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}
77 lines
2.9 KiB
C++
77 lines
2.9 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_COMMON_H_
|
|
#define MODULES_AUDIO_PROCESSING_AGC2_RNN_VAD_COMMON_H_
|
|
|
|
#include <stddef.h>
|
|
|
|
namespace webrtc {
|
|
namespace rnn_vad {
|
|
|
|
constexpr double kPi = 3.14159265358979323846;
|
|
|
|
constexpr int kSampleRate24kHz = 24000;
|
|
constexpr int kFrameSize10ms24kHz = kSampleRate24kHz / 100;
|
|
constexpr int kFrameSize20ms24kHz = kFrameSize10ms24kHz * 2;
|
|
|
|
// Pitch buffer.
|
|
constexpr int kMinPitch24kHz = kSampleRate24kHz / 800; // 0.00125 s.
|
|
constexpr int kMaxPitch24kHz = kSampleRate24kHz / 62.5; // 0.016 s.
|
|
constexpr int kBufSize24kHz = kMaxPitch24kHz + kFrameSize20ms24kHz;
|
|
static_assert((kBufSize24kHz & 1) == 0, "The buffer size must be even.");
|
|
|
|
// 24 kHz analysis.
|
|
// Define a higher minimum pitch period for the initial search. This is used to
|
|
// avoid searching for very short periods, for which a refinement step is
|
|
// responsible.
|
|
constexpr int kInitialMinPitch24kHz = 3 * kMinPitch24kHz;
|
|
static_assert(kMinPitch24kHz < kInitialMinPitch24kHz, "");
|
|
static_assert(kInitialMinPitch24kHz < kMaxPitch24kHz, "");
|
|
static_assert(kMaxPitch24kHz > kInitialMinPitch24kHz, "");
|
|
constexpr int kNumInvertedLags24kHz = kMaxPitch24kHz - kInitialMinPitch24kHz;
|
|
|
|
// 12 kHz analysis.
|
|
constexpr int kSampleRate12kHz = 12000;
|
|
constexpr int kFrameSize10ms12kHz = kSampleRate12kHz / 100;
|
|
constexpr int kFrameSize20ms12kHz = kFrameSize10ms12kHz * 2;
|
|
constexpr int kBufSize12kHz = kBufSize24kHz / 2;
|
|
constexpr int kInitialMinPitch12kHz = kInitialMinPitch24kHz / 2;
|
|
constexpr int kMaxPitch12kHz = kMaxPitch24kHz / 2;
|
|
static_assert(kMaxPitch12kHz > kInitialMinPitch12kHz, "");
|
|
// The inverted lags for the pitch interval [|kInitialMinPitch12kHz|,
|
|
// |kMaxPitch12kHz|] are in the range [0, |kNumInvertedLags12kHz|].
|
|
constexpr int kNumInvertedLags12kHz = kMaxPitch12kHz - kInitialMinPitch12kHz;
|
|
|
|
// 48 kHz constants.
|
|
constexpr int kMinPitch48kHz = kMinPitch24kHz * 2;
|
|
constexpr int kMaxPitch48kHz = kMaxPitch24kHz * 2;
|
|
|
|
// Spectral features.
|
|
constexpr int kNumBands = 22;
|
|
constexpr int kNumLowerBands = 6;
|
|
static_assert((0 < kNumLowerBands) && (kNumLowerBands < kNumBands), "");
|
|
constexpr int kCepstralCoeffsHistorySize = 8;
|
|
static_assert(kCepstralCoeffsHistorySize > 2,
|
|
"The history size must at least be 3 to compute first and second "
|
|
"derivatives.");
|
|
|
|
constexpr int kFeatureVectorSize = 42;
|
|
|
|
enum class Optimization { kNone, kSse2, kNeon };
|
|
|
|
// Detects what kind of optimizations to use for the code.
|
|
Optimization DetectOptimization();
|
|
|
|
} // namespace rnn_vad
|
|
} // namespace webrtc
|
|
|
|
#endif // MODULES_AUDIO_PROCESSING_AGC2_RNN_VAD_COMMON_H_
|