:name ofType:@"m4a"]; // SPECIFY YOUR FILE FORMAT
const char *cString = [source cStringUsingEncoding:NSASCIIStringEncoding];
CFStringRef str = CFStringCreateWithCString(
NULL,
cString,
kCFStringEncodingMacRoman
);
CFURLRef inputFileURL = CFURLCreateWithFileSystemPath(
kCFAllocatorDefault,
str,
kCFURLPOSIXPathStyle,
false
);
ExtAudioFileRef fileRef;
ExtAudioFileOpenURL(inputFileURL, &fileRef);
AudioStreamBasicDescription audioFormat;
audioFormat.mSampleRate = 44100; // GIVE YOUR SAMPLING RATE
audioFormat.mFormatID = kAudioFormatLinearPCM;
audioFormat.mFormatFlags = kLinearPCMFormatFlagIsFloat;
audioFormat.mBitsPerChannel = sizeof(Float32) * 8;
audioFormat.mChannelsPerFrame = 1; // Mono
audioFormat.mBytesPerFrame = audioFormat.mChannelsPerFrame * sizeof(Float32); // == sizeof(Float32)
audioFormat.mFramesPerPacket = 1;
audioFormat.mBytesPerPacket = audioFormat.mFramesPerPacket * audioFormat.mBytesPerFrame; // = sizeof(Float32)
// 3) Apply audio format to the Extended Audio File
ExtAudioFileSetProperty(
fileRef,
kExtAudioFileProperty_ClientDataFormat,
sizeof (AudioStreamBasicDescription), //= audioFormat
&audioFormat);
int numSamples = 1024; //How many samples to read in at a time
UInt32 sizePerPacket = audioFormat.mBytesPerPacket; // = sizeof(Float32) = 32bytes
UInt32 packetsPerBuffer = numSamples;
UInt32 outputBufferSize = packetsPerBuffer * sizePerPacket;
// So the lvalue of outputBuffer is the memory location where we have reserved space
UInt8 *outputBuffer = (UInt8 *)malloc(sizeof(UInt8 *) * outputBufferSize);
AudioBufferList convertedData ;//= malloc(sizeof(convertedData));
convertedData.mNumberBuffers = 1; // Set this to 1 for mono
convertedData.mBuffers[0].mNumberChannels = audioFormat.mChannelsPerFrame; //also = 1
convertedData.mBuffers[0].mDataByteSize = outputBufferSize;
convertedData.mBuffers[0].mData = outputBuffer; //
UInt32 frameCount = numSamples;
float *samplesAsCArray;
int j =0;
double floatDataArray[882000] ; // SPECIFY YOUR DATA LIMIT MINE WAS 882000 , SHOULD BE EQUAL TO OR MORE THAN DATA LIMIT
while (frameCount > 0) {
ExtAudioFileRead(
fileRef,
&frameCount,
&convertedData
);
if (frameCount > 0) {
AudioBuffer audioBuffer = convertedData.mBuffers[0];
samplesAsCArray = (float *)audioBuffer.mData; // CAST YOUR mData INTO FLOAT
for (int i =0; i<1024 /*numSamples */; i++) { //YOU CAN PUT numSamples INTEAD OF 1024
floatDataArray[j] = (double)samplesAsCArray[i] ; //PUT YOUR DATA INTO FLOAT ARRAY
printf("\n%f",floatDataArray[j]); //PRINT YOUR ARRAY'S DATA IN FLOAT FORM RANGING -1 TO +1
j++;
}
}
}}
答案 3 :(得分:0)
这是我的答案,所有的极客
obj-c
这是代码:
-(void) listenerData:(NSNotification *) notify
{
int resnum=112222;
unsigned int bitsum=0;
for(int i=0;i<4;i++)
{
bitsum+=(resnum>>(i*8))&0xff;
}
bitsum=bitsum&0xff;
NSString * check=[NSString stringWithFormat:@"%x %x",resnum,bitsum];
check=nil;
self.drawData=notify.object;``
[self setNeedsDisplay];
}
-(void)drawRect:(CGRect)rect
{
NSArray *data=self.drawData;
NSData *tdata=[data objectAtIndex:0];
double *srcdata=(double*)tdata.bytes;
int datacount=tdata.length/sizeof(double);
tdata=[data objectAtIndex:1];
double *coveddata=(double*)tdata.bytes;
CGContextRef context=UIGraphicsGetCurrentContext();
CGRect bounds=self.bounds;
CGContextClearRect(context, bounds);
CGFloat midpos=bounds.size.height/2;
CGContextBeginPath(context);
const double scale=1.0/100;
CGFloat step=bounds.size.width/(datacount-1);
CGContextMoveToPoint(context, 0, midpos);
CGFloat xpos=0;
for(int i=0;i<datacount;i++)
{
CGContextAddLineToPoint(context, xpos, midpos-srcdata[i]*scale);
xpos+=step;
}
CGContextAddLineToPoint(context, bounds.size.width, midpos);
CGContextClosePath(context);
CGContextSetRGBFillColor(context, 1.0, 0.0, 0.0, 1.0);
CGContextFillPath(context);
CGContextBeginPath(context);
const double scale2=1.0/100;
CGContextMoveToPoint(context, 0, midpos);
xpos=0;
for(int i=0;i<datacount;i++)
{
CGContextAddLineToPoint(context, xpos, midpos+coveddata[i]*scale2);
xpos+=step;
}
CGContextAddLineToPoint(context, bounds.size.width, midpos);
CGContextClosePath(context);
CGContextSetRGBFillColor(context, 1.0, 0.0, 1.0, 1.0);
CGContextFillPath(context);
}