使用FFMPEG库将PCM编码为AAC

准备

ffmpeg 版本4.4

准备一段48000Hz 2 channel f32le 格式的PCM原始数据

这里我们直接使用ffmpeg命令行提取

ffmpeg -i beautlWorld.mp4 -ar 48000 -ac 2 -f f32le 48000_2_f32le.pcm

-ar 采样率

-ac 音频通道

-f f32le 音频样本数据存储格式（f32 ---- float 32位 le ----小端）

使用下面命令进行播放：

ffplay -ar 48000 -ac 2 -f f32le 48000_2_f32le.pcm

编码流程

基本上面的流程已经很清晰了，按照步骤编写代码即可，下面贴出源码

#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>extern "C" {#include <libavcodec/avcodec.h>#include <libavutil/channel_layout.h>#include <libavutil/common.h>#include <libavutil/frame.h>#include <libavutil/samplefmt.h>#include <libavutil/opt.h>
}/* 检测该编码器是否支持该采样格式 */
static int check_sample_fmt(const AVCodec* codec, enum AVSampleFormat sample_fmt)
{const enum  AVSampleFormat* p = codec->sample_fmts;while (*p != AV_SAMPLE_FMT_NONE) { // 通过AV_SAMPLE_FMT_NONE作为结束符if (*p == sample_fmt)return 1;p++;}return 0;
}/* 检测该编码器是否支持该采样率 */
static int check_sample_rate(const AVCodec* codec, const int sample_rate)
{const int* p = codec->supported_samplerates;while (*p != 0) {// 0作为退出条件，比如libfdk-aacenc.c的aac_sample_ratesprintf("%s support %dhz\n", codec->name, *p);if (*p == sample_rate)return 1;p++;}return 0;
}/* 检测该编码器是否支持该采样率, 该函数只是作参考 */
static int check_channel_layout(const AVCodec* codec, const uint64_t channel_layout)
{// 不是每个codec都给出支持的channel_layoutconst uint64_t* p = codec->channel_layouts;if (!p) {printf("the codec %s no set channel_layouts\n", codec->name);return 1;}while (*p != 0) { // 0作为退出条件，比如libfdk-aacenc.c的aac_channel_layoutprintf("%s support channel_layout %d\n", codec->name, *p);if (*p == channel_layout)return 1;p++;}return 0;
}static int check_codec(AVCodec* codec, AVCodecContext* codec_ctx)
{if (!check_sample_fmt(codec, codec_ctx->sample_fmt)) {fprintf(stderr, "Encoder does not support sample format %s",av_get_sample_fmt_name(codec_ctx->sample_fmt));return 0;}if (!check_sample_rate(codec, codec_ctx->sample_rate)) {fprintf(stderr, "Encoder does not support sample rate %d", codec_ctx->sample_rate);return 0;}if (!check_channel_layout(codec, codec_ctx->channel_layout)) {fprintf(stderr, "Encoder does not support channel layout %lu", codec_ctx->channel_layout);return 0;}printf("\n\nAudio encode config\n");printf("bit_rate:%ldkbps\n", codec_ctx->bit_rate / 1024);printf("sample_rate:%d\n", codec_ctx->sample_rate);printf("sample_fmt:%s\n", av_get_sample_fmt_name(codec_ctx->sample_fmt));printf("channels:%d\n", codec_ctx->channels);// frame_size是在avcodec_open2后进行关联printf("1 frame_size:%d\n", codec_ctx->frame_size);return 1;
}//写入ADTS头
static void get_adts_header(AVCodecContext* ctx, uint8_t* adts_header, int aac_length)
{uint8_t freq_idx = 0;    //0: 96000 Hz  3: 48000 Hz 4: 44100 Hzswitch (ctx->sample_rate) {case 96000: freq_idx = 0; break;case 88200: freq_idx = 1; break;case 64000: freq_idx = 2; break;case 48000: freq_idx = 3; break;case 44100: freq_idx = 4; break;case 32000: freq_idx = 5; break;case 24000: freq_idx = 6; break;case 22050: freq_idx = 7; break;case 16000: freq_idx = 8; break;case 12000: freq_idx = 9; break;case 11025: freq_idx = 10; break;case 8000: freq_idx = 11; break;case 7350: freq_idx = 12; break;default: freq_idx = 4; break;}uint8_t chanCfg = ctx->channels;uint32_t frame_length = aac_length + 7;adts_header[0] = 0xFF;adts_header[1] = 0xF1;adts_header[2] = ((ctx->profile) << 6) + (freq_idx << 2) + (chanCfg >> 2);adts_header[3] = (((chanCfg & 3) << 6) + (frame_length >> 11));adts_header[4] = ((frame_length & 0x7FF) >> 3);adts_header[5] = (((frame_length & 7) << 5) + 0x1F);adts_header[6] = 0xFC;
}//编码
static int encode(AVCodecContext* ctx, AVFrame* frame, AVPacket* pkt, FILE* output)
{int ret;/* send the frame for encoding */ret = avcodec_send_frame(ctx, frame);if (ret < 0) {fprintf(stderr, "Error sending the frame to the encoder\n");return -1;}/* read all the available output packets (in general there may be any number of them */// 编码和解码都是一样的，都是send 1次，然后receive多次, 直到AVERROR(EAGAIN)或者AVERROR_EOFwhile (ret >= 0) {ret = avcodec_receive_packet(ctx, pkt);if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF) {return 0;}else if (ret < 0) {fprintf(stderr, "Error encoding audio frame\n");return -1;}uint8_t aac_header[7];get_adts_header(ctx, aac_header, pkt->size);size_t len = 0;len = fwrite(aac_header, 1, 7, output);if (len != 7) {fprintf(stderr, "fwrite aac_header failed\n");return -1;}len = fwrite(pkt->data, 1, pkt->size, output);if (len != pkt->size) {fprintf(stderr, "fwrite aac data failed\n");return -1;}av_packet_unref(pkt);}return -1;
}/** 这里只支持2通道的转换
*/
void f32le_convert_to_fltp(float* f32le, float* fltp, int nb_samples) {float* fltp_l = fltp;   // 左通道float* fltp_r = fltp + nb_samples;   // 右通道for (int i = 0; i < nb_samples; i++) {fltp_l[i] = f32le[i * 2];     // 0 1   - 2 3fltp_r[i] = f32le[i * 2 + 1];   // 可以尝试注释左声道或者右声道听听声音}
}int main(int argc, char** argv)
{const char* in_pcm_file = "D:/测试工程/sound/48000_2_f32le.pcm";      // 输入PCM文件const char* out_aac_file = "D:/测试工程/sound/8k_32kbps_decode_2channel.aac";     // 输出的AAC文件AVCodecID codec_id = AV_CODEC_ID_AAC;// 1.查找编码器AVCodec* codec = (AVCodec *)avcodec_find_encoder(codec_id); // 按ID查找则缺省的aac encode为aacenc.cif (!codec) {fprintf(stderr, "Codec not found\n");exit(1);}// 2.分配内存AVCodecContext* codec_ctx = avcodec_alloc_context3(codec);if (!codec_ctx) {fprintf(stderr, "Could not allocate audio codec context\n");exit(1);}codec_ctx->codec_id = codec_id;codec_ctx->codec_type = AVMEDIA_TYPE_AUDIO;codec_ctx->bit_rate = 32 * 1024;codec_ctx->channel_layout = AV_CH_LAYOUT_STEREO;codec_ctx->sample_rate = 48000;codec_ctx->channels = av_get_channel_layout_nb_channels(codec_ctx->channel_layout);codec_ctx->profile = FF_PROFILE_AAC_LOW;    //codec_ctx->sample_fmt = AV_SAMPLE_FMT_FLTP;// 3.检测支持采样格式支持情况if (!check_codec(codec, codec_ctx)) {exit(1);}// 4.将编码器上下文和编码器进行关联if (avcodec_open2(codec_ctx, codec, NULL) < 0) {fprintf(stderr, "Could not open codec\n");exit(1);}printf("2 frame_size:%d\n\n", codec_ctx->frame_size); // 决定每次到底送多少个采样点// 5.打开输入和输出文件FILE* infile = fopen(in_pcm_file, "rb");if (!infile) {fprintf(stderr, "Could not open %s\n", in_pcm_file);exit(1);}FILE* outfile = fopen(out_aac_file, "wb");if (!outfile) {fprintf(stderr, "Could not open %s\n", out_aac_file);exit(1);}// 6.分配packetAVPacket* pkt = av_packet_alloc();if (!pkt) {fprintf(stderr, "could not allocate the packet\n");exit(1);}// 7.分配frameAVFrame* frame = av_frame_alloc();if (!frame) {fprintf(stderr, "Could not allocate audio frame\n");exit(1);}/* 每次送多少数据给编码器由：*  (1)frame_size(每帧单个通道的采样点数);*  (2)sample_fmt(采样点格式);*  (3)channel_layout(通道布局情况);* 3要素决定*/frame->nb_samples = codec_ctx->frame_size;frame->format = codec_ctx->sample_fmt;frame->channel_layout = codec_ctx->channel_layout;frame->channels = av_get_channel_layout_nb_channels(frame->channel_layout);printf("frame nb_samples:%d\n", frame->nb_samples);printf("frame sample_fmt:%d\n", frame->format);printf("frame channel_layout:%lu\n", frame->channel_layout);printf("frame channels_num:%lu\n\n", frame->channels);// 8.为frame分配bufferint ret = av_frame_get_buffer(frame, 0);if (ret < 0) {fprintf(stderr, "Could not allocate audio data buffers\n");exit(1);}// 9.循环读取数据// 计算出每一帧的数据 单个采样点的字节 * 通道数目 * 每帧采样点数量int frame_bytes = av_get_bytes_per_sample((AVSampleFormat)frame->format) \* frame->channels \* frame->nb_samples;//int frame_bytes = 1 * frame->channels * frame->nb_samples;printf("frame_bytes %d\n", frame_bytes);uint8_t* pcm_buf = (uint8_t*)malloc(frame_bytes);if (!pcm_buf) {printf("pcm_buf malloc failed\n");return 1;}uint8_t* pcm_temp_buf = (uint8_t*)malloc(frame_bytes);if (!pcm_temp_buf) {printf("pcm_temp_buf malloc failed\n");return 1;}//每个通道占的字节数int data_size = av_get_bytes_per_sample((AVSampleFormat)frame->format);int64_t pts = 0;printf("start enode\n");while (!feof(infile)){// 10.确保该frame可写, 如果编码器内部保持了内存参考计数，则需要重新拷贝一个备份 目的是新写入的数据和编码器保存的数据不能产生冲突ret = av_frame_make_writable(frame);if (ret != 0)printf("av_frame_make_writable failed, ret = %d\n", ret);//读取packed模式数据用planar模式存储 aac只支持fltp模式for (int i = 0; i < frame->nb_samples; i++)for (int j = 0; j < frame->channels; j++){fread(frame->data[j] + data_size * i, 1, data_size, infile);}//声道控制//memset(frame->data[1], 0, frame->nb_samples * data_size);pts += frame->nb_samples;frame->pts = pts;       // 使用采样率作为pts的单位，具体换算成秒 pts*1/采样率ret = encode(codec_ctx, frame, pkt, outfile);if (ret < 0) {printf("encode failed\n");break;}}// 13.冲刷编码器encode(codec_ctx, NULL, pkt, outfile);// 14.关闭文件fclose(infile);fclose(outfile);// 15.释放内存if (pcm_buf) {free(pcm_buf);}if (pcm_temp_buf) {free(pcm_temp_buf);}av_frame_free(&frame);av_packet_free(&pkt);avcodec_free_context(&codec_ctx);printf("main finish, please enter Enter and exit\n");getchar();return 0;
}

小记

在编码测试过程中，有几点心得记录下：

1.关于采样率，采样率的大小表示的PCM原始数据格式每秒传递给播放器的样本数，比如48000Hz,那么播放器1s就会收到48000 * 2个样本数据（双通道）。如果采样率设置为原来的两倍，则播放速度也就是原来的两倍,相应播放时间也会减半,同时在比特率不变的情况下，文件大小也会缩小一半左右。

2.关于比特率，比特率影响的是播放时编码后的数据每秒传递给解码器的数据量，比如比特率128kb/s,那么每秒就会给解码器发送128000 / 8 = 1600个字节的数据，注意这1600个数据是压缩数据，分为很多个未解码的包（avpacket），那么这1600个数据最终会被解码成48000 * 2个字节的数据(双通道)。那么比特率的设置有什么用呢？经过测试，可以知道设置比特率会再次影响压缩率，按照我的理解，比特率的设置就是告诉编码器要丢弃多少数据。

我们可以设置几个很大的比特率，进行编码,结果生成的文件大小一样。同时我们播放时发现，过大的比特率编码器并未采用，说明当比特率大于某一个值时，编码器不会丢弃数据，此时将压缩后的数据直接生成文件，而后比特率值有编码器计算后设置。