c36f8623c0
This reverts commit 1b6b958a4aa574b7852fe62efe5d4f96ce085d8b. Reason for revert: Bug fix Original change's description: > Revert "RNN VAD: pitch search optimizations (part 1)" > > This reverts commit 9da3e177fd5c2236cc15fea0ee8933e1dd0d8f6d. > > Reason for revert: bug in ComputePitchPeriod48kHz() > > Original change's description: > > RNN VAD: pitch search optimizations (part 1) > > > > TL;DR this CL improves efficiency and includes several code > > readability improvements mainly triggered by the comments to > > patch set #10. > > > > Highlights: > > - Split `FindBestPitchPeriods()` into 12 and 24 kHz versions > > to hard-code the input size and simplify the 24 kHz version > > - Loop in `ComputePitchPeriod48kHz()` (new name for > > `RefinePitchPeriod48kHz()`) removed since the lags for which > > we need to compute the auto correlation are a few > > - `ComputePitchGainThreshold()` was only used in unit tests; it's been > > moved into the anon ns and the test removed > > > > This CL makes `ComputePitchPeriod48kHz()` is about 10% faster (measured > > with https://webrtc-review.googlesource.com/c/src/+/191320/4/modules/audio_processing/agc2/rnn_vad/pitch_search_internal_unittest.cc). > > The realtime factor has improved by about +14%. > > > > Benchmarked as follows: > > ``` > > out/release/modules_unittests \ > > --gtest_filter=*RnnVadTest.DISABLED_RnnVadPerformance* \ > > --gtest_also_run_disabled_tests --logs > > ``` > > > > Results: > > > > | baseline | this CL > > ------+----------------------+------------------------ > > run 1 | 24.0231 +/- 0.591016 | 23.568 +/- 0.990788 > > | 370.06x | 377.207x > > ------+----------------------+------------------------ > > run 2 | 24.0485 +/- 0.957498 | 23.3714 +/- 0.857523 > > | 369.67x | 380.379x > > ------+----------------------+------------------------ > > run 2 | 25.4091 +/- 2.6123 | 23.709 +/- 1.04477 > > | 349.875x | 374.963x > > > > Bug: webrtc:10480 > > Change-Id: I9a3e9164b2442114b928de506c92a547c273882f > > Reviewed-on: https://webrtc-review.googlesource.com/c/src/+/191320 > > Reviewed-by: Per Åhgren <peah@webrtc.org> > > Commit-Queue: Alessio Bazzica <alessiob@webrtc.org> > > Cr-Commit-Position: refs/heads/master@{#32568} > > TBR=alessiob@webrtc.org,peah@webrtc.org > > No-Presubmit: true > No-Tree-Checks: true > No-Try: true > Bug: webrtc:10480 > Change-Id: I2a91f4f29566f872a7dfa220b31c6c625ed075db > Reviewed-on: https://webrtc-review.googlesource.com/c/src/+/192660 > Commit-Queue: Alessio Bazzica <alessiob@webrtc.org> > Reviewed-by: Alessio Bazzica <alessiob@webrtc.org> > Cr-Commit-Position: refs/heads/master@{#32581} TBR=alessiob@webrtc.org,peah@webrtc.org # Not skipping CQ checks because this is a reland. Bug: webrtc:10480 Change-Id: I66e3e8d73ebc04a437c01a0396cd5613c42a8cf5 Reviewed-on: https://webrtc-review.googlesource.com/c/src/+/192780 Reviewed-by: Alessio Bazzica <alessiob@webrtc.org> Reviewed-by: Per Åhgren <peah@webrtc.org> Commit-Queue: Alessio Bazzica <alessiob@webrtc.org> Cr-Commit-Position: refs/heads/master@{#32585}
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:
|
|
FeaturesExtractor();
|
|
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_
|