我正在以Speex格式获取音频流数据。我尝试为Speex解码为Speex编译ffmpeg。编译ffmpeg时遇到错误，可以在this链接中看到。所以我使用了另一个使用this框架来解码Speex音频的选项。我正在播放解码数据，即使用音频队列的PCM数据。以下是解码Speex数据和播放PCM数据的代码。
SpeexPlayer.h
#import <Foundation/Foundation.h>
#import <AVFoundation/AVFoundation.h>
#import <AudioToolbox/AudioToolbox.h>
#import "RtmpMediaStream.h"
#import "RtmpAVUtils.h"
#import <Speex/speex.h>
#import <Speex/speex_stereo.h>
#import <Speex/speex_callbacks.h>
typedef enum kAudioState {
AUDIO_STATE_PAUSE,
AUDIO_STATE_STOP,
AUDIO_STATE_PLAYING,
AUDIO_STATE_READY
} kAudioState;
typedef SInt16 AudioSampleType;
#define kNumAQBufs 3
#define kAudioBufferSeconds 3
@interface SpeexPlayer : RtmpAVUtils<RtmpMediaStreamAudioDataDelegate>{
SpeexBits bits;
void *dec_state;
BOOL started;
int frame_size;
kAudioState state;
AudioQueueRef audioQueue;
AudioQueueBufferRef audioQueueBuffer;
}
- (id)initWithStream:(RtmpMediaStream *)stream;
- (void)audioQueueOutputCallback:(AudioQueueRef)inAQ inBuffer:(AudioQueueBufferRef)inBuffer;
- (void)audioQueueIsRunningCallback;
@end
SpeexPlayer.m
#import "SpeexPlayer.h"
#import "RtmpConstants.h"
#import "RtmpMediaStream.h"
#import "RtmpPacket.h"
int sample_rate = 11025;
int _lastTimestamp = 0;
BOOL isStarted = NO;
AudioTimeStamp tempTimeStamp;
void audioQueueOutputCallback(void *inClientData, AudioQueueRef inAQ,
AudioQueueBufferRef inBuffer) {
SpeexPlayer *audioController = (__bridge SpeexPlayer*)inClientData;
[audioController audioQueueOutputCallback:inAQ inBuffer:inBuffer];
}
void audioQueueIsRunningCallback(void *inClientData, AudioQueueRef inAQ,
AudioQueuePropertyID inID) {
SpeexPlayer *audioController = (__bridge SpeexPlayer*)inClientData;
[audioController audioQueueIsRunningCallback];
}
@implementation SpeexPlayer
- (id)initWithStream:(RtmpMediaStream *)stream {
if (self = [super initWithStream:stream]) {
frame_size = 0;
int enh = 1;
started = NO;
dec_state = speex_decoder_init(&speex_wb_mode);
speex_decoder_ctl(dec_state, SPEEX_GET_FRAME_SIZE, &frame_size);
speex_decoder_ctl(dec_state, SPEEX_SET_ENH, &enh);
speex_decoder_ctl(dec_state, SPEEX_SET_SAMPLING_RATE, &sample_rate);
speex_bits_init(&bits);
AVAudioSession *audioSession = [AVAudioSession sharedInstance];
[audioSession setCategory:AVAudioSessionCategoryPlayback error:nil];
self.stream.audioDelegate = self;
}
return self;
}
- (void)rtmpMediaStream:(RtmpMediaStream *)stream receivedAudioPacket:(RtmpPacket *)p {
if (state != AUDIO_STATE_READY && state != AUDIO_STATE_PLAYING ) {
[self createAudioQueue];
[self startAudio];
}
static AVPacket packet;
if (state != AUDIO_STATE_PLAYING && isStarted) {
}
isStarted = YES;
if ([self encodePacket:p intoAVPacket:&packet]) {
[self encodeRTMP:p intoQueueBuffer:audioQueueBuffer];
av_free_packet(&packet);
AudioTimeStamp bufferStartTime;
AudioQueueGetCurrentTime(audioQueue, NULL, &bufferStartTime, NULL);
bufferStartTime.mSampleTime += ((Float64)packet.dts)/1000;
bufferStartTime.mFlags = kAudioTimeStampSampleTimeValid;
tempTimeStamp.mSampleTime = bufferStartTime.mSampleTime - 5.0f;
tempTimeStamp.mFlags = kAudioTimeStampSampleTimeValid;
//NSLog(@"timestamp = %@",bufferStartTime);
//[self enqueueBuffer:audioQueueBuffer withTimestamp:bufferStartTime];
[self enqueueBuffer:audioQueueBuffer];
}
}
- (BOOL)createAudioQueue {
state = AUDIO_STATE_READY;
AudioStreamBasicDescription audioStreamBasicDesc;
audioStreamBasicDesc.mFormatID = kAudioFormatLinearPCM;
audioStreamBasicDesc.mSampleRate = 8000;
audioStreamBasicDesc.mFormatFlags = kLinearPCMFormatFlagIsSignedInteger |
kLinearPCMFormatFlagIsPacked | kAudioFormatFlagsCanonical;
audioStreamBasicDesc.mBytesPerPacket = 2;
audioStreamBasicDesc.mFramesPerPacket = 1;
audioStreamBasicDesc.mBytesPerFrame = sizeof(AudioSampleType);
audioStreamBasicDesc.mChannelsPerFrame = 1 ;
audioStreamBasicDesc.mBitsPerChannel = 8 * sizeof(AudioSampleType);
audioStreamBasicDesc.mReserved = 0;
OSStatus status = AudioQueueNewOutput(&audioStreamBasicDesc, audioQueueOutputCallback, (__bridge void*)self,
NULL, NULL, 0, &audioQueue);
if (status != noErr) {
NSLog(@"Could not create new output.");
return NO;
}
status = AudioQueueAddPropertyListener(audioQueue, kAudioQueueProperty_IsRunning,
audioQueueIsRunningCallback, (__bridge void*)self);
if (status != noErr) {
NSLog(@"Could not add propery listener. (kAudioQueueProperty_IsRunning)");
return NO;
}
status = AudioQueueAllocateBufferWithPacketDescriptions(audioQueue,
audioStreamBasicDesc.mSampleRate * kAudioBufferSeconds / 8,
audioStreamBasicDesc.mSampleRate * kAudioBufferSeconds / audioStreamBasicDesc.mFramesPerPacket + 1,
&audioQueueBuffer);
//AudioQueueAllocateBufferWithPacketDescriptions(audioQueue, 400, 500, &audioQueueBuffer);
//status = AudioQueueAllocateBuffer(audioQueue, audioStreamBasicDesc.mSampleRate * kAudioBufferSeconds / 8, &audioQueueBuffer);
if (status != noErr) {
NSLog(@"Could not allocate buffer.");
return NO;
}
return YES;
}
- (void)startAudio {
if (started) {
AudioQueueStart(audioQueue, NULL);
} else {
[self startQueue];
}
state = AUDIO_STATE_PLAYING;
}
- (void)stopAudio{
if (started) {
AudioQueueStop(audioQueue, YES);
state = AUDIO_STATE_STOP;
if (!self.stream.videoDelegate) {
[self.stream pause];
}
}
}
- (void)play {
if (!self.stream.videoDelegate) {
[self.stream play];
}
}
- (void)pause {
if (started) {
state = AUDIO_STATE_PAUSE;
AudioQueuePause(audioQueue);
AudioQueueReset(audioQueue);
if (!self.stream.videoDelegate) {
[self.stream pause];
}
}
}
- (OSStatus)startQueue {
OSStatus status = noErr;
if (!started) {
status = AudioQueueStart(audioQueue, NULL);
if (status == noErr) {
started = YES;
}
else {
NSLog(@"Could not start audio queue.");
}
}
return status;
}
- (void)removeAudioQueue {
[self stopAudio];
started = NO;
AudioQueueFreeBuffer(audioQueue, audioQueueBuffer);
AudioQueueDispose(audioQueue, YES);
}
-(AudioQueueBufferRef)encodeRTMP:(RtmpPacket*)packet intoQueueBuffer:(AudioQueueBufferRef)buffer {
buffer->mAudioDataByteSize = 0;
buffer->mPacketDescriptionCount = 0;
NSData *data = packet.m_payload;
NSData * subdata = [data subdataWithRange:NSMakeRange(1, data.length-1)];
char *c = (char *)subdata.bytes;
speex_bits_read_from(&bits, c,(int)subdata.length);
short *outTemp = (short *)calloc(1, frame_size * 2);
speex_decode_int(dec_state, &bits, outTemp);
NSData *audioData = [NSData dataWithBytes:outTemp length:frame_size];
if (buffer->mAudioDataBytesCapacity - buffer->mAudioDataByteSize >= audioData.length) {
NSLog(@"true");
memcpy((uint8_t *)buffer->mAudioData + buffer->mAudioDataByteSize, outTemp, audioData.length);
buffer->mPacketDescriptions[buffer->mPacketDescriptionCount].mStartOffset = buffer->mAudioDataByteSize;
buffer->mPacketDescriptions[buffer->mPacketDescriptionCount].mDataByteSize = (int)audioData.length;
buffer->mPacketDescriptions[buffer->mPacketDescriptionCount].mVariableFramesInPacket = (int)audioData.length;
buffer->mAudioDataByteSize += audioData.length;
buffer->mPacketDescriptionCount++;
}
return buffer;
}
- (OSStatus)enqueueBuffer:(AudioQueueBufferRef)buffer{
// withTimestamp:(AudioTimeStamp)timestamp {
OSStatus status = noErr;
NSLock * decodeLock = [[NSLock alloc] init];
[decodeLock lock];
if (buffer->mPacketDescriptionCount > 0) {
//status = AudioQueueEnqueueBufferWithParameters(audioQueue, buffer, 0, NULL, 0, 0, 0, NULL, ×tamp, ×tamp);
status = AudioQueueEnqueueBuffer(audioQueue, buffer, 0, NULL);
if (status != noErr) {
NSLog(@"Could not enqueue buffer.");
}
}
else {
AudioQueueStop(audioQueue, NO);
}
[decodeLock unlock];
return status;
}
- (void)audioQueueOutputCallback:(AudioQueueRef)inAQ inBuffer:(AudioQueueBufferRef)inBuffer {
if (state == AUDIO_STATE_PLAYING) {
//[self enqueueBuffer:audioQueueBuffer withTimestamp:tempTimeStamp];
[self enqueueBuffer:inBuffer ];
}
}
- (void)audioQueueIsRunningCallback {
UInt32 isRunning;
UInt32 size = sizeof(isRunning);
OSStatus status = AudioQueueGetProperty(audioQueue, kAudioQueueProperty_IsRunning, &isRunning, &size);
if (status == noErr && !isRunning && state == AUDIO_STATE_PLAYING) {
state = AUDIO_STATE_STOP;
}
}
@end
在方法- (void)rtmpMediaStream:(RtmpMediaStream *)stream receivedAudioPacket:(RtmpPacket *)p和回调方法- (void)audioQueueOutputCallback:(AudioQueueRef)inAQ inBuffer:(AudioQueueBufferRef)inBuffer中收到音频流包时，我将音频队列缓冲区入队。当AudioQueue播放传入流时，我无法收听正确的音频。我所能听到的只是机器人声音，所有测试案例中音频的音调也非常有男子气概。我无法想象我哪里出错了。我无法理解问题是解码部分还是使用AudioQueues使用Audio播放音频。
有人可以提出解决方案吗？