webrtc/modules/audio_processing/include/audio_processing_statistics.h
Sam Zackrisson 4db667be74 Add private voice detection instance to replace public voice detector
This adds a second (!) VoiceDetection instance in APM, activated via webrtc::AudioProcessing::Config and which reports its values in the webrtc::AudioProcessingStats struct.

The alternative is to reuse the existing instance, but that would require adding a proxy interface returned by AudioProcessing::voice_detection() to update the internal config of AudioProcessingImpl when calling voice_detection()->Enable().

Complexity-wise, no reasonable client will enable both interfaces simultaneously, so the footprint is negligible.

Bug: webrtc:9947
Change-Id: I7d8e28b9bf06abab8f9c6822424bdb9d803b987d
Reviewed-on: https://webrtc-review.googlesource.com/c/115243
Commit-Queue: Sam Zackrisson <saza@webrtc.org>
Reviewed-by: Ivo Creusen <ivoc@webrtc.org>
Cr-Commit-Position: refs/heads/master@{#26101}
2018-12-27 12:00:06 +00:00

73 lines
3.1 KiB
C++

/*
* Copyright 2017 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_INCLUDE_AUDIO_PROCESSING_STATISTICS_H_
#define MODULES_AUDIO_PROCESSING_INCLUDE_AUDIO_PROCESSING_STATISTICS_H_
#include <stdint.h>
#include "absl/types/optional.h"
#include "rtc_base/system/rtc_export.h"
namespace webrtc {
// This version of the stats uses Optionals, it will replace the regular
// AudioProcessingStatistics struct.
struct RTC_EXPORT AudioProcessingStats {
AudioProcessingStats();
AudioProcessingStats(const AudioProcessingStats& other);
~AudioProcessingStats();
// The root mean square (RMS) level in dBFS (decibels from digital
// full-scale) of the last capture frame, after processing. It is
// constrained to [-127, 0].
// The computation follows: https://tools.ietf.org/html/rfc6465
// with the intent that it can provide the RTP audio level indication.
// Only reported if level estimation is enabled in AudioProcessing::Config.
absl::optional<int> output_rms_dbfs;
// True if voice is detected in the last capture frame, after processing.
// It is conservative in flagging audio as speech, with low likelihood of
// incorrectly flagging a frame as voice.
// Only reported if voice detection is enabled in AudioProcessing::Config.
absl::optional<bool> voice_detected;
// AEC Statistics.
// ERL = 10log_10(P_far / P_echo)
absl::optional<double> echo_return_loss;
// ERLE = 10log_10(P_echo / P_out)
absl::optional<double> echo_return_loss_enhancement;
// Fraction of time that the AEC linear filter is divergent, in a 1-second
// non-overlapped aggregation window.
absl::optional<double> divergent_filter_fraction;
// The delay metrics consists of the delay median and standard deviation. It
// also consists of the fraction of delay estimates that can make the echo
// cancellation perform poorly. The values are aggregated until the first
// call to |GetStatistics()| and afterwards aggregated and updated every
// second. Note that if there are several clients pulling metrics from
// |GetStatistics()| during a session the first call from any of them will
// change to one second aggregation window for all.
absl::optional<int32_t> delay_median_ms;
absl::optional<int32_t> delay_standard_deviation_ms;
// Residual echo detector likelihood.
absl::optional<double> residual_echo_likelihood;
// Maximum residual echo likelihood from the last time period.
absl::optional<double> residual_echo_likelihood_recent_max;
// The instantaneous delay estimate produced in the AEC. The unit is in
// milliseconds and the value is the instantaneous value at the time of the
// call to |GetStatistics()|.
absl::optional<int32_t> delay_ms;
};
} // namespace webrtc
#endif // MODULES_AUDIO_PROCESSING_INCLUDE_AUDIO_PROCESSING_STATISTICS_H_