AGC2 as a new APM sub-module operating with hard-coded gain.

webrtc/modules/audio_processing/audio_processing_impl.cc

 /*
  *  Copyright (c) 2012 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 "webrtc/modules/audio_processing/audio_processing_impl.h"
 
 #include <math.h>
 #include <algorithm>
+#include <string>
 
 #include "webrtc/base/checks.h"
 #include "webrtc/base/logging.h"
 #include "webrtc/base/platform_file.h"
 #include "webrtc/base/trace_event.h"
 #include "webrtc/common_audio/audio_converter.h"
 #include "webrtc/common_audio/channel_buffer.h"
 #include "webrtc/common_audio/include/audio_util.h"
 #include "webrtc/common_audio/signal_processing/include/signal_processing_library.h"
 #include "webrtc/modules/audio_processing/aec/aec_core.h"
 #include "webrtc/modules/audio_processing/aec3/echo_canceller3.h"
+#include "webrtc/modules/audio_processing/agc2/gain_controller2.h"
 #include "webrtc/modules/audio_processing/agc/agc_manager_direct.h"
 #include "webrtc/modules/audio_processing/audio_buffer.h"
 #include "webrtc/modules/audio_processing/beamformer/nonlinear_beamformer.h"
 #include "webrtc/modules/audio_processing/common.h"
 #include "webrtc/modules/audio_processing/echo_cancellation_impl.h"
 #include "webrtc/modules/audio_processing/echo_control_mobile_impl.h"
 #include "webrtc/modules/audio_processing/gain_control_for_experimental_agc.h"
 #include "webrtc/modules/audio_processing/gain_control_impl.h"
 #if WEBRTC_INTELLIGIBILITY_ENHANCER
 #include "webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer.h"
@@ skipping 128 matching lines @@
 
 bool AudioProcessingImpl::ApmSubmoduleStates::Update(
     bool low_cut_filter_enabled,
     bool echo_canceller_enabled,
     bool mobile_echo_controller_enabled,
     bool residual_echo_detector_enabled,
     bool noise_suppressor_enabled,
     bool intelligibility_enhancer_enabled,
     bool beamformer_enabled,
     bool adaptive_gain_controller_enabled,
+    bool gain_controller2_enabled,
     bool level_controller_enabled,
     bool echo_canceller3_enabled,
     bool voice_activity_detector_enabled,
     bool level_estimator_enabled,
     bool transient_suppressor_enabled) {
   bool changed = false;
   changed |= (low_cut_filter_enabled != low_cut_filter_enabled_);
   changed |= (echo_canceller_enabled != echo_canceller_enabled_);
   changed |=
       (mobile_echo_controller_enabled != mobile_echo_controller_enabled_);
   changed |=
       (residual_echo_detector_enabled != residual_echo_detector_enabled_);
   changed |= (noise_suppressor_enabled != noise_suppressor_enabled_);
   changed |=
       (intelligibility_enhancer_enabled != intelligibility_enhancer_enabled_);
   changed |= (beamformer_enabled != beamformer_enabled_);
   changed |=
       (adaptive_gain_controller_enabled != adaptive_gain_controller_enabled_);
+  changed |=
+      (gain_controller2_enabled != gain_controller2_enabled_);
   changed |= (level_controller_enabled != level_controller_enabled_);
   changed |= (echo_canceller3_enabled != echo_canceller3_enabled_);
   changed |= (level_estimator_enabled != level_estimator_enabled_);
   changed |=
       (voice_activity_detector_enabled != voice_activity_detector_enabled_);
   changed |= (transient_suppressor_enabled != transient_suppressor_enabled_);
   if (changed) {
     low_cut_filter_enabled_ = low_cut_filter_enabled;
     echo_canceller_enabled_ = echo_canceller_enabled;
     mobile_echo_controller_enabled_ = mobile_echo_controller_enabled;
     residual_echo_detector_enabled_ = residual_echo_detector_enabled;
     noise_suppressor_enabled_ = noise_suppressor_enabled;
     intelligibility_enhancer_enabled_ = intelligibility_enhancer_enabled;
     beamformer_enabled_ = beamformer_enabled;
     adaptive_gain_controller_enabled_ = adaptive_gain_controller_enabled;
+    gain_controller2_enabled_ = gain_controller2_enabled;
     level_controller_enabled_ = level_controller_enabled;
     echo_canceller3_enabled_ = echo_canceller3_enabled;
     level_estimator_enabled_ = level_estimator_enabled;
     voice_activity_detector_enabled_ = voice_activity_detector_enabled;
     transient_suppressor_enabled_ = transient_suppressor_enabled;
   }
 
   changed |= first_update_;
   first_update_ = false;
   return changed;
@@ skipping 51 matching lines @@
   std::unique_ptr<IntelligibilityEnhancer> intelligibility_enhancer;
 #endif
 };
 
 struct AudioProcessingImpl::ApmPrivateSubmodules {
   explicit ApmPrivateSubmodules(NonlinearBeamformer* beamformer)
       : beamformer(beamformer) {}
   // Accessed internally from capture or during initialization
   std::unique_ptr<NonlinearBeamformer> beamformer;
   std::unique_ptr<AgcManagerDirect> agc_manager;
+  std::unique_ptr<GainController2> gain_controller2;
   std::unique_ptr<LowCutFilter> low_cut_filter;
   std::unique_ptr<LevelController> level_controller;
   std::unique_ptr<ResidualEchoDetector> residual_echo_detector;
   std::unique_ptr<EchoCanceller3> echo_canceller3;
 };
 
 AudioProcessing* AudioProcessing::Create() {
   webrtc::Config config;
   return Create(config, nullptr);
 }
@@ skipping 223 matching lines @@
   InitializeIntelligibility();
 #endif
   InitializeLowCutFilter();
   public_submodules_->noise_suppression->Initialize(num_proc_channels(),
                                                     proc_sample_rate_hz());
   public_submodules_->voice_detection->Initialize(proc_split_sample_rate_hz());
   public_submodules_->level_estimator->Initialize();
   InitializeLevelController();
   InitializeResidualEchoDetector();
   InitializeEchoCanceller3();
+  InitializeGainController2();
 
 #ifdef WEBRTC_AUDIOPROC_DEBUG_DUMP
   if (debug_dump_.debug_file->is_open()) {
     int err = WriteInitMessage();
     if (err != kNoError) {
       return err;
     }
   }
 #endif
 
@@ skipping 128 matching lines @@
   }
 
   if (config.echo_canceller3.enabled !=
       capture_nonlocked_.echo_canceller3_enabled) {
     capture_nonlocked_.echo_canceller3_enabled =
         config_.echo_canceller3.enabled;
     InitializeEchoCanceller3();
     LOG(LS_INFO) << "Echo canceller 3 activated: "
                  << capture_nonlocked_.echo_canceller3_enabled;
   }
+
+  config_ok = GainController2::Validate(config_.gain_controller2);
+  if (!config_ok) {
+    LOG(LS_ERROR) << "AudioProcessing module config error" << std::endl
+                  << "gain_controller2: "
+                  << GainController2::ToString(config_.gain_controller2)
+                  << std::endl
+                  << "Reverting to default parameter set";
+    config_.gain_controller2 = AudioProcessing::Config::GainController2();
+  }
+
+  if (config.gain_controller2.enabled !=
+      capture_nonlocked_.gain_controller2_enabled) {
+    capture_nonlocked_.gain_controller2_enabled =
+        config_.gain_controller2.enabled;
+    InitializeGainController2();
+    LOG(LS_INFO) << "Gain controller 2 activated: "
+                 << capture_nonlocked_.gain_controller2_enabled;
+  }
 }
 
 void AudioProcessingImpl::SetExtraOptions(const webrtc::Config& config) {
   // Run in a single-threaded manner when setting the extra options.
   rtc::CritScope cs_render(&crit_render_);
   rtc::CritScope cs_capture(&crit_capture_);
 
   public_submodules_->echo_cancellation->SetExtraOptions(config);
 
   if (capture_.transient_suppressor_enabled !=
       config.Get<ExperimentalNs>().enabled) {
     capture_.transient_suppressor_enabled =
         config.Get<ExperimentalNs>().enabled;
     InitializeTransient();
   }
 
 #if WEBRTC_INTELLIGIBILITY_ENHANCER
-  if(capture_nonlocked_.intelligibility_enabled !=
+  if (capture_nonlocked_.intelligibility_enabled !=
      config.Get<Intelligibility>().enabled) {
     capture_nonlocked_.intelligibility_enabled =
         config.Get<Intelligibility>().enabled;
     InitializeIntelligibility();
   }
 #endif
 
 #ifdef WEBRTC_ANDROID_PLATFORM_BUILD
   if (capture_nonlocked_.beamformer_enabled !=
           config.Get<Beamforming>().enabled) {
@@ skipping 584 matching lines @@
 
     public_submodules_->transient_suppressor->Suppress(
         capture_buffer->channels_f()[0], capture_buffer->num_frames(),
         capture_buffer->num_channels(),
         capture_buffer->split_bands_const_f(0)[kBand0To8kHz],
         capture_buffer->num_frames_per_band(), capture_buffer->keyboard_data(),
         capture_buffer->num_keyboard_frames(), voice_probability,
         capture_.key_pressed);
   }
 
+  if (capture_nonlocked_.gain_controller2_enabled) {
+    private_submodules_->gain_controller2->Process(capture_buffer);
+  }
+
   if (capture_nonlocked_.level_controller_enabled) {
     private_submodules_->level_controller->Process(capture_buffer);
   }
 
   // The level estimator operates on the recombined data.
   public_submodules_->level_estimator->ProcessStream(capture_buffer);
 
   capture_output_rms_.Analyze(rtc::ArrayView<const int16_t>(
       capture_buffer->channels_const()[0],
       capture_nonlocked_.capture_processing_format.num_frames()));
@@ skipping 398 matching lines @@
 bool AudioProcessingImpl::UpdateActiveSubmoduleStates() {
   return submodule_states_.Update(
       config_.high_pass_filter.enabled,
       public_submodules_->echo_cancellation->is_enabled(),
       public_submodules_->echo_control_mobile->is_enabled(),
       config_.residual_echo_detector.enabled,
       public_submodules_->noise_suppression->is_enabled(),
       capture_nonlocked_.intelligibility_enabled,
       capture_nonlocked_.beamformer_enabled,
       public_submodules_->gain_control->is_enabled(),
+      capture_nonlocked_.gain_controller2_enabled,
       capture_nonlocked_.level_controller_enabled,
       capture_nonlocked_.echo_canceller3_enabled,
       public_submodules_->voice_detection->is_enabled(),
       public_submodules_->level_estimator->is_enabled(),
       capture_.transient_suppressor_enabled);
 }
 
 
 void AudioProcessingImpl::InitializeTransient() {
   if (capture_.transient_suppressor_enabled) {
@@ skipping 30 matching lines @@
 }
 
 void AudioProcessingImpl::InitializeLowCutFilter() {
   if (config_.high_pass_filter.enabled) {
     private_submodules_->low_cut_filter.reset(
         new LowCutFilter(num_proc_channels(), proc_sample_rate_hz()));
   } else {
     private_submodules_->low_cut_filter.reset();
   }
 }
+
 void AudioProcessingImpl::InitializeEchoCanceller3() {
   if (capture_nonlocked_.echo_canceller3_enabled) {
     private_submodules_->echo_canceller3.reset(
         new EchoCanceller3(proc_sample_rate_hz(), true));
   } else {
     private_submodules_->echo_canceller3.reset();
   }
 }
 
+void AudioProcessingImpl::InitializeGainController2() {
+  if (capture_nonlocked_.gain_controller2_enabled) {
+    private_submodules_->gain_controller2.reset(
+        new GainController2(proc_sample_rate_hz()));
+  } else {
+    private_submodules_->gain_controller2.reset();
+  }
+}
+
 void AudioProcessingImpl::InitializeLevelController() {
   private_submodules_->level_controller->Initialize(proc_sample_rate_hz());
 }
 
 void AudioProcessingImpl::InitializeResidualEchoDetector() {
   private_submodules_->residual_echo_detector->Initialize();
 }
 
 void AudioProcessingImpl::MaybeUpdateHistograms() {
   static const int kMinDiffDelayMs = 60;
@@ skipping 234 matching lines @@
       previous_agc_level(0),
       echo_path_gain_change(false) {}
 
 AudioProcessingImpl::ApmCaptureState::~ApmCaptureState() = default;
 
 AudioProcessingImpl::ApmRenderState::ApmRenderState() = default;
 
 AudioProcessingImpl::ApmRenderState::~ApmRenderState() = default;
 
 }  // namespace webrtc