mirror of
https://github.com/mollyim/webrtc.git
synced 2025-05-13 13:50:40 +01:00
d6ef33e59b
This switches from accepting a sample rate and convert to channel size over to accepting the channel size. Instead of InitializeIfNeeded: * Offer a way to explicitly initialize PushResampler via the ctor (needed for VoiceActivityDetectorWrapper) * Implicitly check for the right configuration from within Resample(). (All calls to Resample() were preceded by a call to Initialize) As part of this, refactor VoiceActivityDetectorWrapper (VADW): * VADW is now initialized in the constructor and more const. * Remove VADW::Initialize() and instead reconstruct VADW if needed. Add constants for max sample rate and num channels to audio_util.h In many cases the numbers for these values are embedded in the code which has led to some inconsistency. Bug: chromium:335805780 Change-Id: Iead0d52eb1b261a8d64e93f51401147c8fba32f0 Reviewed-on: https://webrtc-review.googlesource.com/c/src/+/353360 Reviewed-by: Gustaf Ullberg <gustaf@webrtc.org> Commit-Queue: Tomas Gunnarsson <tommi@webrtc.org> Cr-Commit-Position: refs/heads/main@{#42587}
90 lines
3.7 KiB
C++
90 lines
3.7 KiB
C++
/*
|
|
* Copyright (c) 2012 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 "audio/remix_resample.h"
|
|
|
|
#include <array>
|
|
|
|
#include "api/audio/audio_frame.h"
|
|
#include "audio/utility/audio_frame_operations.h"
|
|
#include "common_audio/resampler/include/push_resampler.h"
|
|
#include "rtc_base/checks.h"
|
|
#include "rtc_base/logging.h"
|
|
|
|
namespace webrtc {
|
|
namespace voe {
|
|
|
|
void RemixAndResample(const AudioFrame& src_frame,
|
|
PushResampler<int16_t>* resampler,
|
|
AudioFrame* dst_frame) {
|
|
RemixAndResample(src_frame.data_view(), src_frame.sample_rate_hz_, resampler,
|
|
dst_frame);
|
|
dst_frame->timestamp_ = src_frame.timestamp_;
|
|
dst_frame->elapsed_time_ms_ = src_frame.elapsed_time_ms_;
|
|
dst_frame->ntp_time_ms_ = src_frame.ntp_time_ms_;
|
|
dst_frame->packet_infos_ = src_frame.packet_infos_;
|
|
}
|
|
|
|
void RemixAndResample(InterleavedView<const int16_t> src_data,
|
|
int sample_rate_hz,
|
|
PushResampler<int16_t>* resampler,
|
|
AudioFrame* dst_frame) {
|
|
// The `samples_per_channel_` members must have been set correctly based on
|
|
// the associated sample rate and the assumed 10ms buffer size.
|
|
// TODO(tommi): Remove the `sample_rate_hz` param.
|
|
RTC_DCHECK_EQ(SampleRateToDefaultChannelSize(sample_rate_hz),
|
|
src_data.samples_per_channel());
|
|
RTC_DCHECK_EQ(SampleRateToDefaultChannelSize(dst_frame->sample_rate_hz_),
|
|
dst_frame->samples_per_channel());
|
|
|
|
// Temporary buffer in case downmixing is required.
|
|
std::array<int16_t, AudioFrame::kMaxDataSizeSamples> downmixed_audio;
|
|
|
|
// Downmix before resampling.
|
|
if (src_data.num_channels() > dst_frame->num_channels_) {
|
|
RTC_DCHECK(src_data.num_channels() == 2 || src_data.num_channels() == 4)
|
|
<< "num_channels: " << src_data.num_channels();
|
|
RTC_DCHECK(dst_frame->num_channels_ == 1 || dst_frame->num_channels_ == 2)
|
|
<< "dst_frame->num_channels_: " << dst_frame->num_channels_;
|
|
|
|
InterleavedView<int16_t> downmixed(downmixed_audio.data(),
|
|
src_data.samples_per_channel(),
|
|
dst_frame->num_channels_);
|
|
AudioFrameOperations::DownmixChannels(src_data, downmixed);
|
|
src_data = downmixed;
|
|
}
|
|
|
|
// TODO(yujo): for muted input frames, don't resample. Either 1) allow
|
|
// resampler to return output length without doing the resample, so we know
|
|
// how much to zero here; or 2) make resampler accept a hint that the input is
|
|
// zeroed.
|
|
|
|
// Stash away the originally requested number of channels. Then provide
|
|
// `dst_frame` as a target buffer with the same number of channels as the
|
|
// source.
|
|
auto original_dst_number_of_channels = dst_frame->num_channels_;
|
|
int out_length = resampler->Resample(
|
|
src_data, dst_frame->mutable_data(dst_frame->samples_per_channel_,
|
|
src_data.num_channels()));
|
|
RTC_CHECK_NE(out_length, -1) << "src_data.size=" << src_data.size();
|
|
RTC_DCHECK_EQ(dst_frame->samples_per_channel(),
|
|
out_length / src_data.num_channels());
|
|
|
|
// Upmix after resampling.
|
|
if (src_data.num_channels() == 1 && original_dst_number_of_channels == 2) {
|
|
// The audio in dst_frame really is mono at this point; MonoToStereo will
|
|
// set this back to stereo.
|
|
RTC_DCHECK_EQ(dst_frame->num_channels_, 1);
|
|
AudioFrameOperations::UpmixChannels(2, dst_frame);
|
|
}
|
|
}
|
|
|
|
} // namespace voe
|
|
} // namespace webrtc
|