2bac896d5e
This CL defines the control flow of the adaptive AGC. It also defines
method and class stubs.
Contents:
1. Divide the 'agc2' build target into 'fixed_digital' and
'adaptive_digital'.
1. Update the dependencies of everything that depended on 'agc2'.
2. Define the sub-modules of the adaptive digital AGC 2. They are:
1. Level Estimator - it gets the energy and a speech probability
and updates a speech level estimate.
2. Noise Estimator - it gets an immutable view of the speech frame
and updates the noise level estimate
3. Gain applier - it gets the speech frame, the current speech and
noise estimates, and the speech probability. It finds a gain to
apply and applies it.
4. AdaptiveAgc - sets up and controls the sub-modules described
above.
Bug: webrtc:7494
Change-Id: Ib7ccd8924e94eead0bc5f935b5d8a12e06e24fd1
Reviewed-on: https://webrtc-review.googlesource.com/64440
Reviewed-by: Alessio Bazzica <alessiob@webrtc.org>
Commit-Queue: Alex Loiko <aleloi@webrtc.org>
Cr-Commit-Position: refs/heads/master@{#22628}
60 lines
2.1 KiB
C++
60 lines
2.1 KiB
C++
/*
|
|
* Copyright (c) 2018 The WebRTC project authors. All Rights Reserved.
|
|
*
|
|
* Use of this source code is governed by a BSD-style license
|
|
* that can be found in the LICENSE file in the root of the source
|
|
* tree. An additional intellectual property rights grant can be found
|
|
* in the file PATENTS. All contributing project authors may
|
|
* be found in the AUTHORS file in the root of the source tree.
|
|
*/
|
|
|
|
#include "modules/audio_processing/agc2/adaptive_agc.h"
|
|
|
|
#include <algorithm>
|
|
#include <numeric>
|
|
|
|
#include "common_audio/include/audio_util.h"
|
|
#include "modules/audio_processing/logging/apm_data_dumper.h"
|
|
#include "modules/audio_processing/vad/voice_activity_detector.h"
|
|
|
|
namespace webrtc {
|
|
|
|
AdaptiveAgc::AdaptiveAgc(ApmDataDumper* apm_data_dumper)
|
|
: speech_level_estimator_(apm_data_dumper),
|
|
gain_applier_(apm_data_dumper),
|
|
apm_data_dumper_(apm_data_dumper) {
|
|
RTC_DCHECK(apm_data_dumper);
|
|
}
|
|
|
|
AdaptiveAgc::~AdaptiveAgc() = default;
|
|
|
|
void AdaptiveAgc::Process(AudioFrameView<float> float_frame) {
|
|
// Some VADs are 'bursty'. They return several estimates for some
|
|
// frames, and no estimates for other frames. We want to feed all to
|
|
// the level estimator, but only care about the last level it
|
|
// produces.
|
|
rtc::ArrayView<const VadWithLevel::LevelAndProbability> vad_results =
|
|
vad_.AnalyzeFrame(float_frame);
|
|
for (const auto& vad_result : vad_results) {
|
|
apm_data_dumper_->DumpRaw("agc2_vad_probability",
|
|
vad_result.speech_probability);
|
|
apm_data_dumper_->DumpRaw("agc2_vad_rms_dbfs", vad_result.speech_rms_dbfs);
|
|
|
|
apm_data_dumper_->DumpRaw("agc2_vad_peak_dbfs",
|
|
vad_result.speech_peak_dbfs);
|
|
speech_level_estimator_.UpdateEstimation(vad_result);
|
|
}
|
|
|
|
const float speech_level_dbfs = speech_level_estimator_.LatestLevelEstimate();
|
|
|
|
const float noise_level_dbfs = noise_level_estimator_.Analyze(float_frame);
|
|
|
|
apm_data_dumper_->DumpRaw("agc2_noise_estimate_dbfs", noise_level_dbfs);
|
|
|
|
// The gain applier applies the gain.
|
|
gain_applier_.Process(speech_level_dbfs, noise_level_dbfs, vad_results,
|
|
float_frame);
|
|
}
|
|
|
|
} // namespace webrtc
|