AnotherFoxGuy/webrtc-audio-processing
1
0
Fork 0
Code Pull Requests Activity

Bump to WebRTC M120 release

Browse Source 
Some API deprecation -- ExperimentalAgc and ExperimentalNs are gone.
We're continuing to carry iSAC even though it's gone upstream, but maybe
we'll want to drop that soon.
This commit is contained in:
Arun Raghavan
2023-12-12 10:42:58 -05:00
parent 9a202fb8c2
commit c6abf6cd3f
479 changed files with 20900 additions and 11996 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
webrtc/modules/audio_processing/agc2/rnn_vad/features_extraction.cc
View File

@ -19,23 +19,23 @@ namespace webrtc {
namespace rnn_vad {
namespace {
// Generated via "B, A = scipy.signal.butter(2, 30/12000, btype='highpass')"
const BiQuadFilter::BiQuadCoefficients kHpfConfig24k = {
// Computed as `scipy.signal.butter(N=2, Wn=60/24000, btype='highpass')`.
constexpr BiQuadFilter::Config kHpfConfig24k{
{0.99446179f, -1.98892358f, 0.99446179f},
{-1.98889291f, 0.98895425f}};
} // namespace
FeaturesExtractor::FeaturesExtractor()
FeaturesExtractor::FeaturesExtractor(const AvailableCpuFeatures& cpu_features)
: use_high_pass_filter_(false),
hpf_(kHpfConfig24k),
pitch_buf_24kHz_(),
pitch_buf_24kHz_view_(pitch_buf_24kHz_.GetBufferView()),
lp_residual_(kBufSize24kHz),
lp_residual_view_(lp_residual_.data(), kBufSize24kHz),
pitch_estimator_(),
pitch_estimator_(cpu_features),
reference_frame_view_(pitch_buf_24kHz_.GetMostRecentValuesView()) {
RTC_DCHECK_EQ(kBufSize24kHz, lp_residual_.size());
hpf_.Initialize(kHpfConfig24k);
Reset();
}
@ -44,8 +44,9 @@ FeaturesExtractor::~FeaturesExtractor() = default;
void FeaturesExtractor::Reset() {
pitch_buf_24kHz_.Reset();
spectral_features_extractor_.Reset();
if (use_high_pass_filter_)
if (use_high_pass_filter_) {
hpf_.Reset();
}
}
bool FeaturesExtractor::CheckSilenceComputeFeatures(
@ -55,10 +56,10 @@ bool FeaturesExtractor::CheckSilenceComputeFeatures(
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|.
// Feed buffer with the pre-processed version of `samples`.
pitch_buf_24kHz_.Push(samples_filtered);
} else {
// Feed buffer with |samples|.
// Feed buffer with `samples`.
pitch_buf_24kHz_.Push(samples);
}
// Extract the LP residual.
@ -67,13 +68,12 @@ bool FeaturesExtractor::CheckSilenceComputeFeatures(
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 * (static_cast<int>(pitch_info_48kHz_.period) - 300);
pitch_period_48kHz_ = pitch_estimator_.Estimate(lp_residual_view_);
feature_vector[kFeatureVectorSize - 2] = 0.01f * (pitch_period_48kHz_ - 300);
// Extract lagged frames (according to the estimated pitch period).
RTC_DCHECK_LE(pitch_info_48kHz_.period / 2, kMaxPitch24kHz);
RTC_DCHECK_LE(pitch_period_48kHz_ / 2, kMaxPitch24kHz);
auto lagged_frame = pitch_buf_24kHz_view_.subview(
kMaxPitch24kHz - pitch_info_48kHz_.period / 2, kFrameSize20ms24kHz);
kMaxPitch24kHz - pitch_period_48kHz_ / 2, kFrameSize20ms24kHz);
// Analyze reference and lagged frames checking if silence has been detected
// and write the feature vector.
return spectral_features_extractor_.CheckSilenceComputeFeatures(