单输入filter流程
解码出AVFrame -> abuffer-> 其他过滤器(volume)...->aformat->abuffersink->过滤后的AVFrame
这里看到有三个通用的过滤器，abuffer,aformat,abuffersink。
abuffer用于接收输入frame,形成待处理的数据缓存，abuffersink用于传出输出Frame，aformat过滤器约束最终的输出格式（采样率，声道数，存储位数等），这三个不可缺少。
而中间的其他过滤器可以串联多个filter，如volume，atempo
初始化过滤器
这里我们先要知道三个重要的结构体
AVFilterGraph (管理所有的filter)
AVFilterContext (filter上下文)
AVFilter(具体过滤器)
具体步骤
1.注册所有filter
avfilter_register_all();
2.创建AVFilterGraph,分配内存
AVFilterGraph *graph = avfilter_graph_alloc();
3.获取过滤器,初始化上下文
AVFilter *abuffer = avfilter_get_by_name("abuffer");
AVFilterContext *abuffer_ctx = avfilter_graph_alloc_filter(graph, abuffer, "src");
4.设置参数
avfilter_init_str(abuffer_ctx,"sample_rate=48000:sample_fmt=s16p:channel_layout=stereo");
avfilter_link(abuffer_ctx, 0, volume_ctx, 0);
avfilter_link(volume_ctx, 0, aformat_ctx, 0);
avfilter_link(aformat_ctx, 0, sink_ctx, 0);
7.配置AVFilterGraph
avfilter_graph_config(graph, NULL);
具体代码如下
int init_volume_filter(AVFilterGraph **pGraph, AVFilterContext **src, AVFilterContext **out,
char *value) {
//初始化AVFilterGraph
AVFilterGraph *graph = avfilter_graph_alloc();
//获取abuffer用于接收输入端
AVFilter *abuffer = avfilter_get_by_name("abuffer");
AVFilterContext *abuffer_ctx = avfilter_graph_alloc_filter(graph, abuffer, "src");
//设置参数，这里需要匹配原始音频采样率、数据格式（位数）
if (avfilter_init_str(abuffer_ctx, "sample_rate=48000:sample_fmt=s16p:channel_layout=stereo") <
0) {
LOGE("error init abuffer filter");
return -1;
}
//初始化volume filter
AVFilter *volume = avfilter_get_by_name("volume");
AVFilterContext *volume_ctx = avfilter_graph_alloc_filter(graph, volume, "volume");
//这里采用av_dict_set设置参数
AVDictionary *args = NULL;
av_dict_set(&args, "volume", value, 0);//这里传入外部参数，可以动态修改
if (avfilter_init_dict(volume_ctx, &args) < 0) {
LOGE("error init volume filter");
return -1;
}
AVFilter *aformat = avfilter_get_by_name("aformat");
AVFilterContext *aformat_ctx = avfilter_graph_alloc_filter(graph, aformat, "aformat");
if (avfilter_init_str(aformat_ctx,
"sample_rates=48000:sample_fmts=s16p:channel_layouts=stereo") < 0) {
LOGE("error init aformat filter");
return -1;
}
//初始化sink用于输出
AVFilter *sink = avfilter_get_by_name("abuffersink");
AVFilterContext *sink_ctx = avfilter_graph_alloc_filter(graph, sink, "sink");
if (avfilter_init_str(sink_ctx, NULL) < 0) {//无需参数
LOGE("error init sink filter");
return -1;
}
//链接各个filter上下文
if (avfilter_link(abuffer_ctx, 0, volume_ctx, 0) != 0) {
LOGE("error link to volume filter");
return -1;
}
if (avfilter_link(volume_ctx, 0, aformat_ctx, 0) != 0) {
LOGE("error link to aformat filter");
return -1;
}
if (avfilter_link(aformat_ctx, 0, sink_ctx, 0) != 0) {
LOGE("error link to sink filter");
return -1;
}
if (avfilter_graph_config(graph, NULL) < 0) {
LOGI("error config filter graph");
return -1;
}
*pGraph = graph;
*src = abuffer_ctx;
*out = sink_ctx;
LOGI("init filter success...");
return 0;
}
这里通过传参数value，来动态修改音量
使用过滤器
使用方法很简单，将解码后的AVFrame通过av_buffersrc_add_frame(abuffer_ctx,frame)加入到输入过滤器上下文abuffer_ctx中，通过av_buffersink_get_frame(sink_ctx,frame)获取处理完成的frame。
代码如下
AVFilterGraph *graph;
AVFilterContext *in_ctx;
AVFilterContext *out_ctx;
//注册所有过滤器
avfilter_register_all();
init_volume_filter(&graph, &in_ctx, &out_ctx, "0.5");
//初始化
while (av_read_frame(fmt_ctx, packet) == 0) {//将音频数据读入packet
if (packet->stream_index == audio_stream_index) {//取音频索引packet
... 解码音频
if (got_frame > 0) {
LOGI("decode frame:%d", index++);
if (index == 1000) {//模拟动态修改音量
init_volume_filter(&graph, &in_ctx, &out_ctx, "0.01");
}
if (index == 2000) {
init_volume_filter(&graph, &in_ctx, &out_ctx, "1.0");
}
if (index == 3000) {
init_volume_filter(&graph, &in_ctx, &out_ctx, "0.01");
}
if (index == 4000) {
init_volume_filter(&graph, &in_ctx, &out_ctx, "1.0");
}
if (av_buffersrc_add_frame(in_ctx, frame) < 0) {//将frame放入输入filter上下文
LOGE("error add frame");
break;
}
while (av_buffersink_get_frame(out_ctx, frame) >= 0) {//从输出filter上下文中获取frame
fwrite(frame->data[0], 1, static_cast<size_t>(frame->linesize[0]),
out_file); //想将单个声道pcm数据写入文件
}
}
}
}
最终解码出来pcm和原始mp3波形对比
修改音量前 修改音量后
可以明显看出音量已经发生变化。
在播放音频时，可以听见有一些噪声，需要swr_convert来重新采样，取出完整的pcm数据。
//初始化SwrContext
SwrContext *swr_ctx = swr_alloc();
enum AVSampleFormat in_sample = codec_ctx->sample_fmt;
enum AVSampleFormat out_sample = AV_SAMPLE_FMT_S16;
int inSampleRate = codec_ctx->sample_rate;
int outSampleRate = inSampleRate;
uint64_t in_ch_layout = codec_ctx->channel_layout;
uint64_t outChannelLayout = AV_CH_LAYOUT_STEREO;
swr_alloc_set_opts(swr_ctx, outChannelLayout, out_sample, outSampleRate, in_ch_layout, in_sample,
inSampleRate, 0, NULL);
swr_init(swr_ctx);
int out_ch_layout_nb = av_get_channel_layout_nb_channels(out_ch_layout);//声道个数
uint8_t *out_buffer = (uint8_t *) av_malloc(MAX_AUDIO_SIZE);//重采样数据
写入pcm数据之前，用swr_convert重新采样一下
while (av_buffersink_get_frame(out_ctx, frame) >= 0) {//从输出filter上下文中获取frame
// fwrite(frame->data[0], 1, static_cast<size_t>(frame->linesize[0]),
// out_file); //想将单个声道pcm数据写入文件
swr_convert(swr_ctx, &out_buffer, MAX_AUDIO_SIZE,
(const uint8_t **) frame->data, frame->nb_samples);
int out_size = av_samples_get_buffer_size(NULL,out_ch_layout_nb,frame->nb_samples,out_sample_fmt,0);
fwrite(out_buffer,1,out_size,out_file);
}
这次我们写入的是完整2个声道的数据，而且也没有噪声了。
使用变速过滤器atempo给音频变速
将volumefilter改成atempo,注意参数设置名为tempo（没有a，不知道为什么）
//初始化volume filter
AVFilter *volume = avfilter_get_by_name("atempo");
AVFilterContext *volume_ctx = avfilter_graph_alloc_filter(graph, volume, "atempo");
//这里采用av_dict_set设置参数
AVDictionary *args = NULL;
av_dict_set(&args, "tempo", value, 0);//调节音量为原先的一半
if (avfilter_init_dict(volume_ctx, &args) < 0) {
LOGE("error init volume filter");
return -1;
}
解码时模拟动态修改速度改成如下
if (index == 1000) {//模拟动态修改音量
init_volume_filter(&graph, &in_ctx, &out_ctx, "1.0");
}
if (index == 2000) {
init_volume_filter(&graph, &in_ctx, &out_ctx, "0.8");
}
if (index == 3000) {
init_volume_filter(&graph, &in_ctx, &out_ctx, "1.5");
}
if (index == 4000) {
init_volume_filter(&graph, &in_ctx, &out_ctx, "2.0");
}