WebRTC中的混音算法

webrtc的混音算法在modules/audio_mixer/frame_combiner.cc文件的FrameCombiner::Combine()函数里

主干程序：

void FrameCombiner::Combine(const std::vector<AudioFrame*>& mix_list,
                            size_t number_of_channels,
                            int sample_rate,
                            size_t number_of_streams,
                            AudioFrame* audio_frame_for_mixing) {
  RTC_DCHECK(audio_frame_for_mixing);

  LogMixingStats(mix_list, sample_rate, number_of_streams);

  SetAudioFrameFields(mix_list, number_of_channels, sample_rate,
                      number_of_streams, audio_frame_for_mixing);

  const size_t samples_per_channel = static_cast<size_t>(
      (sample_rate * webrtc::AudioMixerImpl::kFrameDurationInMs) / 1000);

  for (const auto* frame : mix_list) {
    RTC_DCHECK_EQ(samples_per_channel, frame->samples_per_channel_);
    RTC_DCHECK_EQ(sample_rate, frame->sample_rate_hz_);
  }

  // The 'num_channels_' field of frames in 'mix_list' could be
  // different from 'number_of_channels'.
  for (auto* frame : mix_list) {
    RemixFrame(number_of_channels, frame);
  }

  if (number_of_streams <= 1) {
    MixFewFramesWithNoLimiter(mix_list, audio_frame_for_mixing);
    return;
  }

  std::array<OneChannelBuffer, kMaximumAmountOfChannels> mixing_buffer =
      MixToFloatFrame(mix_list, samples_per_channel, number_of_channels);

  // Put float data in an AudioFrameView.
  std::array<float*, kMaximumAmountOfChannels> channel_pointers{};
  for (size_t i = 0; i < number_of_channels; ++i) {
    channel_pointers[i] = &mixing_buffer[i][0];
  }
  AudioFrameView<float> mixing_buffer_view(
      &channel_pointers[0], number_of_channels, samples_per_channel);

  if (use_limiter_) {
    RunLimiter(mixing_buffer_view, &limiter_);
  }

  InterleaveToAudioFrame(mixing_buffer_view, audio_frame_for_mixing);
}

里面的MixToFloatFrame函数实现混音，将多个混音设备的声音混到数个声道中:

std::array<OneChannelBuffer, kMaximumAmountOfChannels> MixToFloatFrame(
    const std::vector<AudioFrame*>& mix_list,
    size_t samples_per_channel,
    size_t number_of_channels) {
  // Convert to FloatS16 and mix.
  using OneChannelBuffer = std::array<float, kMaximumChannelSize>;
  std::array<OneChannelBuffer, kMaximumAmountOfChannels> mixing_buffer{};

  for (size_t i = 0; i < mix_list.size(); ++i) {
    const AudioFrame* const frame = mix_list[i];
    for (size_t j = 0; j < number_of_channels; ++j) {
      for (size_t k = 0; k < samples_per_channel; ++k) {
        mixing_buffer[j][k] += frame->data()[number_of_channels * k + j];
      }
    }
  }
  return mixing_buffer;
}

RunLimiter函数，对混音结果进行增益处理, 同时防止溢出：

void RunLimiter(AudioFrameView<float> mixing_buffer_view, Limiter* limiter) {
  const size_t sample_rate = mixing_buffer_view.samples_per_channel() * 1000 /
                             AudioMixerImpl::kFrameDurationInMs;
  // TODO(alessiob): Avoid calling SetSampleRate every time.
  limiter->SetSampleRate(sample_rate);
  limiter->Process(mixing_buffer_view);
}

InterleaveToAudioFrame函数：

// Both interleaves and rounds.
void InterleaveToAudioFrame(AudioFrameView<const float> mixing_buffer_view,
                            AudioFrame* audio_frame_for_mixing) {
  const size_t number_of_channels = mixing_buffer_view.num_channels();
  const size_t samples_per_channel = mixing_buffer_view.samples_per_channel();
  // Put data in the result frame.
  for (size_t i = 0; i < number_of_channels; ++i) {
    for (size_t j = 0; j < samples_per_channel; ++j) {
      audio_frame_for_mixing->mutable_data()[number_of_channels * j + i] =
          FloatS16ToS16(mixing_buffer_view.channel(i)[j]);
    }
  }
}