AnotherFoxGuy/webrtc-audio-processing
1
0
Fork 0
Code Pull Requests Activity

Bump to WebRTC M120 release

Browse Source 
Some API deprecation -- ExperimentalAgc and ExperimentalNs are gone.
We're continuing to carry iSAC even though it's gone upstream, but maybe
we'll want to drop that soon.
This commit is contained in:
Arun Raghavan
2023-12-12 10:42:58 -05:00
parent 9a202fb8c2
commit c6abf6cd3f
479 changed files with 20900 additions and 11996 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
webrtc/api/audio_codecs/audio_decoder.cc
View File

@ -10,8 +10,6 @@
#include "api/audio_codecs/audio_decoder.h"
#include <assert.h>
#include <memory>
#include <utility>
@ -162,9 +160,10 @@ AudioDecoder::SpeechType AudioDecoder::ConvertSpeechType(int16_t type) {
case 2:
return kComfortNoise;
default:
assert(false);
RTC_DCHECK_NOTREACHED();
return kSpeech;
}
}
constexpr int AudioDecoder::kMaxNumberOfChannels;
} // namespace webrtc

42
webrtc/api/audio_codecs/audio_decoder.h
View File

@ -20,7 +20,6 @@
#include "absl/types/optional.h"
#include "api/array_view.h"
#include "rtc_base/buffer.h"
#include "rtc_base/constructor_magic.h"
namespace webrtc {
@ -37,6 +36,9 @@ class AudioDecoder {
AudioDecoder() = default;
virtual ~AudioDecoder() = default;
AudioDecoder(const AudioDecoder&) = delete;
AudioDecoder& operator=(const AudioDecoder&) = delete;
class EncodedAudioFrame {
public:
struct DecodeResult {
@ -53,8 +55,8 @@ class AudioDecoder {
// 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
// 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
@ -85,8 +87,8 @@ class AudioDecoder {
// 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
// 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);
@ -95,12 +97,12 @@ class AudioDecoder {
// 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|
// 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
// 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,
@ -123,11 +125,11 @@ class AudioDecoder {
// 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.
// 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
// 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
@ -136,7 +138,7 @@ class AudioDecoder {
// 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.
// TODO(bugs.webrtc.org/9676): Remove default implementation.
virtual void GeneratePlc(size_t requested_samples_per_channel,
rtc::BufferT<int16_t>* concealment_audio);
@ -146,19 +148,19 @@ class AudioDecoder {
// 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
// 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
// `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.
// 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;
@ -170,6 +172,9 @@ class AudioDecoder {
// during the lifetime of the decoder.
virtual size_t Channels() const = 0;
// The maximum number of audio channels supported by WebRTC decoders.
static constexpr int kMaxNumberOfChannels = 24;
protected:
static SpeechType ConvertSpeechType(int16_t type);
@ -184,9 +189,6 @@ class AudioDecoder {
int sample_rate_hz,
int16_t* decoded,
SpeechType* speech_type);
private:
RTC_DISALLOW_COPY_AND_ASSIGN(AudioDecoder);
};
} // namespace webrtc

3
webrtc/api/audio_codecs/audio_encoder.cc
View File

@ -83,7 +83,7 @@ void AudioEncoder::OnReceivedUplinkPacketLossFraction(
void AudioEncoder::OnReceivedUplinkRecoverablePacketLossFraction(
float uplink_recoverable_packet_loss_fraction) {
RTC_NOTREACHED();
RTC_DCHECK_NOTREACHED();
}
void AudioEncoder::OnReceivedTargetAudioBitrate(int target_audio_bitrate_bps) {
@ -110,4 +110,5 @@ ANAStats AudioEncoder::GetANAStats() const {
return ANAStats();
}
constexpr int AudioEncoder::kMaxNumberOfChannels;
} // namespace webrtc

23
webrtc/api/audio_codecs/audio_encoder.h
View File

@ -16,12 +16,12 @@
#include <utility>
#include <vector>
#include "absl/base/attributes.h"
#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 {
@ -95,13 +95,13 @@ class AudioEncoder {
// 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|
// 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
// struct's `encoded_bytes` will be the sum of all the `encoded_bytes` in the
// vector.
struct EncodedInfo : public EncodedInfoLeaf {
EncodedInfo();
@ -143,7 +143,7 @@ class AudioEncoder {
// 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
// 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.
@ -182,12 +182,11 @@ class AudioEncoder {
// 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);
ABSL_DEPRECATED("Use OnReceivedTargetAudioBitrate instead")
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
@ -206,11 +205,12 @@ class AudioEncoder {
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].
// `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(
ABSL_DEPRECATED("")
virtual void OnReceivedUplinkRecoverablePacketLossFraction(
float uplink_recoverable_packet_loss_fraction);
// Provides target audio bitrate to this encoder to allow it to adapt.
@ -246,6 +246,9 @@ class AudioEncoder {
virtual absl::optional<std::pair<TimeDelta, TimeDelta>> GetFrameLengthRange()
const = 0;
// The maximum number of audio channels supported by WebRTC encoders.
static constexpr int kMaxNumberOfChannels = 24;
protected:
// Subclasses implement this to perform the actual encoding. Called by
// Encode().