音频解码就是将mp3 aac等格式这些文件解析为pcm格式的过程。
和视频解码流程一样，只是有些函数不一样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
//封装格式
//解码
extern "C" {
};
static int audio_decode_example(const char *input, const char *output) {
AVCodec *pCodec;
AVCodecContext *pCodecContext;
AVFormatContext *pFormatContext;
struct SwrContext *au_convert_ctx;
uint8_t *out_buffer;
//1. 注册
av_register_all();
//2.打开解码器 <-- 拿到解码器 <-- 拿到id <-- 拿到stream和拿到AVCodecContext <-- 拿到AVFormatContext
//2.1 拿到AVFormatContext
pFormatContext = avformat_alloc_context();
//2.1.1 打开文件
if (avformat_open_input(&pFormatContext, input, NULL, NULL) != 0) {
LOGE("打开文件失败!");
return -1;
}
//2.2 拿到AVCodecContext
//2.2.1 拿到流信息
if (avformat_find_stream_info(pFormatContext, NULL) < 0) {
LOGE("AVFormatContext获取流信息失败!");
return -1;
}
//打印信息
// av_dump_format(pFormatContext, 0, input, false);
//2.2.2 通过streams找到audio的索引下标 也就获取到了stream
int audioStream = -1;
int i = 0;
for (; i < pFormatContext->nb_streams; i++)
if (pFormatContext->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO) {
audioStream = i;
break;
}
if (audioStream == -1) {
LOGE("AVMEDIA_TYPE_AUDIO索引没找到!");
return -1;
}
//2.2.3 获取到AVCodecContext
pCodecContext = pFormatContext->streams[audioStream]->codec;
//2.2.4 通过AVCodecContext拿到id ，拿到解码器
pCodec = avcodec_find_decoder(pCodecContext->codec_id);
if (pCodec == NULL) {
LOGE("AVCodec获取失败!");
return -1;
}
//2.2.5 打开解码器
if (avcodec_open2(pCodecContext, pCodec, NULL) < 0) {
LOGE("打开解码器失败!");
return -1;
}
//3. 解码 将解码数据封装在AVFrame <-- 拿到编码的数据AVPacket <-- 读取数据源 <-- 解码文件参数设置
//3.1 AVPacket初始化
AVPacket *packet = (AVPacket *) av_malloc(sizeof(AVPacket));
av_init_packet(packet);
//3.2 解码文件参数设置
uint64_t out_channel_layout = AV_CH_LAYOUT_STEREO;
//nb_samples: AAC-1024 MP3-1152
//音频帧中每个声道的采样数
int out_nb_samples = pCodecContext->frame_size;
//音频采样格式 量化精度
AVSampleFormat out_sample_fmt = AV_SAMPLE_FMT_S16;
//采样率
int out_sample_rate = 44100;
//声道
int out_channels = av_get_channel_layout_nb_channels(out_channel_layout);
//获取到 缓冲大小
int out_buffer_size = av_samples_get_buffer_size(NULL, out_channels, out_nb_samples,
out_sample_fmt, 1);
out_buffer = (uint8_t *) av_malloc(MAX_AUDIO_FRAME_SIZE * 2);
//3.3 初始化AVFrame
AVFrame *pFrame = av_frame_alloc();
//3.4 获取到编码文件的参数信息
//声道
int64_t in_channel_layout = av_get_default_channel_layout(pCodecContext->channels);
//3.5 参数设置
au_convert_ctx = swr_alloc();
au_convert_ctx = swr_alloc_set_opts(au_convert_ctx, out_channel_layout, out_sample_fmt,
out_sample_rate,
in_channel_layout, pCodecContext->sample_fmt,
pCodecContext->sample_rate, 0, NULL);
swr_init(au_convert_ctx);
//4. 读取编码数据到AVPacket 然后将数据解码存储到AVFrame 转换存储数据
//4.1 读取编码数据到AVPacket
int got_picture;
int index = 0;
FILE *outputFile = fopen(output, "wb");
while (av_read_frame(pFormatContext, packet) >= 0) {
if (packet->stream_index == audioStream) {
//4.2 将数据解码存储到AVFrame
if (avcodec_decode_audio4(pCodecContext, pFrame, &got_picture, packet) < 0) {
LOGE("解码失败");
return -1;
}
if (got_picture > 0) {
//4.3 转换音频数据
swr_convert(au_convert_ctx, &out_buffer, MAX_AUDIO_FRAME_SIZE,
(const uint8_t **) pFrame->data, pFrame->nb_samples);
LOGE("index:%5d\t pts:%lld\t packet size:%d\n",index,packet->pts,packet->size);
//4.4 存储数据
fwrite(out_buffer, 1, static_cast<size_t>(out_buffer_size), outputFile);
index++;
}
}
//5. 释放相关资源
av_packet_unref(packet);
}
swr_free(&au_convert_ctx);
fclose(outputFile);
av_free(out_buffer);
// Close the codec
avcodec_close(pCodecContext);
// Close the video file
avformat_close_input(&pFormatContext);
return 0;
}
extern "C"
JNIEXPORT jint JNICALL
Java_zzw_com_ffmpegdemo_VideoUtils_audio_1decode(JNIEnv *env, jclass type, jstring input_,
jstring output_) {
const char *input = env->GetStringUTFChars(input_, 0);
const char *output = env->GetStringUTFChars(output_, 0);
int flog = audio_decode_example(input, output);
env->ReleaseStringUTFChars(input_, input);
env->ReleaseStringUTFChars(output_, output);
return flog;
}
参考地址:
https://blog.csdn.net/leixiaohua1020/article/details/46890259