C++ FFmpeg distorted sound when converting audio

Question

I'm using the FFmpeg library to generate MP4 files containing audio from various files, such as MP3, WAV, OGG, but I'm having some troubles (I'm also putting video in there, but for simplicity's sake I'm omitting that for this question, since I've got that working). My current code opens an audio file, decodes the content and converts it into the MP4 container and finally writes it into the destination file as interleaved frames.

It works perfectly for most MP3 files, but when inputting WAV or OGG, the audio in the resulting MP4 is slightly distorted and often plays at the wrong speed (up to many times faster or slower).

I've looked at countless of examples of using the converting functions (swr_convert), but I can't seem to get rid of the noise in the exported audio.

Here's how I add an audio stream to the MP4 (outContext is the AVFormatContext for the output file):

audioCodec = avcodec_find_encoder(outContext->oformat->audio_codec);
if (!audioCodec)
    die("Could not find audio encoder!");


// Start stream
audioStream = avformat_new_stream(outContext, audioCodec);
if (!audioStream)
    die("Could not allocate audio stream!");

audioCodecContext = audioStream->codec;
audioStream->id = 1;


// Setup
audioCodecContext->sample_fmt = AV_SAMPLE_FMT_S16;
audioCodecContext->bit_rate = 128000;
audioCodecContext->sample_rate = 44100;
audioCodecContext->channels = 2;
audioCodecContext->channel_layout = AV_CH_LAYOUT_STEREO;


// Open the codec
if (avcodec_open2(audioCodecContext, audioCodec, NULL) < 0)
    die("Could not open audio codec");

And to open a sound file from MP3/WAV/OGG (from the filename variable)...

// 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");

Finally, to decode+convert+encode...

// 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);

I have also tried setting appropriate pts values for outgoing frames, but that doesn't seem to affect the sound quality at all.

I'm also unsure how/if I should be allocating the converted data, can av_samples_alloc be used for this? What about avcodec_fill_audio_frame? Am I on the right track?

Any input is appreciated (I can also send the exported MP4s if necessary, if you want to hear the distortion).

Answer 1

if (avcodec_encode_audio2(audioCodecContext, &outPacket, audioFrameConverted, &frameFinished) < 0)
                die("Error encoding audio frame");

You seem to be assuming that the encoder will eat all submitted samples - it doesn't. It also doesn't cache them internally. It will eat a specific number of samples (AVCodecContext.frame_size), and the rest should be resubmitted in the next call to avcodec_encode_audio2().

[edit]

ok, so your edited code is better, but not there yet. You're still assuming the decoder will output at least frame_size samples for each call to avcodec_decode_audioN() (after resampling), which may not be the case. If that happens (and it does, for ogg), your avcodec_encode_audioN() call will encode an incomplete input buffer (because you say it's got frame_size samples, but it doesn't). Likewise, your code also doesn't deal with cases where the decoder outputs a number significantly bigger than frame_size (like 10*frame_size) expected by the encoder, in which case you'll get overruns - basically your 1:1 decode/encode mapping is the main source of your problem.

As a solution, consider the swrContext a FIFO, where you input all decoder samples, and loop over it until it's got less than frame_size samples left. I'll leave it up to you to learn how to deal with end-of-stream, because you'll need to flush cached samples out of the decoder (by calling avcodec_decode_audioN() with AVPacket where .data = NULL and .size = 0), flush the swrContext (by calling swr_context() until it returns 0) as well as flush the encoder (by feeding it NULL AVFrames until it returns AVPacket with .size = 0). Right now you'll probably get an output file where the end is slightly truncated. That shouldn't be hard to figure out.

This code works for me for m4a/ogg/mp3 to m4a/aac conversion:

#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;
}