Update to current webrtc library
This is from the upstream library commit id 3326535126e435f1ba647885ce43a8f0f3d317eb, corresponding to Chromium 88.0.4290.1.
This commit is contained in:
170
webrtc/api/audio_codecs/audio_decoder.cc
Normal file
170
webrtc/api/audio_codecs/audio_decoder.cc
Normal file
@ -0,0 +1,170 @@
|
||||
/*
|
||||
* 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 "api/audio_codecs/audio_decoder.h"
|
||||
|
||||
#include <assert.h>
|
||||
|
||||
#include <memory>
|
||||
#include <utility>
|
||||
|
||||
#include "api/array_view.h"
|
||||
#include "rtc_base/checks.h"
|
||||
#include "rtc_base/sanitizer.h"
|
||||
#include "rtc_base/trace_event.h"
|
||||
|
||||
namespace webrtc {
|
||||
|
||||
namespace {
|
||||
|
||||
class OldStyleEncodedFrame final : public AudioDecoder::EncodedAudioFrame {
|
||||
public:
|
||||
OldStyleEncodedFrame(AudioDecoder* decoder, rtc::Buffer&& payload)
|
||||
: decoder_(decoder), payload_(std::move(payload)) {}
|
||||
|
||||
size_t Duration() const override {
|
||||
const int ret = decoder_->PacketDuration(payload_.data(), payload_.size());
|
||||
return ret < 0 ? 0 : static_cast<size_t>(ret);
|
||||
}
|
||||
|
||||
absl::optional<DecodeResult> Decode(
|
||||
rtc::ArrayView<int16_t> decoded) const override {
|
||||
auto speech_type = AudioDecoder::kSpeech;
|
||||
const int ret = decoder_->Decode(
|
||||
payload_.data(), payload_.size(), decoder_->SampleRateHz(),
|
||||
decoded.size() * sizeof(int16_t), decoded.data(), &speech_type);
|
||||
return ret < 0 ? absl::nullopt
|
||||
: absl::optional<DecodeResult>(
|
||||
{static_cast<size_t>(ret), speech_type});
|
||||
}
|
||||
|
||||
private:
|
||||
AudioDecoder* const decoder_;
|
||||
const rtc::Buffer payload_;
|
||||
};
|
||||
|
||||
} // namespace
|
||||
|
||||
bool AudioDecoder::EncodedAudioFrame::IsDtxPacket() const {
|
||||
return false;
|
||||
}
|
||||
|
||||
AudioDecoder::ParseResult::ParseResult() = default;
|
||||
AudioDecoder::ParseResult::ParseResult(ParseResult&& b) = default;
|
||||
AudioDecoder::ParseResult::ParseResult(uint32_t timestamp,
|
||||
int priority,
|
||||
std::unique_ptr<EncodedAudioFrame> frame)
|
||||
: timestamp(timestamp), priority(priority), frame(std::move(frame)) {
|
||||
RTC_DCHECK_GE(priority, 0);
|
||||
}
|
||||
|
||||
AudioDecoder::ParseResult::~ParseResult() = default;
|
||||
|
||||
AudioDecoder::ParseResult& AudioDecoder::ParseResult::operator=(
|
||||
ParseResult&& b) = default;
|
||||
|
||||
std::vector<AudioDecoder::ParseResult> AudioDecoder::ParsePayload(
|
||||
rtc::Buffer&& payload,
|
||||
uint32_t timestamp) {
|
||||
std::vector<ParseResult> results;
|
||||
std::unique_ptr<EncodedAudioFrame> frame(
|
||||
new OldStyleEncodedFrame(this, std::move(payload)));
|
||||
results.emplace_back(timestamp, 0, std::move(frame));
|
||||
return results;
|
||||
}
|
||||
|
||||
int AudioDecoder::Decode(const uint8_t* encoded,
|
||||
size_t encoded_len,
|
||||
int sample_rate_hz,
|
||||
size_t max_decoded_bytes,
|
||||
int16_t* decoded,
|
||||
SpeechType* speech_type) {
|
||||
TRACE_EVENT0("webrtc", "AudioDecoder::Decode");
|
||||
rtc::MsanCheckInitialized(rtc::MakeArrayView(encoded, encoded_len));
|
||||
int duration = PacketDuration(encoded, encoded_len);
|
||||
if (duration >= 0 &&
|
||||
duration * Channels() * sizeof(int16_t) > max_decoded_bytes) {
|
||||
return -1;
|
||||
}
|
||||
return DecodeInternal(encoded, encoded_len, sample_rate_hz, decoded,
|
||||
speech_type);
|
||||
}
|
||||
|
||||
int AudioDecoder::DecodeRedundant(const uint8_t* encoded,
|
||||
size_t encoded_len,
|
||||
int sample_rate_hz,
|
||||
size_t max_decoded_bytes,
|
||||
int16_t* decoded,
|
||||
SpeechType* speech_type) {
|
||||
TRACE_EVENT0("webrtc", "AudioDecoder::DecodeRedundant");
|
||||
rtc::MsanCheckInitialized(rtc::MakeArrayView(encoded, encoded_len));
|
||||
int duration = PacketDurationRedundant(encoded, encoded_len);
|
||||
if (duration >= 0 &&
|
||||
duration * Channels() * sizeof(int16_t) > max_decoded_bytes) {
|
||||
return -1;
|
||||
}
|
||||
return DecodeRedundantInternal(encoded, encoded_len, sample_rate_hz, decoded,
|
||||
speech_type);
|
||||
}
|
||||
|
||||
int AudioDecoder::DecodeRedundantInternal(const uint8_t* encoded,
|
||||
size_t encoded_len,
|
||||
int sample_rate_hz,
|
||||
int16_t* decoded,
|
||||
SpeechType* speech_type) {
|
||||
return DecodeInternal(encoded, encoded_len, sample_rate_hz, decoded,
|
||||
speech_type);
|
||||
}
|
||||
|
||||
bool AudioDecoder::HasDecodePlc() const {
|
||||
return false;
|
||||
}
|
||||
|
||||
size_t AudioDecoder::DecodePlc(size_t num_frames, int16_t* decoded) {
|
||||
return 0;
|
||||
}
|
||||
|
||||
// TODO(bugs.webrtc.org/9676): Remove default implementation.
|
||||
void AudioDecoder::GeneratePlc(size_t /*requested_samples_per_channel*/,
|
||||
rtc::BufferT<int16_t>* /*concealment_audio*/) {}
|
||||
|
||||
int AudioDecoder::ErrorCode() {
|
||||
return 0;
|
||||
}
|
||||
|
||||
int AudioDecoder::PacketDuration(const uint8_t* encoded,
|
||||
size_t encoded_len) const {
|
||||
return kNotImplemented;
|
||||
}
|
||||
|
||||
int AudioDecoder::PacketDurationRedundant(const uint8_t* encoded,
|
||||
size_t encoded_len) const {
|
||||
return kNotImplemented;
|
||||
}
|
||||
|
||||
bool AudioDecoder::PacketHasFec(const uint8_t* encoded,
|
||||
size_t encoded_len) const {
|
||||
return false;
|
||||
}
|
||||
|
||||
AudioDecoder::SpeechType AudioDecoder::ConvertSpeechType(int16_t type) {
|
||||
switch (type) {
|
||||
case 0: // TODO(hlundin): Both iSAC and Opus return 0 for speech.
|
||||
case 1:
|
||||
return kSpeech;
|
||||
case 2:
|
||||
return kComfortNoise;
|
||||
default:
|
||||
assert(false);
|
||||
return kSpeech;
|
||||
}
|
||||
}
|
||||
|
||||
} // namespace webrtc
|
193
webrtc/api/audio_codecs/audio_decoder.h
Normal file
193
webrtc/api/audio_codecs/audio_decoder.h
Normal file
@ -0,0 +1,193 @@
|
||||
/*
|
||||
* 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.
|
||||
*/
|
||||
|
||||
#ifndef API_AUDIO_CODECS_AUDIO_DECODER_H_
|
||||
#define API_AUDIO_CODECS_AUDIO_DECODER_H_
|
||||
|
||||
#include <stddef.h>
|
||||
#include <stdint.h>
|
||||
|
||||
#include <memory>
|
||||
#include <vector>
|
||||
|
||||
#include "absl/types/optional.h"
|
||||
#include "api/array_view.h"
|
||||
#include "rtc_base/buffer.h"
|
||||
#include "rtc_base/constructor_magic.h"
|
||||
|
||||
namespace webrtc {
|
||||
|
||||
class AudioDecoder {
|
||||
public:
|
||||
enum SpeechType {
|
||||
kSpeech = 1,
|
||||
kComfortNoise = 2,
|
||||
};
|
||||
|
||||
// Used by PacketDuration below. Save the value -1 for errors.
|
||||
enum { kNotImplemented = -2 };
|
||||
|
||||
AudioDecoder() = default;
|
||||
virtual ~AudioDecoder() = default;
|
||||
|
||||
class EncodedAudioFrame {
|
||||
public:
|
||||
struct DecodeResult {
|
||||
size_t num_decoded_samples;
|
||||
SpeechType speech_type;
|
||||
};
|
||||
|
||||
virtual ~EncodedAudioFrame() = default;
|
||||
|
||||
// Returns the duration in samples-per-channel of this audio frame.
|
||||
// If no duration can be ascertained, returns zero.
|
||||
virtual size_t Duration() const = 0;
|
||||
|
||||
// Returns true if this packet contains DTX.
|
||||
virtual bool IsDtxPacket() const;
|
||||
|
||||
// Decodes this frame of audio and writes the result in |decoded|.
|
||||
// |decoded| must be large enough to store as many samples as indicated by a
|
||||
// call to Duration() . On success, returns an absl::optional containing the
|
||||
// total number of samples across all channels, as well as whether the
|
||||
// decoder produced comfort noise or speech. On failure, returns an empty
|
||||
// absl::optional. Decode may be called at most once per frame object.
|
||||
virtual absl::optional<DecodeResult> Decode(
|
||||
rtc::ArrayView<int16_t> decoded) const = 0;
|
||||
};
|
||||
|
||||
struct ParseResult {
|
||||
ParseResult();
|
||||
ParseResult(uint32_t timestamp,
|
||||
int priority,
|
||||
std::unique_ptr<EncodedAudioFrame> frame);
|
||||
ParseResult(ParseResult&& b);
|
||||
~ParseResult();
|
||||
|
||||
ParseResult& operator=(ParseResult&& b);
|
||||
|
||||
// The timestamp of the frame is in samples per channel.
|
||||
uint32_t timestamp;
|
||||
// The relative priority of the frame compared to other frames of the same
|
||||
// payload and the same timeframe. A higher value means a lower priority.
|
||||
// The highest priority is zero - negative values are not allowed.
|
||||
int priority;
|
||||
std::unique_ptr<EncodedAudioFrame> frame;
|
||||
};
|
||||
|
||||
// Let the decoder parse this payload and prepare zero or more decodable
|
||||
// frames. Each frame must be between 10 ms and 120 ms long. The caller must
|
||||
// ensure that the AudioDecoder object outlives any frame objects returned by
|
||||
// this call. The decoder is free to swap or move the data from the |payload|
|
||||
// buffer. |timestamp| is the input timestamp, in samples, corresponding to
|
||||
// the start of the payload.
|
||||
virtual std::vector<ParseResult> ParsePayload(rtc::Buffer&& payload,
|
||||
uint32_t timestamp);
|
||||
|
||||
// TODO(bugs.webrtc.org/10098): The Decode and DecodeRedundant methods are
|
||||
// obsolete; callers should call ParsePayload instead. For now, subclasses
|
||||
// must still implement DecodeInternal.
|
||||
|
||||
// Decodes |encode_len| bytes from |encoded| and writes the result in
|
||||
// |decoded|. The maximum bytes allowed to be written into |decoded| is
|
||||
// |max_decoded_bytes|. Returns the total number of samples across all
|
||||
// channels. If the decoder produced comfort noise, |speech_type|
|
||||
// is set to kComfortNoise, otherwise it is kSpeech. The desired output
|
||||
// sample rate is provided in |sample_rate_hz|, which must be valid for the
|
||||
// codec at hand.
|
||||
int Decode(const uint8_t* encoded,
|
||||
size_t encoded_len,
|
||||
int sample_rate_hz,
|
||||
size_t max_decoded_bytes,
|
||||
int16_t* decoded,
|
||||
SpeechType* speech_type);
|
||||
|
||||
// Same as Decode(), but interfaces to the decoders redundant decode function.
|
||||
// The default implementation simply calls the regular Decode() method.
|
||||
int DecodeRedundant(const uint8_t* encoded,
|
||||
size_t encoded_len,
|
||||
int sample_rate_hz,
|
||||
size_t max_decoded_bytes,
|
||||
int16_t* decoded,
|
||||
SpeechType* speech_type);
|
||||
|
||||
// Indicates if the decoder implements the DecodePlc method.
|
||||
virtual bool HasDecodePlc() const;
|
||||
|
||||
// Calls the packet-loss concealment of the decoder to update the state after
|
||||
// one or several lost packets. The caller has to make sure that the
|
||||
// memory allocated in |decoded| should accommodate |num_frames| frames.
|
||||
virtual size_t DecodePlc(size_t num_frames, int16_t* decoded);
|
||||
|
||||
// Asks the decoder to generate packet-loss concealment and append it to the
|
||||
// end of |concealment_audio|. The concealment audio should be in
|
||||
// channel-interleaved format, with as many channels as the last decoded
|
||||
// packet produced. The implementation must produce at least
|
||||
// requested_samples_per_channel, or nothing at all. This is a signal to the
|
||||
// caller to conceal the loss with other means. If the implementation provides
|
||||
// concealment samples, it is also responsible for "stitching" it together
|
||||
// with the decoded audio on either side of the concealment.
|
||||
// Note: The default implementation of GeneratePlc will be deleted soon. All
|
||||
// implementations must provide their own, which can be a simple as a no-op.
|
||||
// TODO(bugs.webrtc.org/9676): Remove default impementation.
|
||||
virtual void GeneratePlc(size_t requested_samples_per_channel,
|
||||
rtc::BufferT<int16_t>* concealment_audio);
|
||||
|
||||
// Resets the decoder state (empty buffers etc.).
|
||||
virtual void Reset() = 0;
|
||||
|
||||
// Returns the last error code from the decoder.
|
||||
virtual int ErrorCode();
|
||||
|
||||
// Returns the duration in samples-per-channel of the payload in |encoded|
|
||||
// which is |encoded_len| bytes long. Returns kNotImplemented if no duration
|
||||
// estimate is available, or -1 in case of an error.
|
||||
virtual int PacketDuration(const uint8_t* encoded, size_t encoded_len) const;
|
||||
|
||||
// Returns the duration in samples-per-channel of the redandant payload in
|
||||
// |encoded| which is |encoded_len| bytes long. Returns kNotImplemented if no
|
||||
// duration estimate is available, or -1 in case of an error.
|
||||
virtual int PacketDurationRedundant(const uint8_t* encoded,
|
||||
size_t encoded_len) const;
|
||||
|
||||
// Detects whether a packet has forward error correction. The packet is
|
||||
// comprised of the samples in |encoded| which is |encoded_len| bytes long.
|
||||
// Returns true if the packet has FEC and false otherwise.
|
||||
virtual bool PacketHasFec(const uint8_t* encoded, size_t encoded_len) const;
|
||||
|
||||
// Returns the actual sample rate of the decoder's output. This value may not
|
||||
// change during the lifetime of the decoder.
|
||||
virtual int SampleRateHz() const = 0;
|
||||
|
||||
// The number of channels in the decoder's output. This value may not change
|
||||
// during the lifetime of the decoder.
|
||||
virtual size_t Channels() const = 0;
|
||||
|
||||
protected:
|
||||
static SpeechType ConvertSpeechType(int16_t type);
|
||||
|
||||
virtual int DecodeInternal(const uint8_t* encoded,
|
||||
size_t encoded_len,
|
||||
int sample_rate_hz,
|
||||
int16_t* decoded,
|
||||
SpeechType* speech_type) = 0;
|
||||
|
||||
virtual int DecodeRedundantInternal(const uint8_t* encoded,
|
||||
size_t encoded_len,
|
||||
int sample_rate_hz,
|
||||
int16_t* decoded,
|
||||
SpeechType* speech_type);
|
||||
|
||||
private:
|
||||
RTC_DISALLOW_COPY_AND_ASSIGN(AudioDecoder);
|
||||
};
|
||||
|
||||
} // namespace webrtc
|
||||
#endif // API_AUDIO_CODECS_AUDIO_DECODER_H_
|
113
webrtc/api/audio_codecs/audio_encoder.cc
Normal file
113
webrtc/api/audio_codecs/audio_encoder.cc
Normal file
@ -0,0 +1,113 @@
|
||||
/*
|
||||
* Copyright (c) 2014 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 "api/audio_codecs/audio_encoder.h"
|
||||
|
||||
#include "rtc_base/checks.h"
|
||||
#include "rtc_base/trace_event.h"
|
||||
|
||||
namespace webrtc {
|
||||
|
||||
ANAStats::ANAStats() = default;
|
||||
ANAStats::~ANAStats() = default;
|
||||
ANAStats::ANAStats(const ANAStats&) = default;
|
||||
|
||||
AudioEncoder::EncodedInfo::EncodedInfo() = default;
|
||||
AudioEncoder::EncodedInfo::EncodedInfo(const EncodedInfo&) = default;
|
||||
AudioEncoder::EncodedInfo::EncodedInfo(EncodedInfo&&) = default;
|
||||
AudioEncoder::EncodedInfo::~EncodedInfo() = default;
|
||||
AudioEncoder::EncodedInfo& AudioEncoder::EncodedInfo::operator=(
|
||||
const EncodedInfo&) = default;
|
||||
AudioEncoder::EncodedInfo& AudioEncoder::EncodedInfo::operator=(EncodedInfo&&) =
|
||||
default;
|
||||
|
||||
int AudioEncoder::RtpTimestampRateHz() const {
|
||||
return SampleRateHz();
|
||||
}
|
||||
|
||||
AudioEncoder::EncodedInfo AudioEncoder::Encode(
|
||||
uint32_t rtp_timestamp,
|
||||
rtc::ArrayView<const int16_t> audio,
|
||||
rtc::Buffer* encoded) {
|
||||
TRACE_EVENT0("webrtc", "AudioEncoder::Encode");
|
||||
RTC_CHECK_EQ(audio.size(),
|
||||
static_cast<size_t>(NumChannels() * SampleRateHz() / 100));
|
||||
|
||||
const size_t old_size = encoded->size();
|
||||
EncodedInfo info = EncodeImpl(rtp_timestamp, audio, encoded);
|
||||
RTC_CHECK_EQ(encoded->size() - old_size, info.encoded_bytes);
|
||||
return info;
|
||||
}
|
||||
|
||||
bool AudioEncoder::SetFec(bool enable) {
|
||||
return !enable;
|
||||
}
|
||||
|
||||
bool AudioEncoder::SetDtx(bool enable) {
|
||||
return !enable;
|
||||
}
|
||||
|
||||
bool AudioEncoder::GetDtx() const {
|
||||
return false;
|
||||
}
|
||||
|
||||
bool AudioEncoder::SetApplication(Application application) {
|
||||
return false;
|
||||
}
|
||||
|
||||
void AudioEncoder::SetMaxPlaybackRate(int frequency_hz) {}
|
||||
|
||||
void AudioEncoder::SetTargetBitrate(int target_bps) {}
|
||||
|
||||
rtc::ArrayView<std::unique_ptr<AudioEncoder>>
|
||||
AudioEncoder::ReclaimContainedEncoders() {
|
||||
return nullptr;
|
||||
}
|
||||
|
||||
bool AudioEncoder::EnableAudioNetworkAdaptor(const std::string& config_string,
|
||||
RtcEventLog* event_log) {
|
||||
return false;
|
||||
}
|
||||
|
||||
void AudioEncoder::DisableAudioNetworkAdaptor() {}
|
||||
|
||||
void AudioEncoder::OnReceivedUplinkPacketLossFraction(
|
||||
float uplink_packet_loss_fraction) {}
|
||||
|
||||
void AudioEncoder::OnReceivedUplinkRecoverablePacketLossFraction(
|
||||
float uplink_recoverable_packet_loss_fraction) {
|
||||
RTC_NOTREACHED();
|
||||
}
|
||||
|
||||
void AudioEncoder::OnReceivedTargetAudioBitrate(int target_audio_bitrate_bps) {
|
||||
OnReceivedUplinkBandwidth(target_audio_bitrate_bps, absl::nullopt);
|
||||
}
|
||||
|
||||
void AudioEncoder::OnReceivedUplinkBandwidth(
|
||||
int target_audio_bitrate_bps,
|
||||
absl::optional<int64_t> bwe_period_ms) {}
|
||||
|
||||
void AudioEncoder::OnReceivedUplinkAllocation(BitrateAllocationUpdate update) {
|
||||
OnReceivedUplinkBandwidth(update.target_bitrate.bps(),
|
||||
update.bwe_period.ms());
|
||||
}
|
||||
|
||||
void AudioEncoder::OnReceivedRtt(int rtt_ms) {}
|
||||
|
||||
void AudioEncoder::OnReceivedOverhead(size_t overhead_bytes_per_packet) {}
|
||||
|
||||
void AudioEncoder::SetReceiverFrameLengthRange(int min_frame_length_ms,
|
||||
int max_frame_length_ms) {}
|
||||
|
||||
ANAStats AudioEncoder::GetANAStats() const {
|
||||
return ANAStats();
|
||||
}
|
||||
|
||||
} // namespace webrtc
|
257
webrtc/api/audio_codecs/audio_encoder.h
Normal file
257
webrtc/api/audio_codecs/audio_encoder.h
Normal file
@ -0,0 +1,257 @@
|
||||
/*
|
||||
* Copyright (c) 2014 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 API_AUDIO_CODECS_AUDIO_ENCODER_H_
|
||||
#define API_AUDIO_CODECS_AUDIO_ENCODER_H_
|
||||
|
||||
#include <memory>
|
||||
#include <string>
|
||||
#include <utility>
|
||||
#include <vector>
|
||||
|
||||
#include "absl/types/optional.h"
|
||||
#include "api/array_view.h"
|
||||
#include "api/call/bitrate_allocation.h"
|
||||
#include "api/units/time_delta.h"
|
||||
#include "rtc_base/buffer.h"
|
||||
#include "rtc_base/deprecation.h"
|
||||
|
||||
namespace webrtc {
|
||||
|
||||
class RtcEventLog;
|
||||
|
||||
// Statistics related to Audio Network Adaptation.
|
||||
struct ANAStats {
|
||||
ANAStats();
|
||||
ANAStats(const ANAStats&);
|
||||
~ANAStats();
|
||||
// Number of actions taken by the ANA bitrate controller since the start of
|
||||
// the call. If this value is not set, it indicates that the bitrate
|
||||
// controller is disabled.
|
||||
absl::optional<uint32_t> bitrate_action_counter;
|
||||
// Number of actions taken by the ANA channel controller since the start of
|
||||
// the call. If this value is not set, it indicates that the channel
|
||||
// controller is disabled.
|
||||
absl::optional<uint32_t> channel_action_counter;
|
||||
// Number of actions taken by the ANA DTX controller since the start of the
|
||||
// call. If this value is not set, it indicates that the DTX controller is
|
||||
// disabled.
|
||||
absl::optional<uint32_t> dtx_action_counter;
|
||||
// Number of actions taken by the ANA FEC controller since the start of the
|
||||
// call. If this value is not set, it indicates that the FEC controller is
|
||||
// disabled.
|
||||
absl::optional<uint32_t> fec_action_counter;
|
||||
// Number of times the ANA frame length controller decided to increase the
|
||||
// frame length since the start of the call. If this value is not set, it
|
||||
// indicates that the frame length controller is disabled.
|
||||
absl::optional<uint32_t> frame_length_increase_counter;
|
||||
// Number of times the ANA frame length controller decided to decrease the
|
||||
// frame length since the start of the call. If this value is not set, it
|
||||
// indicates that the frame length controller is disabled.
|
||||
absl::optional<uint32_t> frame_length_decrease_counter;
|
||||
// The uplink packet loss fractions as set by the ANA FEC controller. If this
|
||||
// value is not set, it indicates that the ANA FEC controller is not active.
|
||||
absl::optional<float> uplink_packet_loss_fraction;
|
||||
};
|
||||
|
||||
// This is the interface class for encoders in AudioCoding module. Each codec
|
||||
// type must have an implementation of this class.
|
||||
class AudioEncoder {
|
||||
public:
|
||||
// Used for UMA logging of codec usage. The same codecs, with the
|
||||
// same values, must be listed in
|
||||
// src/tools/metrics/histograms/histograms.xml in chromium to log
|
||||
// correct values.
|
||||
enum class CodecType {
|
||||
kOther = 0, // Codec not specified, and/or not listed in this enum
|
||||
kOpus = 1,
|
||||
kIsac = 2,
|
||||
kPcmA = 3,
|
||||
kPcmU = 4,
|
||||
kG722 = 5,
|
||||
kIlbc = 6,
|
||||
|
||||
// Number of histogram bins in the UMA logging of codec types. The
|
||||
// total number of different codecs that are logged cannot exceed this
|
||||
// number.
|
||||
kMaxLoggedAudioCodecTypes
|
||||
};
|
||||
|
||||
struct EncodedInfoLeaf {
|
||||
size_t encoded_bytes = 0;
|
||||
uint32_t encoded_timestamp = 0;
|
||||
int payload_type = 0;
|
||||
bool send_even_if_empty = false;
|
||||
bool speech = true;
|
||||
CodecType encoder_type = CodecType::kOther;
|
||||
};
|
||||
|
||||
// This is the main struct for auxiliary encoding information. Each encoded
|
||||
// packet should be accompanied by one EncodedInfo struct, containing the
|
||||
// total number of |encoded_bytes|, the |encoded_timestamp| and the
|
||||
// |payload_type|. If the packet contains redundant encodings, the |redundant|
|
||||
// vector will be populated with EncodedInfoLeaf structs. Each struct in the
|
||||
// vector represents one encoding; the order of structs in the vector is the
|
||||
// same as the order in which the actual payloads are written to the byte
|
||||
// stream. When EncoderInfoLeaf structs are present in the vector, the main
|
||||
// struct's |encoded_bytes| will be the sum of all the |encoded_bytes| in the
|
||||
// vector.
|
||||
struct EncodedInfo : public EncodedInfoLeaf {
|
||||
EncodedInfo();
|
||||
EncodedInfo(const EncodedInfo&);
|
||||
EncodedInfo(EncodedInfo&&);
|
||||
~EncodedInfo();
|
||||
EncodedInfo& operator=(const EncodedInfo&);
|
||||
EncodedInfo& operator=(EncodedInfo&&);
|
||||
|
||||
std::vector<EncodedInfoLeaf> redundant;
|
||||
};
|
||||
|
||||
virtual ~AudioEncoder() = default;
|
||||
|
||||
// Returns the input sample rate in Hz and the number of input channels.
|
||||
// These are constants set at instantiation time.
|
||||
virtual int SampleRateHz() const = 0;
|
||||
virtual size_t NumChannels() const = 0;
|
||||
|
||||
// Returns the rate at which the RTP timestamps are updated. The default
|
||||
// implementation returns SampleRateHz().
|
||||
virtual int RtpTimestampRateHz() const;
|
||||
|
||||
// Returns the number of 10 ms frames the encoder will put in the next
|
||||
// packet. This value may only change when Encode() outputs a packet; i.e.,
|
||||
// the encoder may vary the number of 10 ms frames from packet to packet, but
|
||||
// it must decide the length of the next packet no later than when outputting
|
||||
// the preceding packet.
|
||||
virtual size_t Num10MsFramesInNextPacket() const = 0;
|
||||
|
||||
// Returns the maximum value that can be returned by
|
||||
// Num10MsFramesInNextPacket().
|
||||
virtual size_t Max10MsFramesInAPacket() const = 0;
|
||||
|
||||
// Returns the current target bitrate in bits/s. The value -1 means that the
|
||||
// codec adapts the target automatically, and a current target cannot be
|
||||
// provided.
|
||||
virtual int GetTargetBitrate() const = 0;
|
||||
|
||||
// Accepts one 10 ms block of input audio (i.e., SampleRateHz() / 100 *
|
||||
// NumChannels() samples). Multi-channel audio must be sample-interleaved.
|
||||
// The encoder appends zero or more bytes of output to |encoded| and returns
|
||||
// additional encoding information. Encode() checks some preconditions, calls
|
||||
// EncodeImpl() which does the actual work, and then checks some
|
||||
// postconditions.
|
||||
EncodedInfo Encode(uint32_t rtp_timestamp,
|
||||
rtc::ArrayView<const int16_t> audio,
|
||||
rtc::Buffer* encoded);
|
||||
|
||||
// Resets the encoder to its starting state, discarding any input that has
|
||||
// been fed to the encoder but not yet emitted in a packet.
|
||||
virtual void Reset() = 0;
|
||||
|
||||
// Enables or disables codec-internal FEC (forward error correction). Returns
|
||||
// true if the codec was able to comply. The default implementation returns
|
||||
// true when asked to disable FEC and false when asked to enable it (meaning
|
||||
// that FEC isn't supported).
|
||||
virtual bool SetFec(bool enable);
|
||||
|
||||
// Enables or disables codec-internal VAD/DTX. Returns true if the codec was
|
||||
// able to comply. The default implementation returns true when asked to
|
||||
// disable DTX and false when asked to enable it (meaning that DTX isn't
|
||||
// supported).
|
||||
virtual bool SetDtx(bool enable);
|
||||
|
||||
// Returns the status of codec-internal DTX. The default implementation always
|
||||
// returns false.
|
||||
virtual bool GetDtx() const;
|
||||
|
||||
// Sets the application mode. Returns true if the codec was able to comply.
|
||||
// The default implementation just returns false.
|
||||
enum class Application { kSpeech, kAudio };
|
||||
virtual bool SetApplication(Application application);
|
||||
|
||||
// Tells the encoder about the highest sample rate the decoder is expected to
|
||||
// use when decoding the bitstream. The encoder would typically use this
|
||||
// information to adjust the quality of the encoding. The default
|
||||
// implementation does nothing.
|
||||
virtual void SetMaxPlaybackRate(int frequency_hz);
|
||||
|
||||
// This is to be deprecated. Please use |OnReceivedTargetAudioBitrate|
|
||||
// instead.
|
||||
// Tells the encoder what average bitrate we'd like it to produce. The
|
||||
// encoder is free to adjust or disregard the given bitrate (the default
|
||||
// implementation does the latter).
|
||||
RTC_DEPRECATED virtual void SetTargetBitrate(int target_bps);
|
||||
|
||||
// Causes this encoder to let go of any other encoders it contains, and
|
||||
// returns a pointer to an array where they are stored (which is required to
|
||||
// live as long as this encoder). Unless the returned array is empty, you may
|
||||
// not call any methods on this encoder afterwards, except for the
|
||||
// destructor. The default implementation just returns an empty array.
|
||||
// NOTE: This method is subject to change. Do not call or override it.
|
||||
virtual rtc::ArrayView<std::unique_ptr<AudioEncoder>>
|
||||
ReclaimContainedEncoders();
|
||||
|
||||
// Enables audio network adaptor. Returns true if successful.
|
||||
virtual bool EnableAudioNetworkAdaptor(const std::string& config_string,
|
||||
RtcEventLog* event_log);
|
||||
|
||||
// Disables audio network adaptor.
|
||||
virtual void DisableAudioNetworkAdaptor();
|
||||
|
||||
// Provides uplink packet loss fraction to this encoder to allow it to adapt.
|
||||
// |uplink_packet_loss_fraction| is in the range [0.0, 1.0].
|
||||
virtual void OnReceivedUplinkPacketLossFraction(
|
||||
float uplink_packet_loss_fraction);
|
||||
|
||||
RTC_DEPRECATED virtual void OnReceivedUplinkRecoverablePacketLossFraction(
|
||||
float uplink_recoverable_packet_loss_fraction);
|
||||
|
||||
// Provides target audio bitrate to this encoder to allow it to adapt.
|
||||
virtual void OnReceivedTargetAudioBitrate(int target_bps);
|
||||
|
||||
// Provides target audio bitrate and corresponding probing interval of
|
||||
// the bandwidth estimator to this encoder to allow it to adapt.
|
||||
virtual void OnReceivedUplinkBandwidth(int target_audio_bitrate_bps,
|
||||
absl::optional<int64_t> bwe_period_ms);
|
||||
|
||||
// Provides target audio bitrate and corresponding probing interval of
|
||||
// the bandwidth estimator to this encoder to allow it to adapt.
|
||||
virtual void OnReceivedUplinkAllocation(BitrateAllocationUpdate update);
|
||||
|
||||
// Provides RTT to this encoder to allow it to adapt.
|
||||
virtual void OnReceivedRtt(int rtt_ms);
|
||||
|
||||
// Provides overhead to this encoder to adapt. The overhead is the number of
|
||||
// bytes that will be added to each packet the encoder generates.
|
||||
virtual void OnReceivedOverhead(size_t overhead_bytes_per_packet);
|
||||
|
||||
// To allow encoder to adapt its frame length, it must be provided the frame
|
||||
// length range that receivers can accept.
|
||||
virtual void SetReceiverFrameLengthRange(int min_frame_length_ms,
|
||||
int max_frame_length_ms);
|
||||
|
||||
// Get statistics related to audio network adaptation.
|
||||
virtual ANAStats GetANAStats() const;
|
||||
|
||||
// The range of frame lengths that are supported or nullopt if there's no sch
|
||||
// information. This is used to calculated the full bitrate range, including
|
||||
// overhead.
|
||||
virtual absl::optional<std::pair<TimeDelta, TimeDelta>> GetFrameLengthRange()
|
||||
const = 0;
|
||||
|
||||
protected:
|
||||
// Subclasses implement this to perform the actual encoding. Called by
|
||||
// Encode().
|
||||
virtual EncodedInfo EncodeImpl(uint32_t rtp_timestamp,
|
||||
rtc::ArrayView<const int16_t> audio,
|
||||
rtc::Buffer* encoded) = 0;
|
||||
};
|
||||
} // namespace webrtc
|
||||
#endif // API_AUDIO_CODECS_AUDIO_ENCODER_H_
|
Reference in New Issue
Block a user