mirror of
https://github.com/mollyim/webrtc.git
synced 2025-05-19 08:37:54 +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}
79 lines
3 KiB
C++
79 lines
3 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_VAD_WRAPPER_H_
|
|
#define MODULES_AUDIO_PROCESSING_AGC2_VAD_WRAPPER_H_
|
|
|
|
#include <memory>
|
|
#include <vector>
|
|
|
|
#include "api/array_view.h"
|
|
#include "common_audio/resampler/include/push_resampler.h"
|
|
#include "modules/audio_processing/agc2/cpu_features.h"
|
|
#include "modules/audio_processing/include/audio_frame_view.h"
|
|
|
|
namespace webrtc {
|
|
|
|
// Wraps a single-channel Voice Activity Detector (VAD) which is used to analyze
|
|
// the first channel of the input audio frames. Takes care of resampling the
|
|
// input frames to match the sample rate of the wrapped VAD and periodically
|
|
// resets the VAD.
|
|
class VoiceActivityDetectorWrapper {
|
|
public:
|
|
// Single channel VAD interface.
|
|
class MonoVad {
|
|
public:
|
|
virtual ~MonoVad() = default;
|
|
// Returns the sample rate (Hz) required for the input frames analyzed by
|
|
// `ComputeProbability`.
|
|
virtual int SampleRateHz() const = 0;
|
|
// Resets the internal state.
|
|
virtual void Reset() = 0;
|
|
// Analyzes an audio frame and returns the speech probability.
|
|
virtual float Analyze(rtc::ArrayView<const float> frame) = 0;
|
|
};
|
|
|
|
// Ctor. Uses `cpu_features` to instantiate the default VAD.
|
|
VoiceActivityDetectorWrapper(const AvailableCpuFeatures& cpu_features,
|
|
int sample_rate_hz);
|
|
|
|
// Ctor. `vad_reset_period_ms` indicates the period in milliseconds to call
|
|
// `MonoVad::Reset()`; it must be equal to or greater than the duration of two
|
|
// frames. Uses `cpu_features` to instantiate the default VAD.
|
|
VoiceActivityDetectorWrapper(int vad_reset_period_ms,
|
|
const AvailableCpuFeatures& cpu_features,
|
|
int sample_rate_hz);
|
|
// Ctor. Uses a custom `vad`.
|
|
VoiceActivityDetectorWrapper(int vad_reset_period_ms,
|
|
std::unique_ptr<MonoVad> vad,
|
|
int sample_rate_hz);
|
|
|
|
VoiceActivityDetectorWrapper(const VoiceActivityDetectorWrapper&) = delete;
|
|
VoiceActivityDetectorWrapper& operator=(const VoiceActivityDetectorWrapper&) =
|
|
delete;
|
|
~VoiceActivityDetectorWrapper();
|
|
|
|
// Analyzes the first channel of `frame` and returns the speech probability.
|
|
// `frame` must be a 10 ms frame with the sample rate specified in the last
|
|
// `Initialize()` call.
|
|
float Analyze(AudioFrameView<const float> frame);
|
|
|
|
private:
|
|
const int vad_reset_period_frames_;
|
|
const int frame_size_;
|
|
int time_to_vad_reset_;
|
|
std::unique_ptr<MonoVad> vad_;
|
|
std::vector<float> resampled_buffer_;
|
|
PushResampler<float> resampler_;
|
|
};
|
|
|
|
} // namespace webrtc
|
|
|
|
#endif // MODULES_AUDIO_PROCESSING_AGC2_VAD_WRAPPER_H_
|