mirror of
https://github.com/mollyim/webrtc.git
synced 2025-05-16 23:30:48 +01:00
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}
40 lines
1.3 KiB
C++
40 lines
1.3 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_VAD_VAD_WITH_LEVEL_H_
|
|
#define MODULES_AUDIO_PROCESSING_VAD_VAD_WITH_LEVEL_H_
|
|
|
|
#include "api/array_view.h"
|
|
#include "modules/audio_processing/include/audio_frame_view.h"
|
|
|
|
namespace webrtc {
|
|
class VadWithLevel {
|
|
public:
|
|
struct LevelAndProbability {
|
|
constexpr LevelAndProbability(float prob, float rms, float peak)
|
|
: speech_probability(prob),
|
|
speech_rms_dbfs(rms),
|
|
speech_peak_dbfs(peak) {}
|
|
LevelAndProbability() = default;
|
|
float speech_probability = 0;
|
|
float speech_rms_dbfs = 0; // Root mean square in decibels to full-scale.
|
|
float speech_peak_dbfs = 0;
|
|
};
|
|
|
|
// TODO(webrtc:7494): This is a stub. Add implementation.
|
|
rtc::ArrayView<const LevelAndProbability> AnalyzeFrame(
|
|
AudioFrameView<const float> frame) {
|
|
return {nullptr, 0};
|
|
}
|
|
};
|
|
|
|
} // namespace webrtc
|
|
|
|
#endif // MODULES_AUDIO_PROCESSING_VAD_VAD_WITH_LEVEL_H_
|