gpt4 book ai didi

ios - 在 iOS 上使用 OpenAL 进行声音捕捉

转载 作者:可可西里 更新时间:2023-11-01 05:42:14 25 4
gpt4 key购买 nike

我正在尝试使用 OpenAL 在 iOS 上进行声音捕捉(我正在编写一个跨平台库,这就是我避免使用特定于 iOS 的方式来录制声音的原因)。开箱即用的 OpenAL 捕获不起作用,但存在一个已知的解决方法:open an output context before starting capture .此解决方案适用于 iOS 5.0。

但是在 iOS 5.1.1 上,解决方法仅对我尝试记录的第一个样本有帮助。 (在开始捕获并打开默认输出设备之前,我将 AudioSession 切换为 PlayAndRecord。录制样本后,我关闭设备并将 session 切换回原来的状态。)对于第二个示例,重新打开输出上下文没有帮助,也没有捕获到声音。

是否有解决此问题的已知方法?

// Here's what I do before starting the recording
oldAudioSessionCategory = [audioSession category];
[audioSession setCategory:AVAudioSessionCategoryPlayAndRecord error:nil];
[audioSession setActive:YES error:nil];
// We need to have an active context. If there is none, create one.
if (!alcGetCurrentContext()) {
outputDevice = alcOpenDevice(NULL);
outputContext = alcCreateContext(outputDevice, NULL);
alcMakeContextCurrent(outputContext);
}

// Capture itself
inputDevice = alcCaptureOpenDevice(NULL, frequency, FORMAT, bufferSize);
....
alcCaptureCloseDevice(inputDevice);

// Restoring the audio state to whatever it had been before capture
if (outputContext) {
alcDestroyContext(outputContext);
alcCloseDevice(outputDevice);
}
[[AVAudioSession sharedInstance] setCategory:oldAudioSessionCategory
error:nil];

最佳答案

这是我用来模拟捕获扩展的代码。一些评论:

  1. 在整个项目中,OpenKD 用于线程原语等。您可能需要更换这些电话。
  2. 我不得不在开始捕获时与延迟作斗争。结果,我不断地读取声音输入,并在不需要时将其丢弃。 (提出了这样的解决方案,例如 here。)这反过来又需要捕获 onResignActive 通知,以便释放对麦克风的控制。您可能想要也可能不想使用这样的组合。
  3. 我必须定义一个单独的函数 alcGetAvailableSamples,而不是 alcGetIntegerv(device, ALC_CAPTURE_SAMPLES, 1, &res)

简而言之,此代码不太可能按原样在您的项目中使用,但希望您可以根据您的需要进行调整。

#include <stdbool.h>
#include <stddef.h>
#include <stdint.h>
#include <KD/kd.h>
#include <AL/al.h>
#include <AL/alc.h>

#include <AudioToolbox/AudioToolbox.h>
#import <Foundation/Foundation.h>
#import <UIKit/UIKit.h>

#include "KD/kdext.h"

struct InputDeviceData {
int id;
KDThreadMutex *mutex;
AudioUnit audioUnit;
int nChannels;
int frequency;
ALCenum format;
int sampleSize;
uint8_t *buf;
size_t bufSize; // in bytes
size_t bufFilledBytes; // in bytes
bool started;
};

static struct InputDeviceData *cachedInData = NULL;

static OSStatus renderCallback (void *inRefCon,
AudioUnitRenderActionFlags *ioActionFlags,
const AudioTimeStamp *inTimeStamp,
UInt32 inBusNumber,
UInt32 inNumberFrames,
AudioBufferList *ioData);
static AudioUnit getAudioUnit();
static void setupNotifications();
static void destroyCachedInData();
static struct InputDeviceData *setupCachedInData(AudioUnit audioUnit, ALCuint frequency, ALCenum format, ALCsizei bufferSizeInSamples);
static struct InputDeviceData *getInputDeviceData(AudioUnit audioUnit, ALCuint frequency, ALCenum format, ALCsizei bufferSizeInSamples);

/** I only have to use NSNotificationCenter instead of CFNotificationCenter
* because there is no published name for WillResignActive/WillBecomeActive
* notifications in CoreFoundation.
*/
@interface ALCNotificationObserver : NSObject
- (void)onResignActive;
@end
@implementation ALCNotificationObserver
- (void)onResignActive {
destroyCachedInData();
}
@end

static void setupNotifications() {
static ALCNotificationObserver *observer = NULL;
if (!observer) {
observer = [[ALCNotificationObserver alloc] init];
[[NSNotificationCenter defaultCenter] addObserver:observer selector:@selector(onResignActive) name:UIApplicationWillResignActiveNotification object:nil];
}
}

static OSStatus renderCallback (void *inRefCon,
AudioUnitRenderActionFlags *ioActionFlags,
const AudioTimeStamp *inTimeStamp,
UInt32 inBusNumber,
UInt32 inNumberFrames,
AudioBufferList *ioData) {
struct InputDeviceData *inData = (struct InputDeviceData*)inRefCon;

kdThreadMutexLock(inData->mutex);
size_t bytesToRender = inNumberFrames * inData->sampleSize;
if (bytesToRender + inData->bufFilledBytes <= inData->bufSize) {
OSStatus status;
struct AudioBufferList audioBufferList; // 1 buffer is declared inside the structure itself.
audioBufferList.mNumberBuffers = 1;
audioBufferList.mBuffers[0].mNumberChannels = inData->nChannels;
audioBufferList.mBuffers[0].mDataByteSize = bytesToRender;
audioBufferList.mBuffers[0].mData = inData->buf + inData->bufFilledBytes;
status = AudioUnitRender(inData->audioUnit,
ioActionFlags,
inTimeStamp,
inBusNumber,
inNumberFrames,
&audioBufferList);
if (inData->started) {
inData->bufFilledBytes += bytesToRender;
}
} else {
kdLogFormatMessage("%s: buffer overflow", __FUNCTION__);
}
kdThreadMutexUnlock(inData->mutex);

return 0;
}

static AudioUnit getAudioUnit() {
static AudioUnit audioUnit = NULL;

if (!audioUnit) {
AudioComponentDescription ioUnitDescription;

ioUnitDescription.componentType = kAudioUnitType_Output;
ioUnitDescription.componentSubType = kAudioUnitSubType_VoiceProcessingIO;
ioUnitDescription.componentManufacturer = kAudioUnitManufacturer_Apple;
ioUnitDescription.componentFlags = 0;
ioUnitDescription.componentFlagsMask = 0;

AudioComponent foundIoUnitReference = AudioComponentFindNext(NULL,
&ioUnitDescription);
AudioComponentInstanceNew(foundIoUnitReference,
&audioUnit);

if (audioUnit == NULL) {
kdLogMessage("Could not obtain AudioUnit");
}
}

return audioUnit;
}

static void destroyCachedInData() {
OSStatus status;
if (cachedInData) {
status = AudioOutputUnitStop(cachedInData->audioUnit);
status = AudioUnitUninitialize(cachedInData->audioUnit);
free(cachedInData->buf);
kdThreadMutexFree(cachedInData->mutex);
free(cachedInData);
cachedInData = NULL;
}
}

static struct InputDeviceData *setupCachedInData(AudioUnit audioUnit, ALCuint frequency, ALCenum format, ALCsizei bufferSizeInSamples) {
static int idCount = 0;
OSStatus status;
int bytesPerFrame = (format == AL_FORMAT_MONO8) ? 1 :
(format == AL_FORMAT_MONO16) ? 2 :
(format == AL_FORMAT_STEREO8) ? 2 :
(format == AL_FORMAT_STEREO16) ? 4 : -1;
int channelsPerFrame = (format == AL_FORMAT_MONO8) ? 1 :
(format == AL_FORMAT_MONO16) ? 1 :
(format == AL_FORMAT_STEREO8) ? 2 :
(format == AL_FORMAT_STEREO16) ? 2 : -1;
int bitsPerChannel = (format == AL_FORMAT_MONO8) ? 8 :
(format == AL_FORMAT_MONO16) ? 16 :
(format == AL_FORMAT_STEREO8) ? 8 :
(format == AL_FORMAT_STEREO16) ? 16 : -1;

cachedInData = malloc(sizeof(struct InputDeviceData));
cachedInData->id = ++idCount;
cachedInData->format = format;
cachedInData->frequency = frequency;
cachedInData->mutex = kdThreadMutexCreate(NULL);
cachedInData->audioUnit = audioUnit;
cachedInData->nChannels = channelsPerFrame;
cachedInData->sampleSize = bytesPerFrame;
cachedInData->bufSize = bufferSizeInSamples * bytesPerFrame;
cachedInData->buf = malloc(cachedInData->bufSize);
cachedInData->bufFilledBytes = 0;
cachedInData->started = FALSE;

UInt32 enableOutput = 1; // to enable output
status = AudioUnitSetProperty(audioUnit,
kAudioOutputUnitProperty_EnableIO,
kAudioUnitScope_Input,
1,
&enableOutput, sizeof(enableOutput));

struct AudioStreamBasicDescription basicDescription;
basicDescription.mSampleRate = (Float64)frequency;
basicDescription.mFormatID = kAudioFormatLinearPCM;
basicDescription.mFormatFlags = kAudioFormatFlagIsSignedInteger | kAudioFormatFlagIsPacked;
basicDescription.mBytesPerPacket = bytesPerFrame;
basicDescription.mFramesPerPacket = 1;
basicDescription.mBytesPerFrame = bytesPerFrame;
basicDescription.mChannelsPerFrame = channelsPerFrame;
basicDescription.mBitsPerChannel = bitsPerChannel;
basicDescription.mReserved = 0;

status = AudioUnitSetProperty(audioUnit,
kAudioUnitProperty_StreamFormat, // property key
kAudioUnitScope_Output, // scope
1, // 1 is output
&basicDescription, sizeof(basicDescription)); // value

AURenderCallbackStruct renderCallbackStruct;
renderCallbackStruct.inputProc = renderCallback;
renderCallbackStruct.inputProcRefCon = cachedInData;
status = AudioUnitSetProperty(audioUnit,
kAudioOutputUnitProperty_SetInputCallback, // property key
kAudioUnitScope_Output, // scope
1, // 1 is output
&renderCallbackStruct, sizeof(renderCallbackStruct)); // value

status = AudioOutputUnitStart(cachedInData->audioUnit);

return cachedInData;
}

static struct InputDeviceData *getInputDeviceData(AudioUnit audioUnit, ALCuint frequency, ALCenum format, ALCsizei bufferSizeInSamples) {
if (cachedInData &&
(cachedInData->frequency != frequency ||
cachedInData->format != format ||
cachedInData->bufSize / cachedInData->sampleSize != bufferSizeInSamples)) {
kdAssert(!cachedInData->started);
destroyCachedInData();
}
if (!cachedInData) {
setupCachedInData(audioUnit, frequency, format, bufferSizeInSamples);
setupNotifications();
}

return cachedInData;
}


ALC_API ALCdevice* ALC_APIENTRY alcCaptureOpenDevice(const ALCchar *devicename, ALCuint frequency, ALCenum format, ALCsizei buffersizeInSamples) {
kdAssert(devicename == NULL);

AudioUnit audioUnit = getAudioUnit();
struct InputDeviceData *res = getInputDeviceData(audioUnit, frequency, format, buffersizeInSamples);
return (ALCdevice*)res->id;
}

ALC_API ALCboolean ALC_APIENTRY alcCaptureCloseDevice(ALCdevice *device) {
alcCaptureStop(device);
return true;
}

ALC_API void ALC_APIENTRY alcCaptureStart(ALCdevice *device) {
if (!cachedInData || (int)device != cachedInData->id) {
// may happen after the app loses and regains active status.
kdLogFormatMessage("Attempt to start a stale AL capture device");
return;
}
cachedInData->started = TRUE;
}

ALC_API void ALC_APIENTRY alcCaptureStop(ALCdevice *device) {
if (!cachedInData || (int)device != cachedInData->id) {
// may happen after the app loses and regains active status.
kdLogFormatMessage("Attempt to stop a stale AL capture device");
return;
}
cachedInData->started = FALSE;
}

ALC_API ALCint ALC_APIENTRY alcGetAvailableSamples(ALCdevice *device) {
if (!cachedInData || (int)device != cachedInData->id) {
// may happen after the app loses and regains active status.
kdLogFormatMessage("Attempt to get sample count from a stale AL capture device");
return 0;
}
ALCint res;
kdThreadMutexLock(cachedInData->mutex);
res = cachedInData->bufFilledBytes / cachedInData->sampleSize;
kdThreadMutexUnlock(cachedInData->mutex);
return res;
}

ALC_API void ALC_APIENTRY alcCaptureSamples(ALCdevice *device, ALCvoid *buffer, ALCsizei samples) {
if (!cachedInData || (int)device != cachedInData->id) {
// may happen after the app loses and regains active status.
kdLogFormatMessage("Attempt to get samples from a stale AL capture device");
return;
}
size_t bytesToCapture = samples * cachedInData->sampleSize;
kdAssert(cachedInData->started);
kdAssert(bytesToCapture <= cachedInData->bufFilledBytes);

kdThreadMutexLock(cachedInData->mutex);
memcpy(buffer, cachedInData->buf, bytesToCapture);
memmove(cachedInData->buf, cachedInData->buf + bytesToCapture, cachedInData->bufFilledBytes - bytesToCapture);
cachedInData->bufFilledBytes -= bytesToCapture;
kdThreadMutexUnlock(cachedInData->mutex);
}

关于ios - 在 iOS 上使用 OpenAL 进行声音捕捉,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/10756972/

25 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com