1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
|
/*
* 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.
*/
#include "modules/audio_coding/codecs/opus/audio_decoder_opus.h"
#include <memory>
#include <utility>
#include "absl/types/optional.h"
#include "api/array_view.h"
#include "rtc_base/checks.h"
namespace webrtc {
namespace {
class OpusFrame : public AudioDecoder::EncodedAudioFrame {
public:
OpusFrame(AudioDecoderOpusImpl* decoder,
rtc::Buffer&& payload,
bool is_primary_payload)
: decoder_(decoder),
payload_(std::move(payload)),
is_primary_payload_(is_primary_payload) {}
size_t Duration() const override {
int ret;
if (is_primary_payload_) {
ret = decoder_->PacketDuration(payload_.data(), payload_.size());
} else {
ret = decoder_->PacketDurationRedundant(payload_.data(), payload_.size());
}
return (ret < 0) ? 0 : static_cast<size_t>(ret);
}
bool IsDtxPacket() const override { return payload_.size() <= 2; }
absl::optional<DecodeResult> Decode(
rtc::ArrayView<int16_t> decoded) const override {
AudioDecoder::SpeechType speech_type = AudioDecoder::kSpeech;
int ret;
if (is_primary_payload_) {
ret = decoder_->Decode(
payload_.data(), payload_.size(), decoder_->SampleRateHz(),
decoded.size() * sizeof(int16_t), decoded.data(), &speech_type);
} else {
ret = decoder_->DecodeRedundant(
payload_.data(), payload_.size(), decoder_->SampleRateHz(),
decoded.size() * sizeof(int16_t), decoded.data(), &speech_type);
}
if (ret < 0)
return absl::nullopt;
return DecodeResult{static_cast<size_t>(ret), speech_type};
}
private:
AudioDecoderOpusImpl* const decoder_;
const rtc::Buffer payload_;
const bool is_primary_payload_;
};
} // namespace
AudioDecoderOpusImpl::AudioDecoderOpusImpl(size_t num_channels)
: channels_(num_channels) {
RTC_DCHECK(num_channels == 1 || num_channels == 2 || num_channels == 4 ||
num_channels == 6 || num_channels == 8);
const int error = WebRtcOpus_DecoderCreate(&dec_state_, channels_);
RTC_DCHECK(error == 0);
WebRtcOpus_DecoderInit(dec_state_);
}
AudioDecoderOpusImpl::~AudioDecoderOpusImpl() {
WebRtcOpus_DecoderFree(dec_state_);
}
std::vector<AudioDecoder::ParseResult> AudioDecoderOpusImpl::ParsePayload(
rtc::Buffer&& payload,
uint32_t timestamp) {
std::vector<ParseResult> results;
if (PacketHasFec(payload.data(), payload.size())) {
const int duration =
PacketDurationRedundant(payload.data(), payload.size());
RTC_DCHECK_GE(duration, 0);
rtc::Buffer payload_copy(payload.data(), payload.size());
std::unique_ptr<EncodedAudioFrame> fec_frame(
new OpusFrame(this, std::move(payload_copy), false));
results.emplace_back(timestamp - duration, 1, std::move(fec_frame));
}
std::unique_ptr<EncodedAudioFrame> frame(
new OpusFrame(this, std::move(payload), true));
results.emplace_back(timestamp, 0, std::move(frame));
return results;
}
int AudioDecoderOpusImpl::DecodeInternal(const uint8_t* encoded,
size_t encoded_len,
int sample_rate_hz,
int16_t* decoded,
SpeechType* speech_type) {
RTC_DCHECK_EQ(sample_rate_hz, 48000);
int16_t temp_type = 1; // Default is speech.
int ret =
WebRtcOpus_Decode(dec_state_, encoded, encoded_len, decoded, &temp_type);
if (ret > 0)
ret *= static_cast<int>(channels_); // Return total number of samples.
*speech_type = ConvertSpeechType(temp_type);
return ret;
}
int AudioDecoderOpusImpl::DecodeRedundantInternal(const uint8_t* encoded,
size_t encoded_len,
int sample_rate_hz,
int16_t* decoded,
SpeechType* speech_type) {
if (!PacketHasFec(encoded, encoded_len)) {
// This packet is a RED packet.
return DecodeInternal(encoded, encoded_len, sample_rate_hz, decoded,
speech_type);
}
RTC_DCHECK_EQ(sample_rate_hz, 48000);
int16_t temp_type = 1; // Default is speech.
int ret = WebRtcOpus_DecodeFec(dec_state_, encoded, encoded_len, decoded,
&temp_type);
if (ret > 0)
ret *= static_cast<int>(channels_); // Return total number of samples.
*speech_type = ConvertSpeechType(temp_type);
return ret;
}
void AudioDecoderOpusImpl::Reset() {
WebRtcOpus_DecoderInit(dec_state_);
}
int AudioDecoderOpusImpl::PacketDuration(const uint8_t* encoded,
size_t encoded_len) const {
return WebRtcOpus_DurationEst(dec_state_, encoded, encoded_len);
}
int AudioDecoderOpusImpl::PacketDurationRedundant(const uint8_t* encoded,
size_t encoded_len) const {
if (!PacketHasFec(encoded, encoded_len)) {
// This packet is a RED packet.
return PacketDuration(encoded, encoded_len);
}
return WebRtcOpus_FecDurationEst(encoded, encoded_len);
}
bool AudioDecoderOpusImpl::PacketHasFec(const uint8_t* encoded,
size_t encoded_len) const {
int fec;
fec = WebRtcOpus_PacketHasFec(encoded, encoded_len);
return (fec == 1);
}
int AudioDecoderOpusImpl::SampleRateHz() const {
return 48000;
}
size_t AudioDecoderOpusImpl::Channels() const {
return channels_;
}
} // namespace webrtc
|
