mirror of
https://github.com/mollyim/webrtc.git
synced 2025-05-17 23:57:59 +01:00
8dbdf5e3bf
Internal refactoring of AGC2 to decouple the VAD, its wrapper and the peak and RMS level measurements. Bit exactness verified with audioproc_f on a collection of AEC dumps and Wav files (42 recordings in total). Bug: webrtc:7494 Change-Id: Ib560f1fcaa601557f4f30e47025c69e91b1b62e0 Reviewed-on: https://webrtc-review.googlesource.com/c/src/+/234524 Commit-Queue: Alessio Bazzica <alessiob@webrtc.org> Reviewed-by: Hanna Silen <silen@webrtc.org> Cr-Commit-Position: refs/heads/main@{#35208}
77 lines
2.6 KiB
C++
77 lines
2.6 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.
|
|
*/
|
|
|
|
#ifndef MODULES_AUDIO_PROCESSING_AGC2_ADAPTIVE_MODE_LEVEL_ESTIMATOR_H_
|
|
#define MODULES_AUDIO_PROCESSING_AGC2_ADAPTIVE_MODE_LEVEL_ESTIMATOR_H_
|
|
|
|
#include <stddef.h>
|
|
|
|
#include <type_traits>
|
|
|
|
#include "modules/audio_processing/agc2/agc2_common.h"
|
|
#include "modules/audio_processing/agc2/vad_wrapper.h"
|
|
#include "modules/audio_processing/include/audio_processing.h"
|
|
|
|
namespace webrtc {
|
|
class ApmDataDumper;
|
|
|
|
// Level estimator for the digital adaptive gain controller.
|
|
class AdaptiveModeLevelEstimator {
|
|
public:
|
|
AdaptiveModeLevelEstimator(
|
|
ApmDataDumper* apm_data_dumper,
|
|
const AudioProcessing::Config::GainController2::AdaptiveDigital& config);
|
|
AdaptiveModeLevelEstimator(const AdaptiveModeLevelEstimator&) = delete;
|
|
AdaptiveModeLevelEstimator& operator=(const AdaptiveModeLevelEstimator&) =
|
|
delete;
|
|
|
|
// Updates the level estimation.
|
|
void Update(float rms_dbfs, float peak_dbfs, float speech_probability);
|
|
// Returns the estimated speech plus noise level.
|
|
float level_dbfs() const { return level_dbfs_; }
|
|
// Returns true if the estimator is confident on its current estimate.
|
|
bool IsConfident() const;
|
|
|
|
void Reset();
|
|
|
|
private:
|
|
// Part of the level estimator state used for check-pointing and restore ops.
|
|
struct LevelEstimatorState {
|
|
bool operator==(const LevelEstimatorState& s) const;
|
|
inline bool operator!=(const LevelEstimatorState& s) const {
|
|
return !(*this == s);
|
|
}
|
|
// TODO(bugs.webrtc.org/7494): Remove `time_to_confidence_ms` if redundant.
|
|
int time_to_confidence_ms;
|
|
struct Ratio {
|
|
float numerator;
|
|
float denominator;
|
|
float GetRatio() const;
|
|
} level_dbfs;
|
|
};
|
|
static_assert(std::is_trivially_copyable<LevelEstimatorState>::value, "");
|
|
|
|
void ResetLevelEstimatorState(LevelEstimatorState& state) const;
|
|
|
|
void DumpDebugData() const;
|
|
|
|
ApmDataDumper* const apm_data_dumper_;
|
|
|
|
const float initial_speech_level_dbfs_;
|
|
const int adjacent_speech_frames_threshold_;
|
|
LevelEstimatorState preliminary_state_;
|
|
LevelEstimatorState reliable_state_;
|
|
float level_dbfs_;
|
|
int num_adjacent_speech_frames_;
|
|
};
|
|
|
|
} // namespace webrtc
|
|
|
|
#endif // MODULES_AUDIO_PROCESSING_AGC2_ADAPTIVE_MODE_LEVEL_ESTIMATOR_H_
|