1b6b958a4a
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}
91 lines
3.5 KiB
C++
91 lines
3.5 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.
|
|
*/
|
|
|
|
#include "modules/audio_processing/agc2/rnn_vad/features_extraction.h"
|
|
|
|
#include <array>
|
|
|
|
#include "modules/audio_processing/agc2/rnn_vad/lp_residual.h"
|
|
#include "rtc_base/checks.h"
|
|
|
|
namespace webrtc {
|
|
namespace rnn_vad {
|
|
namespace {
|
|
|
|
// Generated via "B, A = scipy.signal.butter(2, 30/12000, btype='highpass')"
|
|
const BiQuadFilter::BiQuadCoefficients kHpfConfig24k = {
|
|
{0.99446179f, -1.98892358f, 0.99446179f},
|
|
{-1.98889291f, 0.98895425f}};
|
|
|
|
} // namespace
|
|
|
|
FeaturesExtractor::FeaturesExtractor()
|
|
: use_high_pass_filter_(false),
|
|
pitch_buf_24kHz_(),
|
|
pitch_buf_24kHz_view_(pitch_buf_24kHz_.GetBufferView()),
|
|
lp_residual_(kBufSize24kHz),
|
|
lp_residual_view_(lp_residual_.data(), kBufSize24kHz),
|
|
pitch_estimator_(),
|
|
reference_frame_view_(pitch_buf_24kHz_.GetMostRecentValuesView()) {
|
|
RTC_DCHECK_EQ(kBufSize24kHz, lp_residual_.size());
|
|
hpf_.Initialize(kHpfConfig24k);
|
|
Reset();
|
|
}
|
|
|
|
FeaturesExtractor::~FeaturesExtractor() = default;
|
|
|
|
void FeaturesExtractor::Reset() {
|
|
pitch_buf_24kHz_.Reset();
|
|
spectral_features_extractor_.Reset();
|
|
if (use_high_pass_filter_)
|
|
hpf_.Reset();
|
|
}
|
|
|
|
bool FeaturesExtractor::CheckSilenceComputeFeatures(
|
|
rtc::ArrayView<const float, kFrameSize10ms24kHz> samples,
|
|
rtc::ArrayView<float, kFeatureVectorSize> feature_vector) {
|
|
// Pre-processing.
|
|
if (use_high_pass_filter_) {
|
|
std::array<float, kFrameSize10ms24kHz> samples_filtered;
|
|
hpf_.Process(samples, samples_filtered);
|
|
// Feed buffer with the pre-processed version of |samples|.
|
|
pitch_buf_24kHz_.Push(samples_filtered);
|
|
} else {
|
|
// Feed buffer with |samples|.
|
|
pitch_buf_24kHz_.Push(samples);
|
|
}
|
|
// Extract the LP residual.
|
|
float lpc_coeffs[kNumLpcCoefficients];
|
|
ComputeAndPostProcessLpcCoefficients(pitch_buf_24kHz_view_, lpc_coeffs);
|
|
ComputeLpResidual(lpc_coeffs, pitch_buf_24kHz_view_, lp_residual_view_);
|
|
// Estimate pitch on the LP-residual and write the normalized pitch period
|
|
// into the output vector (normalization based on training data stats).
|
|
pitch_info_48kHz_ = pitch_estimator_.Estimate(lp_residual_view_);
|
|
feature_vector[kFeatureVectorSize - 2] =
|
|
0.01f * (pitch_info_48kHz_.period - 300);
|
|
// Extract lagged frames (according to the estimated pitch period).
|
|
RTC_DCHECK_LE(pitch_info_48kHz_.period / 2, kMaxPitch24kHz);
|
|
auto lagged_frame = pitch_buf_24kHz_view_.subview(
|
|
kMaxPitch24kHz - pitch_info_48kHz_.period / 2, kFrameSize20ms24kHz);
|
|
// Analyze reference and lagged frames checking if silence has been detected
|
|
// and write the feature vector.
|
|
return spectral_features_extractor_.CheckSilenceComputeFeatures(
|
|
reference_frame_view_, {lagged_frame.data(), kFrameSize20ms24kHz},
|
|
{feature_vector.data() + kNumLowerBands, kNumBands - kNumLowerBands},
|
|
{feature_vector.data(), kNumLowerBands},
|
|
{feature_vector.data() + kNumBands, kNumLowerBands},
|
|
{feature_vector.data() + kNumBands + kNumLowerBands, kNumLowerBands},
|
|
{feature_vector.data() + kNumBands + 2 * kNumLowerBands, kNumLowerBands},
|
|
&feature_vector[kFeatureVectorSize - 1]);
|
|
}
|
|
|
|
} // namespace rnn_vad
|
|
} // namespace webrtc
|