253f8369bb
In preparation for adding AVX2 code, a safe scheme to support
different SIMD optimizations is added.
Safety features:
- AVX2 kill switch to stop using it even if supported by the
architecture
- struct indicating the available CPU features propagated from
AGC2 to each component; in this way
- better control over the unit tests
- no need to propagate individual kill switches but just
set to false features that are turned off
Note that (i) this CL does not change the performance of the RNN VAD
and (ii) no AVX2 optimization is added yet.
Bug: webrtc:10480
Change-Id: I0e61f3311ecd140f38369cf68b6e5954f3dc1f5a
Reviewed-on: https://webrtc-review.googlesource.com/c/src/+/193140
Reviewed-by: Per Åhgren <peah@webrtc.org>
Commit-Queue: Alessio Bazzica <alessiob@webrtc.org>
Cr-Commit-Position: refs/heads/master@{#32739}
62 lines
2.4 KiB
C++
62 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_RNN_VAD_FEATURES_EXTRACTION_H_
|
|
#define MODULES_AUDIO_PROCESSING_AGC2_RNN_VAD_FEATURES_EXTRACTION_H_
|
|
|
|
#include <vector>
|
|
|
|
#include "api/array_view.h"
|
|
#include "modules/audio_processing/agc2/biquad_filter.h"
|
|
#include "modules/audio_processing/agc2/rnn_vad/common.h"
|
|
#include "modules/audio_processing/agc2/rnn_vad/pitch_search.h"
|
|
#include "modules/audio_processing/agc2/rnn_vad/sequence_buffer.h"
|
|
#include "modules/audio_processing/agc2/rnn_vad/spectral_features.h"
|
|
|
|
namespace webrtc {
|
|
namespace rnn_vad {
|
|
|
|
// Feature extractor to feed the VAD RNN.
|
|
class FeaturesExtractor {
|
|
public:
|
|
explicit FeaturesExtractor(const AvailableCpuFeatures& cpu_features);
|
|
FeaturesExtractor(const FeaturesExtractor&) = delete;
|
|
FeaturesExtractor& operator=(const FeaturesExtractor&) = delete;
|
|
~FeaturesExtractor();
|
|
void Reset();
|
|
// Analyzes the samples, computes the feature vector and returns true if
|
|
// silence is detected (false if not). When silence is detected,
|
|
// |feature_vector| is partially written and therefore must not be used to
|
|
// feed the VAD RNN.
|
|
bool CheckSilenceComputeFeatures(
|
|
rtc::ArrayView<const float, kFrameSize10ms24kHz> samples,
|
|
rtc::ArrayView<float, kFeatureVectorSize> feature_vector);
|
|
|
|
private:
|
|
const bool use_high_pass_filter_;
|
|
// TODO(bugs.webrtc.org/7494): Remove HPF depending on how AGC2 is used in APM
|
|
// and on whether an HPF is already used as pre-processing step in APM.
|
|
BiQuadFilter hpf_;
|
|
SequenceBuffer<float, kBufSize24kHz, kFrameSize10ms24kHz, kFrameSize20ms24kHz>
|
|
pitch_buf_24kHz_;
|
|
rtc::ArrayView<const float, kBufSize24kHz> pitch_buf_24kHz_view_;
|
|
std::vector<float> lp_residual_;
|
|
rtc::ArrayView<float, kBufSize24kHz> lp_residual_view_;
|
|
PitchEstimator pitch_estimator_;
|
|
rtc::ArrayView<const float, kFrameSize20ms24kHz> reference_frame_view_;
|
|
SpectralFeaturesExtractor spectral_features_extractor_;
|
|
int pitch_period_48kHz_;
|
|
};
|
|
|
|
} // namespace rnn_vad
|
|
} // namespace webrtc
|
|
|
|
#endif // MODULES_AUDIO_PROCESSING_AGC2_RNN_VAD_FEATURES_EXTRACTION_H_
|