mirror of
https://github.com/mollyim/webrtc.git
synced 2025-05-16 07:10:38 +01:00
92ea95e34a
In https://webrtc-review.googlesource.com/c/src/+/1560 we moved WebRTC from src/webrtc to src/ (in order to preserve an healthy git history). This CL takes care of fixing header guards, #include paths, etc... NOPRESUBMIT=true NOTREECHECKS=true NOTRY=true TBR=tommi@webrtc.org Bug: chromium:611808 Change-Id: Iea91618212bee0af16aa3f05071eab8f93706578 Reviewed-on: https://webrtc-review.googlesource.com/1561 Reviewed-by: Mirko Bonadei <mbonadei@webrtc.org> Reviewed-by: Henrik Kjellander <kjellander@webrtc.org> Commit-Queue: Mirko Bonadei <mbonadei@webrtc.org> Cr-Commit-Position: refs/heads/master@{#19846}
71 lines
2.5 KiB
C++
71 lines
2.5 KiB
C++
/*
|
|
* Copyright (c) 2015 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_VAD_VOICE_ACTIVITY_DETECTOR_H_
|
|
#define MODULES_AUDIO_PROCESSING_VAD_VOICE_ACTIVITY_DETECTOR_H_
|
|
|
|
#include <memory>
|
|
#include <vector>
|
|
|
|
#include "common_audio/resampler/include/resampler.h"
|
|
#include "modules/audio_processing/vad/vad_audio_proc.h"
|
|
#include "modules/audio_processing/vad/common.h"
|
|
#include "modules/audio_processing/vad/pitch_based_vad.h"
|
|
#include "modules/audio_processing/vad/standalone_vad.h"
|
|
|
|
namespace webrtc {
|
|
|
|
// A Voice Activity Detector (VAD) that combines the voice probability from the
|
|
// StandaloneVad and PitchBasedVad to get a more robust estimation.
|
|
class VoiceActivityDetector {
|
|
public:
|
|
VoiceActivityDetector();
|
|
~VoiceActivityDetector();
|
|
|
|
// Processes each audio chunk and estimates the voice probability. The maximum
|
|
// supported sample rate is 32kHz.
|
|
// TODO(aluebs): Change |length| to size_t.
|
|
void ProcessChunk(const int16_t* audio, size_t length, int sample_rate_hz);
|
|
|
|
// Returns a vector of voice probabilities for each chunk. It can be empty for
|
|
// some chunks, but it catches up afterwards returning multiple values at
|
|
// once.
|
|
const std::vector<double>& chunkwise_voice_probabilities() const {
|
|
return chunkwise_voice_probabilities_;
|
|
}
|
|
|
|
// Returns a vector of RMS values for each chunk. It has the same length as
|
|
// chunkwise_voice_probabilities().
|
|
const std::vector<double>& chunkwise_rms() const { return chunkwise_rms_; }
|
|
|
|
// Returns the last voice probability, regardless of the internal
|
|
// implementation, although it has a few chunks of delay.
|
|
float last_voice_probability() const { return last_voice_probability_; }
|
|
|
|
private:
|
|
// TODO(aluebs): Change these to float.
|
|
std::vector<double> chunkwise_voice_probabilities_;
|
|
std::vector<double> chunkwise_rms_;
|
|
|
|
float last_voice_probability_;
|
|
|
|
Resampler resampler_;
|
|
VadAudioProc audio_processing_;
|
|
|
|
std::unique_ptr<StandaloneVad> standalone_vad_;
|
|
PitchBasedVad pitch_based_vad_;
|
|
|
|
int16_t resampled_[kLength10Ms];
|
|
AudioFeatures features_;
|
|
};
|
|
|
|
} // namespace webrtc
|
|
|
|
#endif // MODULES_AUDIO_PROCESSING_VAD_VOICE_ACTIVITY_DETECTOR_H_
|