我正在解码OGG视频（theora＆amp; vorbis作为编解码器）并希望在播放声音时在屏幕上显示它（使用Ogre 3D）。我可以很好地解码图像流，并且视频可以正确地以正确的帧速率播放等。
然而，我无法使用OpenAL来播放声音。
编辑：我设法让播放声音至少与视频中的实际音频相似。更新了示例代码。
编辑2：我现在能够获得“几乎”正确的声音。我必须将OpenAL设置为使用AL_FORMAT_STEREO_FLOAT32（初始化扩展后）而不是仅使用STEREO16。现在声音“只有”极高音调和口吃，但速度正确。
以下是我对音频数据包进行解码的方法（在后台线程中，相当于视频文件图像流的效果）：
//------------------------------------------------------------------------------
int decodeAudioPacket( AVPacket& p_packet, AVCodecContext* p_audioCodecContext, AVFrame* p_frame,
FFmpegVideoPlayer* p_player, VideoInfo& p_videoInfo)
{
// Decode audio frame
int got_frame = 0;
int decoded = avcodec_decode_audio4(p_audioCodecContext, p_frame, &got_frame, &p_packet);
if (decoded < 0)
{
p_videoInfo.error = "Error decoding audio frame.";
return decoded;
}
// Frame is complete, store it in audio frame queue
if (got_frame)
{
int bufferSize = av_samples_get_buffer_size(NULL, p_audioCodecContext->channels, p_frame->nb_samples,
p_audioCodecContext->sample_fmt, 0);
int64_t duration = p_frame->pkt_duration;
int64_t dts = p_frame->pkt_dts;
if (staticOgreLog)
{
staticOgreLog->logMessage("Audio frame bufferSize / duration / dts: "
+ boost::lexical_cast<std::string>(bufferSize) + " / "
+ boost::lexical_cast<std::string>(duration) + " / "
+ boost::lexical_cast<std::string>(dts), Ogre::LML_NORMAL);
}
// Create the audio frame
AudioFrame* frame = new AudioFrame();
frame->dataSize = bufferSize;
frame->data = new uint8_t[bufferSize];
if (p_frame->channels == 2)
{
memcpy(frame->data, p_frame->data[0], bufferSize >> 1);
memcpy(frame->data + (bufferSize >> 1), p_frame->data[1], bufferSize >> 1);
}
else
{
memcpy(frame->data, p_frame->data, bufferSize);
}
double timeBase = ((double)p_audioCodecContext->time_base.num) / (double)p_audioCodecContext->time_base.den;
frame->lifeTime = duration * timeBase;
p_player->addAudioFrame(frame);
}
return decoded;
}
所以，正如你所看到的，我解码了帧，将它存储到我自己的struct，AudioFrame。现在，当播放声音时，我使用这样的音频帧：
int numBuffers = 4;
ALuint buffers[4];
alGenBuffers(numBuffers, buffers);
ALenum success = alGetError();
if(success != AL_NO_ERROR)
{
CONSOLE_LOG("Error on alGenBuffers : " + Ogre::StringConverter::toString(success) + alGetString(success));
return;
}
// Fill a number of data buffers with audio from the stream
std::vector<AudioFrame*> audioBuffers;
std::vector<unsigned int> audioBufferSizes;
unsigned int numReturned = FFMPEG_PLAYER->getDecodedAudioFrames(numBuffers, audioBuffers, audioBufferSizes);
// Assign the data buffers to the OpenAL buffers
for (unsigned int i = 0; i < numReturned; ++i)
{
alBufferData(buffers[i], _streamingFormat, audioBuffers[i]->data, audioBufferSizes[i], _streamingFrequency);
success = alGetError();
if(success != AL_NO_ERROR)
{
CONSOLE_LOG("Error on alBufferData : " + Ogre::StringConverter::toString(success) + alGetString(success)
+ " size: " + Ogre::StringConverter::toString(audioBufferSizes[i]));
return;
}
}
// Queue the buffers into OpenAL
alSourceQueueBuffers(_source, numReturned, buffers);
success = alGetError();
if(success != AL_NO_ERROR)
{
CONSOLE_LOG("Error queuing streaming buffers: " + Ogre::StringConverter::toString(success) + alGetString(success));
return;
}
}
alSourcePlay(_source);
我给OpenAL的格式和频率是AL_FORMAT_STEREO_FLOAT32（它是立体声声音流，我确实初始化了FLOAT32扩展）和48000（这是音频流的AVCodecContext的采样率）。
在播放过程中，我会执行以下操作来重新填充OpenAL的缓冲区：
ALint numBuffersProcessed;
// Check if OpenAL is done with any of the queued buffers
alGetSourcei(_source, AL_BUFFERS_PROCESSED, &numBuffersProcessed);
if(numBuffersProcessed <= 0)
return;
// Fill a number of data buffers with audio from the stream
std::vector<AudiFrame*> audioBuffers;
std::vector<unsigned int> audioBufferSizes;
unsigned int numFilled = FFMPEG_PLAYER->getDecodedAudioFrames(numBuffersProcessed, audioBuffers, audioBufferSizes);
// Assign the data buffers to the OpenAL buffers
ALuint buffer;
for (unsigned int i = 0; i < numFilled; ++i)
{
// Pop the oldest queued buffer from the source,
// fill it with the new data, then re-queue it
alSourceUnqueueBuffers(_source, 1, &buffer);
ALenum success = alGetError();
if(success != AL_NO_ERROR)
{
CONSOLE_LOG("Error Unqueuing streaming buffers: " + Ogre::StringConverter::toString(success));
return;
}
alBufferData(buffer, _streamingFormat, audioBuffers[i]->data, audioBufferSizes[i], _streamingFrequency);
success = alGetError();
if(success != AL_NO_ERROR)
{
CONSOLE_LOG("Error on re- alBufferData: " + Ogre::StringConverter::toString(success));
return;
}
alSourceQueueBuffers(_source, 1, &buffer);
success = alGetError();
if(success != AL_NO_ERROR)
{
CONSOLE_LOG("Error re-queuing streaming buffers: " + Ogre::StringConverter::toString(success) + " "
+ alGetString(success));
return;
}
}
// Make sure the source is still playing,
// and restart it if needed.
ALint playStatus;
alGetSourcei(_source, AL_SOURCE_STATE, &playStatus);
if(playStatus != AL_PLAYING)
alSourcePlay(_source);
正如您所看到的，我做了很多错误检查。但我不会从OpenAL或FFmpeg那里得到任何错误。 编辑：我听到的有点类似于视频中的实际音频，但非常高音调和口吃很多。此外，它似乎是在电视噪音的顶部播放。很奇怪。另外，它的播放速度比正确的音频慢得多。 编辑：2 使用AL_FORMAT_STEREO_FLOAT32后，声音以正确的速度播放，但仍然是非常高的音调和口吃（虽然比之前少）。
视频本身没有损坏，可以在任何播放器上播放。
，OpenAL也可以在同一个应用程序中播放* .way文件，因此也可以。任何想法在这里可能是错误的或如何正确地做到这一点？
我唯一的猜测是，不知何故，FFmpeg的解码函数不会产生OpenGL可以读取的数据。但这就是FFmpeg解码示例，所以我不知道缺少什么。据我了解，decode_audio4函数将帧解码为原始数据。 OpenAL应该能够处理RAW数据（或者更确切地说，不能与其他任何数据一起使用）。
答案 0 :(得分：2)
所以，我终于想出了怎么做。哎呀，真是一团糟。来自libav-users邮件列表上的用户的hint让我走上了正确的道路。
以下是我的错误：
在alBufferData函数中使用错误的格式。我使用了AL_FORMAT_STEREO16（因为这是OpenAL使用的每个流媒体示例）。我应该使用AL_FORMAT_STEREO_FLOAT32，因为视频I流是Ogg而vorbis存储在浮点中。使用swr_convert从AV_SAMPLE_FMT_FLTP转换为AV_SAMPLE_FMT_S16只会崩溃。不知道为什么。
不使用swr_convert将解码后的音频帧转换为目标格式。在我尝试使用swr_convert从FLTP转换为S16之后，它会在没有给出理由的情况下崩溃，我以为它被打破了。但在弄清楚我的第一个错误之后，我再次尝试，从FLTP转换为FLT（非平面）然后它工作了！因此OpenAL使用交错格式，而不是平面格式。很高兴知道。
所以这里有一个decodeAudioPacket函数，它适用于Ogg视频，vorbis音频流：
int decodeAudioPacket( AVPacket& p_packet, AVCodecContext* p_audioCodecContext, AVFrame* p_frame,
SwrContext* p_swrContext, uint8_t** p_destBuffer, int p_destLinesize,
FFmpegVideoPlayer* p_player, VideoInfo& p_videoInfo)
{
// Decode audio frame
int got_frame = 0;
int decoded = avcodec_decode_audio4(p_audioCodecContext, p_frame, &got_frame, &p_packet);
if (decoded < 0)
{
p_videoInfo.error = "Error decoding audio frame.";
return decoded;
}
if(decoded <= p_packet.size)
{
/* Move the unread data to the front and clear the end bits */
int remaining = p_packet.size - decoded;
memmove(p_packet.data, &p_packet.data[decoded], remaining);
av_shrink_packet(&p_packet, remaining);
}
// Frame is complete, store it in audio frame queue
if (got_frame)
{
int outputSamples = swr_convert(p_swrContext,
p_destBuffer, p_destLinesize,
(const uint8_t**)p_frame->extended_data, p_frame->nb_samples);
int bufferSize = av_get_bytes_per_sample(AV_SAMPLE_FMT_FLT) * p_videoInfo.audioNumChannels
* outputSamples;
int64_t duration = p_frame->pkt_duration;
int64_t dts = p_frame->pkt_dts;
if (staticOgreLog)
{
staticOgreLog->logMessage("Audio frame bufferSize / duration / dts: "
+ boost::lexical_cast<std::string>(bufferSize) + " / "
+ boost::lexical_cast<std::string>(duration) + " / "
+ boost::lexical_cast<std::string>(dts), Ogre::LML_NORMAL);
}
// Create the audio frame
AudioFrame* frame = new AudioFrame();
frame->dataSize = bufferSize;
frame->data = new uint8_t[bufferSize];
memcpy(frame->data, p_destBuffer[0], bufferSize);
double timeBase = ((double)p_audioCodecContext->time_base.num) / (double)p_audioCodecContext->time_base.den;
frame->lifeTime = duration * timeBase;
p_player->addAudioFrame(frame);
}
return decoded;
}
以下是我初始化上下文和目标缓冲区的方法：
// Initialize SWR context
SwrContext* swrContext = swr_alloc_set_opts(NULL,
audioCodecContext->channel_layout, AV_SAMPLE_FMT_FLT, audioCodecContext->sample_rate,
audioCodecContext->channel_layout, audioCodecContext->sample_fmt, audioCodecContext->sample_rate,
0, NULL);
int result = swr_init(swrContext);
// Create destination sample buffer
uint8_t** destBuffer = NULL;
int destBufferLinesize;
av_samples_alloc_array_and_samples( &destBuffer,
&destBufferLinesize,
videoInfo.audioNumChannels,
2048,
AV_SAMPLE_FMT_FLT,
0);