87b86acde9
Make the digital adaptive gain applier more robust to VAD false positives. Achieved by allowing a gain increase only if enough adjacent speech frames are observed. Tested: - Bit-exactness verified with audioproc_f - If `kDefaultDigitalGainApplierAdjacentSpeechFramesThreshold` == 2 then not bit-exact Bug: webrtc:7494 Change-Id: I3bab5a449aaf0ef1a64b671b413ba2ddb4688cd2 Reviewed-on: https://webrtc-review.googlesource.com/c/src/+/186042 Commit-Queue: Alessio Bazzica <alessiob@webrtc.org> Reviewed-by: Ivo Creusen <ivoc@webrtc.org> Cr-Commit-Position: refs/heads/master@{#32263}
63 lines
2.4 KiB
C++
63 lines
2.4 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_DIGITAL_GAIN_APPLIER_H_
|
|
#define MODULES_AUDIO_PROCESSING_AGC2_ADAPTIVE_DIGITAL_GAIN_APPLIER_H_
|
|
|
|
#include "modules/audio_processing/agc2/gain_applier.h"
|
|
#include "modules/audio_processing/agc2/vad_with_level.h"
|
|
#include "modules/audio_processing/include/audio_frame_view.h"
|
|
|
|
namespace webrtc {
|
|
|
|
class ApmDataDumper;
|
|
|
|
// Part of the adaptive digital controller that applies a digital adaptive gain.
|
|
// The gain is updated towards a target. The logic decides when gain updates are
|
|
// allowed, it controls the adaptation speed and caps the target based on the
|
|
// estimated noise level and the speech level estimate confidence.
|
|
class AdaptiveDigitalGainApplier {
|
|
public:
|
|
// Information about a frame to process.
|
|
struct FrameInfo {
|
|
float input_level_dbfs; // Estimated speech plus noise level.
|
|
float input_noise_level_dbfs; // Estimated noise level.
|
|
VadLevelAnalyzer::Result vad_result;
|
|
float limiter_envelope_dbfs; // Envelope level from the limiter.
|
|
bool estimate_is_confident;
|
|
};
|
|
|
|
explicit AdaptiveDigitalGainApplier(ApmDataDumper* apm_data_dumper);
|
|
// Ctor. `adjacent_speech_frames_threshold` indicates how many speech frames
|
|
// are required before a gain increase is allowed.
|
|
AdaptiveDigitalGainApplier(ApmDataDumper* apm_data_dumper,
|
|
int adjacent_speech_frames_threshold);
|
|
AdaptiveDigitalGainApplier(const AdaptiveDigitalGainApplier&) = delete;
|
|
AdaptiveDigitalGainApplier& operator=(const AdaptiveDigitalGainApplier&) =
|
|
delete;
|
|
|
|
// Analyzes `info`, updates the digital gain and applies it to `frame`.
|
|
void Process(const FrameInfo& info, AudioFrameView<float> frame);
|
|
|
|
private:
|
|
ApmDataDumper* const apm_data_dumper_;
|
|
GainApplier gain_applier_;
|
|
|
|
const int adjacent_speech_frames_threshold_;
|
|
|
|
int calls_since_last_gain_log_;
|
|
int frames_to_gain_increase_allowed_;
|
|
float last_gain_db_;
|
|
};
|
|
|
|
} // namespace webrtc
|
|
|
|
#endif // MODULES_AUDIO_PROCESSING_AGC2_ADAPTIVE_DIGITAL_GAIN_APPLIER_H_
|