Audio C++；FFmpeg在转换音频时失真的声音
我正在使用FFmpeg库生成MP4文件，其中包含来自各种文件的音频，例如MP3、WAV、OGG，但我遇到了一些问题（我也将视频放在其中，但为了简单起见，我在这个问题中省略了它，因为我已经实现了这一点）。我的当前代码打开一个音频文件，解码内容并将其转换为MP4容器，最后将其作为交错帧写入目标文件 它适用于大多数MP3文件，但当输入WAV或OGG时，生成的MP4中的音频会稍微失真，并且经常以错误的速度播放（快或慢很多倍） 我看过无数使用转换函数（swr_convert）的例子，但我似乎无法消除导出音频中的噪声 以下是我如何将音频流添加到MP4（outContext是输出文件的AVFormatContext）：Audio C++；FFmpeg在转换音频时失真的声音,audio,ffmpeg,decode,mp4,Audio,Ffmpeg,Decode,Mp4,我正在使用FFmpeg库生成MP4文件，其中包含来自各种文件的音频，例如MP3、WAV、OGG，但我遇到了一些问题（我也将视频放在其中，但为了简单起见，我在这个问题中省略了它，因为我已经实现了这一点）。我的当前代码打开一个音频文件，解码内容并将其转换为MP4容器，最后将其作为交错帧写入目标文件 它适用于大多数MP3文件，但当输入WAV或OGG时，生成的MP4中的音频会稍微失真，并且经常以错误的速度播放（快或慢很多倍） 我看过无数使用转换函数（swr_convert）的例子，但我似乎无法消除导出音
audioCodec=avcodec\u find\u编码器（outContext->oformat->audio\u codec）；
if（！音频编解码器）
死（“找不到音频编码器！”）；
//起始流
audioStream=avformat\u new\u stream（outContext，audioCodec）；
如果（！音频流）
die（“无法分配音频流！”）；
AudioCodeContext=audioStream->codec；
音频流->id=1；
//设置
AudioCodeContext->sample_fmt=AV_sample_fmt_S16；
AudioCodeContext->比特率=128000；
AudioCodeContext->采样率=44100；
AudioCodeContext->Channel=2；
AudioCodeContext->channel_layout=AV_Chu layout_STEREO；
//打开编解码器
if（avcodec_open2（audioCodecContext，audioCodec，NULL）<0）
die（“无法打开音频编解码器”）；
//创建上下文
formatContext=avformat_alloc_context（）；
if（avformat\u open\u输入（&formatContext，filename，NULL，NULL）编解码器；
//查找解码器
codec=avcodec\u find\u解码器（codecContext->codec\u id）；
如果（编解码器==NULL）
死（“找不到编解码器！”）；
//开放式编解码器
if（avcodec_open2（codecContext，codec，0）通道，0）；
av_opt_set_int（swrContext，“in_channel_layout”，编解码器上下文->channel_layout，0）；
av_opt_set_int（swrContext，“in_sample_rate”，codecContext->sample_rate，0）；
av_opt_set_sample_fmt（swrContext，“in_sample_fmt”，codecContext->sample_fmt，0）；
av_opt_set_int（swrContext，“输出频道计数”，AudioCodeContext->channel，0）；
av_opt_set_int（swrContext，“输出频道布局”，AudioCodeContext->频道布局，0）；
av_opt_set_int（swrContext，“out_sample_rate”，AudioCodeContext->sample_rate，0）；
av_opt_set_sample_fmt（swrContext，“out_sample_fmt”，AudioCodeContext->sample_fmt，0）；
if（swr_init（swrContext））
die（“未能初始化swr上下文”）；
// Allocate and init re-usable frames
audioFrameDecoded = av_frame_alloc();
if (!audioFrameDecoded)
die("Could not allocate audio frame");
audioFrameDecoded->format = fileCodecContext->sample_fmt;
audioFrameDecoded->channel_layout = fileCodecContext->channel_layout;
audioFrameDecoded->channels = fileCodecContext->channels;
audioFrameDecoded->sample_rate = fileCodecContext->sample_rate;
audioFrameConverted = av_frame_alloc();
if (!audioFrameConverted)
die("Could not allocate audio frame");
audioFrameConverted->nb_samples = audioCodecContext->frame_size;
audioFrameConverted->format = audioCodecContext->sample_fmt;
audioFrameConverted->channel_layout = audioCodecContext->channel_layout;
audioFrameConverted->channels = audioCodecContext->channels;
audioFrameConverted->sample_rate = audioCodecContext->sample_rate;
AVPacket inPacket;
av_init_packet(&inPacket);
inPacket.data = NULL;
inPacket.size = 0;
int frameFinished = 0;
while (av_read_frame(formatContext, &inPacket) >= 0) {
if (inPacket.stream_index == streamId) {
int len = avcodec_decode_audio4(fileCodecContext, audioFrameDecoded, &frameFinished, &inPacket);
if (frameFinished) {
// Convert
uint8_t *convertedData=NULL;
if (av_samples_alloc(&convertedData,
NULL,
audioCodecContext->channels,
audioFrameConverted->nb_samples,
audioCodecContext->sample_fmt, 0) < 0)
die("Could not allocate samples");
int outSamples = swr_convert(swrContext,
&convertedData,
audioFrameConverted->nb_samples,
(const uint8_t **)audioFrameDecoded->data,
audioFrameDecoded->nb_samples);
if (outSamples < 0)
die("Could not convert");
size_t buffer_size = av_samples_get_buffer_size(NULL,
audioCodecContext->channels,
audioFrameConverted->nb_samples,
audioCodecContext->sample_fmt,
0);
if (buffer_size < 0)
die("Invalid buffer size");
if (avcodec_fill_audio_frame(audioFrameConverted,
audioCodecContext->channels,
audioCodecContext->sample_fmt,
convertedData,
buffer_size,
0) < 0)
die("Could not fill frame");
AVPacket outPacket;
av_init_packet(&outPacket);
outPacket.data = NULL;
outPacket.size = 0;
if (avcodec_encode_audio2(audioCodecContext, &outPacket, audioFrameConverted, &frameFinished) < 0)
die("Error encoding audio frame");
if (frameFinished) {
outPacket.stream_index = audioStream->index;
if (av_interleaved_write_frame(outContext, &outPacket) != 0)
die("Error while writing audio frame");
av_free_packet(&outPacket);
}
}
}
}
av_frame_free(&audioFrameConverted);
av_frame_free(&audioFrameDecoded);
av_free_packet(&inPacket);
//分配并初始化可重用帧
audioFrameDecoded=av_frame_alloc（）；
如果（！audioFrameDecoded）
die（“无法分配音频帧”）；
audioFrameDecoded->format=FileCodeContext->sample\u fmt；
audioFrameDecoded->channel\u layout=FileCodeContext->channel\u layout；
audioFrameDecoded->channels=FileCodeContext->channels；
audioFrameDecoded->sample\u rate=FileCodeContext->sample\u rate；
audioFrameConverted=av_frame_alloc（）；
如果（！audioFrameConverted）
die（“无法分配音频帧”）；
audioFrameConverted->nb_样本=AudioCodeContext->frame_大小；
audioFrameConverted->format=AudioCodeContext->sample\u fmt；
audioFrameConverted->channel\u layout=AudioCodeContext->channel\u layout；
audioFrameConverted->Channel=AudioCodeContext->Channel；
audioFrameConverted->采样率=AudioCodeContext->采样率；
AVPacket-inPacket；
av_初始_数据包（&inPacket）；
inPacket.data=NULL；
inPacket.size=0；
int frameFinished=0；
while（av_read_frame（formatContext，&inPacket）>=0）{
if（inPacket.stream_index==streamId）{
int len=avcodec\u decode\u audio4（fileCodecContext、audioFrameDecoded、frameFinished和inPacket）；
如果（框架完成）{
//皈依
uint8_t*convertedData=NULL；
如果（av）样本分配和转换数据，
无效的
AudioCodeContext->频道，
音频帧转换->nb_样本，
AudioCodeContext->sample_fmt，0）<0）
die（“无法分配样本”）；
int outSamples=swr\U convert（swrContext，
&转换数据，
音频帧转换->nb_样本，
（const uint8_t**）音频帧解码->数据，
音频帧解码->nb_样本）；
if（样本数<0）
死亡（“无法转换”）；
size\u t buffer\u size=av\u samples\u get\u buffer\u size（空，
AudioCodeContext->频道，
音频帧转换->nb_样本，
AudioCodeContext->sample_fmt，
0);
如果（缓冲区大小<0）
模具（“无效缓冲区大小”）；
如果（avcodec_fill_audio_frame）（音频帧转换，
AudioCodeContext->频道，
AudioCodeContext->sample_fmt，
转换数据，
缓冲区大小，
0) < 0)
D
// Create contex
formatContext = avformat_alloc_context();
if (avformat_open_input(&formatContext, filename, NULL, NULL)<0)
die("Could not open file");
// Find info
if (avformat_find_stream_info(formatContext, 0)<0)
die("Could not find file info");
av_dump_format(formatContext, 0, filename, false);
// Find audio stream
streamId = av_find_best_stream(formatContext, AVMEDIA_TYPE_AUDIO, -1, -1, NULL, 0);
if (streamId < 0)
die("Could not find Audio Stream");
codecContext = formatContext->streams[streamId]->codec;
// Find decoder
codec = avcodec_find_decoder(codecContext->codec_id);
if (codec == NULL)
die("cannot find codec!");
// Open codec
if (avcodec_open2(codecContext, codec, 0)<0)
die("Codec cannot be found");
// Set up resample context
swrContext = swr_alloc();
if (!swrContext)
die("Failed to alloc swr context");
av_opt_set_int(swrContext, "in_channel_count", codecContext->channels, 0);
av_opt_set_int(swrContext, "in_channel_layout", codecContext->channel_layout, 0);
av_opt_set_int(swrContext, "in_sample_rate", codecContext->sample_rate, 0);
av_opt_set_sample_fmt(swrContext, "in_sample_fmt", codecContext->sample_fmt, 0);
av_opt_set_int(swrContext, "out_channel_count", audioCodecContext->channels, 0);
av_opt_set_int(swrContext, "out_channel_layout", audioCodecContext->channel_layout, 0);
av_opt_set_int(swrContext, "out_sample_rate", audioCodecContext->sample_rate, 0);
av_opt_set_sample_fmt(swrContext, "out_sample_fmt", audioCodecContext->sample_fmt, 0);
if (swr_init(swrContext))
die("Failed to init swr context");
// Allocate and init re-usable frames
audioFrameDecoded = av_frame_alloc();
if (!audioFrameDecoded)
die("Could not allocate audio frame");
audioFrameDecoded->format = fileCodecContext->sample_fmt;
audioFrameDecoded->channel_layout = fileCodecContext->channel_layout;
audioFrameDecoded->channels = fileCodecContext->channels;
audioFrameDecoded->sample_rate = fileCodecContext->sample_rate;
audioFrameConverted = av_frame_alloc();
if (!audioFrameConverted)
die("Could not allocate audio frame");
audioFrameConverted->nb_samples = audioCodecContext->frame_size;
audioFrameConverted->format = audioCodecContext->sample_fmt;
audioFrameConverted->channel_layout = audioCodecContext->channel_layout;
audioFrameConverted->channels = audioCodecContext->channels;
audioFrameConverted->sample_rate = audioCodecContext->sample_rate;
AVPacket inPacket;
av_init_packet(&inPacket);
inPacket.data = NULL;
inPacket.size = 0;
int frameFinished = 0;
while (av_read_frame(formatContext, &inPacket) >= 0) {
if (inPacket.stream_index == streamId) {
int len = avcodec_decode_audio4(fileCodecContext, audioFrameDecoded, &frameFinished, &inPacket);
if (frameFinished) {
// Convert
uint8_t *convertedData=NULL;
if (av_samples_alloc(&convertedData,
NULL,
audioCodecContext->channels,
audioFrameConverted->nb_samples,
audioCodecContext->sample_fmt, 0) < 0)
die("Could not allocate samples");
int outSamples = swr_convert(swrContext,
&convertedData,
audioFrameConverted->nb_samples,
(const uint8_t **)audioFrameDecoded->data,
audioFrameDecoded->nb_samples);
if (outSamples < 0)
die("Could not convert");
size_t buffer_size = av_samples_get_buffer_size(NULL,
audioCodecContext->channels,
audioFrameConverted->nb_samples,
audioCodecContext->sample_fmt,
0);
if (buffer_size < 0)
die("Invalid buffer size");
if (avcodec_fill_audio_frame(audioFrameConverted,
audioCodecContext->channels,
audioCodecContext->sample_fmt,
convertedData,
buffer_size,
0) < 0)
die("Could not fill frame");
AVPacket outPacket;
av_init_packet(&outPacket);
outPacket.data = NULL;
outPacket.size = 0;
if (avcodec_encode_audio2(audioCodecContext, &outPacket, audioFrameConverted, &frameFinished) < 0)
die("Error encoding audio frame");
if (frameFinished) {
outPacket.stream_index = audioStream->index;
if (av_interleaved_write_frame(outContext, &outPacket) != 0)
die("Error while writing audio frame");
av_free_packet(&outPacket);
}
}
}
}
av_frame_free(&audioFrameConverted);
av_frame_free(&audioFrameDecoded);
av_free_packet(&inPacket);
if (avcodec_encode_audio2(audioCodecContext, &outPacket, audioFrameConverted, &frameFinished) < 0)
die("Error encoding audio frame");
#include "libswresample/swresample.h"
#include "libavcodec/avcodec.h"
#include "libavformat/avformat.h"
#include "libavutil/opt.h"
#include <stdio.h>
#include <stdlib.h>
static void die(char *str) {
fprintf(stderr, "%s\n", str);
exit(1);
}
static AVStream *add_audio_stream(AVFormatContext *oc, enum AVCodecID codec_id)
{
AVCodecContext *c;
AVCodec *encoder = avcodec_find_encoder(codec_id);
AVStream *st = avformat_new_stream(oc, encoder);
if (!st) die("av_new_stream");
c = st->codec;
c->codec_id = codec_id;
c->codec_type = AVMEDIA_TYPE_AUDIO;
/* put sample parameters */
c->bit_rate = 64000;
c->sample_rate = 44100;
c->channels = 2;
c->sample_fmt = encoder->sample_fmts[0];
c->channel_layout = AV_CH_LAYOUT_STEREO;
// some formats want stream headers to be separate
if(oc->oformat->flags & AVFMT_GLOBALHEADER)
c->flags |= CODEC_FLAG_GLOBAL_HEADER;
return st;
}
static void open_audio(AVFormatContext *oc, AVStream *st)
{
AVCodecContext *c = st->codec;
AVCodec *codec;
/* find the audio encoder */
codec = avcodec_find_encoder(c->codec_id);
if (!codec) die("avcodec_find_encoder");
/* open it */
AVDictionary *dict = NULL;
av_dict_set(&dict, "strict", "+experimental", 0);
int res = avcodec_open2(c, codec, &dict);
if (res < 0) die("avcodec_open");
}
int main(int argc, char *argv[]) {
av_register_all();
if (argc != 3) {
fprintf(stderr, "%s <in> <out>\n", argv[0]);
exit(1);
}
// Allocate and init re-usable frames
AVCodecContext *fileCodecContext, *audioCodecContext;
AVFormatContext *formatContext, *outContext;
AVStream *audioStream;
SwrContext *swrContext;
int streamId;
// input file
const char *file = argv[1];
int res = avformat_open_input(&formatContext, file, NULL, NULL);
if (res != 0) die("avformat_open_input");
res = avformat_find_stream_info(formatContext, NULL);
if (res < 0) die("avformat_find_stream_info");
AVCodec *codec;
res = av_find_best_stream(formatContext, AVMEDIA_TYPE_AUDIO, -1, -1, &codec, 0);
if (res < 0) die("av_find_best_stream");
streamId = res;
fileCodecContext = avcodec_alloc_context3(codec);
avcodec_copy_context(fileCodecContext, formatContext->streams[streamId]->codec);
res = avcodec_open2(fileCodecContext, codec, NULL);
if (res < 0) die("avcodec_open2");
// output file
const char *outfile = argv[2];
AVOutputFormat *fmt = fmt = av_guess_format(NULL, outfile, NULL);
if (!fmt) die("av_guess_format");
outContext = avformat_alloc_context();
outContext->oformat = fmt;
audioStream = add_audio_stream(outContext, fmt->audio_codec);
open_audio(outContext, audioStream);
res = avio_open2(&outContext->pb, outfile, AVIO_FLAG_WRITE, NULL, NULL);
if (res < 0) die("url_fopen");
avformat_write_header(outContext, NULL);
audioCodecContext = audioStream->codec;
// resampling
swrContext = swr_alloc();
av_opt_set_channel_layout(swrContext, "in_channel_layout", fileCodecContext->channel_layout, 0);
av_opt_set_channel_layout(swrContext, "out_channel_layout", audioCodecContext->channel_layout, 0);
av_opt_set_int(swrContext, "in_sample_rate", fileCodecContext->sample_rate, 0);
av_opt_set_int(swrContext, "out_sample_rate", audioCodecContext->sample_rate, 0);
av_opt_set_sample_fmt(swrContext, "in_sample_fmt", fileCodecContext->sample_fmt, 0);
av_opt_set_sample_fmt(swrContext, "out_sample_fmt", audioCodecContext->sample_fmt, 0);
res = swr_init(swrContext);
if (res < 0) die("swr_init");
AVFrame *audioFrameDecoded = av_frame_alloc();
if (!audioFrameDecoded)
die("Could not allocate audio frame");
audioFrameDecoded->format = fileCodecContext->sample_fmt;
audioFrameDecoded->channel_layout = fileCodecContext->channel_layout;
audioFrameDecoded->channels = fileCodecContext->channels;
audioFrameDecoded->sample_rate = fileCodecContext->sample_rate;
AVFrame *audioFrameConverted = av_frame_alloc();
if (!audioFrameConverted) die("Could not allocate audio frame");
audioFrameConverted->nb_samples = audioCodecContext->frame_size;
audioFrameConverted->format = audioCodecContext->sample_fmt;
audioFrameConverted->channel_layout = audioCodecContext->channel_layout;
audioFrameConverted->channels = audioCodecContext->channels;
audioFrameConverted->sample_rate = audioCodecContext->sample_rate;
AVPacket inPacket;
av_init_packet(&inPacket);
inPacket.data = NULL;
inPacket.size = 0;
int frameFinished = 0;
while (av_read_frame(formatContext, &inPacket) >= 0) {
if (inPacket.stream_index == streamId) {
int len = avcodec_decode_audio4(fileCodecContext, audioFrameDecoded, &frameFinished, &inPacket);
if (frameFinished) {
// Convert
uint8_t *convertedData=NULL;
if (av_samples_alloc(&convertedData,
NULL,
audioCodecContext->channels,
audioFrameConverted->nb_samples,
audioCodecContext->sample_fmt, 0) < 0)
die("Could not allocate samples");
int outSamples = swr_convert(swrContext, NULL, 0,
//&convertedData,
//audioFrameConverted->nb_samples,
(const uint8_t **)audioFrameDecoded->data,
audioFrameDecoded->nb_samples);
if (outSamples < 0) die("Could not convert");
for (;;) {
outSamples = swr_get_out_samples(swrContext, 0);
if (outSamples < audioCodecContext->frame_size * audioCodecContext->channels) break; // see comments, thanks to @dajuric for fixing this
outSamples = swr_convert(swrContext,
&convertedData,
audioFrameConverted->nb_samples, NULL, 0);
size_t buffer_size = av_samples_get_buffer_size(NULL,
audioCodecContext->channels,
audioFrameConverted->nb_samples,
audioCodecContext->sample_fmt,
0);
if (buffer_size < 0) die("Invalid buffer size");
if (avcodec_fill_audio_frame(audioFrameConverted,
audioCodecContext->channels,
audioCodecContext->sample_fmt,
convertedData,
buffer_size,
0) < 0)
die("Could not fill frame");
AVPacket outPacket;
av_init_packet(&outPacket);
outPacket.data = NULL;
outPacket.size = 0;
if (avcodec_encode_audio2(audioCodecContext, &outPacket, audioFrameConverted, &frameFinished) < 0)
die("Error encoding audio frame");
if (frameFinished) {
outPacket.stream_index = audioStream->index;
if (av_interleaved_write_frame(outContext, &outPacket) != 0)
die("Error while writing audio frame");
av_free_packet(&outPacket);
}
}
}
}
}
swr_close(swrContext);
swr_free(&swrContext);
av_frame_free(&audioFrameConverted);
av_frame_free(&audioFrameDecoded);
av_free_packet(&inPacket);
av_write_trailer(outContext);
avio_close(outContext->pb);
avcodec_close(fileCodecContext);
avcodec_free_context(&fileCodecContext);
avformat_close_input(&formatContext);
return 0;
}
c->sample_rate = fileCodecContext->sample_rate;
if (audioFrameConverted->nb_samples <= 0) audioFrameConverted->nb_samples = 32; //wav files have a 0
if ((outSamples < audioCodecContext->frame_size * audioCodecContext->channels) || audioCodecContext->frame_size==0 && (outSamples < audioFrameConverted->nb_samples * audioCodecContext->channels)) break; // see comments, thanks to @dajuric for fixing this
out_audioStream->time_base = in_audioStream->time_base; // entered before avio_open.
outPacket.dts = audioFrameDecoded->pkt_dts;//rest after avcodec_encode_audio2
outPacket.pts = audioFrameDecoded->pkt_pts;
av_packet_rescale_ts(&outPacket, in_audioStream->time_base, out_audioStream->time_base);