我正在开发一个音频处理系统，有时需要将相同的音频重新采样两次。第一次从FFmpeg进行音频重采样工作正常，第二次导致音频失真。我通过修改FFmpeg提供的resampling_audio示例来重现此问题。如何使用swr_convert两次转换相同的音频？
下面，我附上了resampling_audio示例的修改版本。为了重现此问题，请按照下列步骤操作：
./configure make -j4 examples（这将需要一段时间）doc/examples/resampling_audio以产生预期的输出doc/examples/resampling_audio.c替换为我下面随附的版本make -j4 examples doc/examples/resampling_audio（带有新的args）以输出两个新文件（每次转换一个）。我在其中运行的环境是Ubuntu 16.04；然后，我将输出文件复制到Windows PC上，以Audacity打开它们。
这是我修改后的resampling_audio.c文件。我创建了一些新变量，并复制了执行转换的代码块。第一次转换应保持不变，第二次转换将从第一次转换中获取数据，然后尝试再次进行转换。
/*
* Copyright (c) 2012 Stefano Sabatini
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
/**
* @example resampling_audio.c
* libswresample API use example.
*/
#include <libavutil/opt.h>
#include <libavutil/channel_layout.h>
#include <libavutil/samplefmt.h>
#include <libswresample/swresample.h>
static int get_format_from_sample_fmt(const char **fmt,
enum AVSampleFormat sample_fmt)
{
int i;
struct sample_fmt_entry {
enum AVSampleFormat sample_fmt; const char *fmt_be, *fmt_le;
} sample_fmt_entries[] = {
{ AV_SAMPLE_FMT_U8, "u8", "u8" },
{ AV_SAMPLE_FMT_S16, "s16be", "s16le" },
{ AV_SAMPLE_FMT_S32, "s32be", "s32le" },
{ AV_SAMPLE_FMT_FLT, "f32be", "f32le" },
{ AV_SAMPLE_FMT_DBL, "f64be", "f64le" },
};
*fmt = NULL;
for (i = 0; i < FF_ARRAY_ELEMS(sample_fmt_entries); i++) {
struct sample_fmt_entry *entry = &sample_fmt_entries[i];
if (sample_fmt == entry->sample_fmt) {
*fmt = AV_NE(entry->fmt_be, entry->fmt_le);
return 0;
}
}
fprintf(stderr,
"Sample format %s not supported as output format\n",
av_get_sample_fmt_name(sample_fmt));
return AVERROR(EINVAL);
}
/**
* Fill dst buffer with nb_samples, generated starting from t.
*/
static void fill_samples(double *dst, int nb_samples, int nb_channels, int sample_rate, double *t)
{
int i, j;
double tincr = 1.0 / sample_rate, *dstp = dst;
const double c = 2 * M_PI * 440.0;
/* generate sin tone with 440Hz frequency and duplicated channels */
for (i = 0; i < nb_samples; i++) {
*dstp = sin(c * *t);
for (j = 1; j < nb_channels; j++)
dstp[j] = dstp[0];
dstp += nb_channels;
*t += tincr;
}
}
int main(int argc, char **argv)
{
int64_t src_ch_layout = AV_CH_LAYOUT_STEREO, dst_ch_layout = AV_CH_LAYOUT_SURROUND;
int src_rate = 48000, dst_rate = 44100;
uint8_t **src_data = NULL, **dst_data = NULL, **dst_data2 = NULL;
int src_nb_channels = 0, dst_nb_channels = 0;
int src_linesize, dst_linesize;
int src_nb_samples = 1024, dst_nb_samples, max_dst_nb_samples, dst_nb_samples2, max_dst_nb_samples2;
enum AVSampleFormat src_sample_fmt = AV_SAMPLE_FMT_DBL, dst_sample_fmt = AV_SAMPLE_FMT_S16;
const char *dst_filename = NULL, *dst_filename2 = NULL;
FILE *dst_file, *dst_file2;
int dst_bufsize, dst_bufsize2;
const char *fmt;
struct SwrContext *swr_ctx;
struct SwrContext *swr_ctx2;
double t;
int ret;
if (argc != 3) {
fprintf(stderr, "Usage: %s output_file_first output_file_second\n"
"API example program to show how to resample an audio stream with libswresample.\n"
"This program generates a series of audio frames, resamples them to a specified "
"output format and rate and saves them to an output file named output_file.\n",
argv[0]);
exit(1);
}
dst_filename = argv[1];
dst_filename2 = argv[2];
dst_file = fopen(dst_filename, "wb");
if (!dst_file) {
fprintf(stderr, "Could not open destination file %s\n", dst_filename);
exit(1);
}
dst_file2 = fopen(dst_filename2, "wb");
if (!dst_file2) {
fprintf(stderr, "Could not open destination file 2 %s\n", dst_filename2);
exit(1);
}
/* create resampler context */
swr_ctx = swr_alloc();
if (!swr_ctx) {
fprintf(stderr, "Could not allocate resampler context\n");
ret = AVERROR(ENOMEM);
goto end;
}
/* set options */
av_opt_set_int(swr_ctx, "in_channel_layout", src_ch_layout, 0);
av_opt_set_int(swr_ctx, "in_sample_rate", src_rate, 0);
av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt", src_sample_fmt, 0);
av_opt_set_int(swr_ctx, "out_channel_layout", dst_ch_layout, 0);
av_opt_set_int(swr_ctx, "out_sample_rate", dst_rate, 0);
av_opt_set_sample_fmt(swr_ctx, "out_sample_fmt", dst_sample_fmt, 0);
/* initialize the resampling context */
if ((ret = swr_init(swr_ctx)) < 0) {
fprintf(stderr, "Failed to initialize the resampling context\n");
goto end;
}
/* create resampler context 2 */
swr_ctx2 = swr_alloc();
if (!swr_ctx2) {
fprintf(stderr, "Could not allocate resampler context 2\n");
ret = AVERROR(ENOMEM);
goto end;
}
/* set options */
av_opt_set_int(swr_ctx2, "in_channel_layout", dst_ch_layout, 0);
av_opt_set_int(swr_ctx2, "in_sample_rate", dst_rate, 0);
av_opt_set_sample_fmt(swr_ctx2, "in_sample_fmt", dst_sample_fmt, 0);
av_opt_set_int(swr_ctx2, "out_channel_layout", dst_ch_layout, 0);
av_opt_set_int(swr_ctx2, "out_sample_rate", 32000, 0);
av_opt_set_sample_fmt(swr_ctx2, "out_sample_fmt", dst_sample_fmt, 0);
/* initialize the resampling context */
if ((ret = swr_init(swr_ctx2)) < 0) {
fprintf(stderr, "Failed to initialize the resampling context 2\n");
goto end;
}
/* allocate source and destination samples buffers */
src_nb_channels = av_get_channel_layout_nb_channels(src_ch_layout);
ret = av_samples_alloc_array_and_samples(&src_data, &src_linesize, src_nb_channels,
src_nb_samples, src_sample_fmt, 0);
if (ret < 0) {
fprintf(stderr, "Could not allocate source samples\n");
goto end;
}
/* compute the number of converted samples: buffering is avoided
* ensuring that the output buffer will contain at least all the
* converted input samples */
max_dst_nb_samples = dst_nb_samples =
av_rescale_rnd(src_nb_samples, dst_rate, src_rate, AV_ROUND_UP);
/* buffer is going to be directly written to a rawaudio file, no alignment */
dst_nb_channels = av_get_channel_layout_nb_channels(dst_ch_layout);
ret = av_samples_alloc_array_and_samples(&dst_data, &dst_linesize, dst_nb_channels,
dst_nb_samples, dst_sample_fmt, 0);
if (ret < 0) {
fprintf(stderr, "Could not allocate destination samples\n");
goto end;
}
/* compute the number of converted samples: buffering is avoided
* ensuring that the output buffer will contain at least all the
* converted input samples */
max_dst_nb_samples2 = dst_nb_samples2 =
av_rescale_rnd(dst_nb_samples, 32000, dst_rate, AV_ROUND_UP);
/* buffer is going to be directly written to a rawaudio file, no alignment */
// dst_nb_channels2 = av_get_channel_layout_nb_channels(dst_ch_layout);
ret = av_samples_alloc_array_and_samples(&dst_data2, &dst_linesize, dst_nb_channels,
dst_nb_samples2, dst_sample_fmt, 0);
if (ret < 0) {
fprintf(stderr, "Could not allocate destination samples 2\n");
goto end;
}
t = 0;
do {
/* generate synthetic audio */
fill_samples((double *)src_data[0], src_nb_samples, src_nb_channels, src_rate, &t);
/* compute destination number of samples */
dst_nb_samples = av_rescale_rnd(swr_get_delay(swr_ctx, src_rate) +
src_nb_samples, dst_rate, src_rate, AV_ROUND_UP);
if (dst_nb_samples > max_dst_nb_samples) {
av_freep(&dst_data[0]);
ret = av_samples_alloc(dst_data, &dst_linesize, dst_nb_channels,
dst_nb_samples, dst_sample_fmt, 1);
if (ret < 0)
break;
max_dst_nb_samples = dst_nb_samples;
}
/* convert to destination format */
ret = swr_convert(swr_ctx, dst_data, dst_nb_samples, (const uint8_t **)src_data, src_nb_samples);
if (ret < 0) {
fprintf(stderr, "Error while converting\n");
goto end;
}
dst_bufsize = av_samples_get_buffer_size(&dst_linesize, dst_nb_channels,
ret, dst_sample_fmt, 1);
if (dst_bufsize < 0) {
fprintf(stderr, "Could not get sample buffer size\n");
goto end;
}
printf("t:%f in:%d out:%d\n", t, src_nb_samples, ret);
fwrite(dst_data[0], 1, dst_bufsize, dst_file);
/* compute destination number of samples 2 */
dst_nb_samples2 = av_rescale_rnd(swr_get_delay(swr_ctx2, dst_rate) +
dst_nb_samples2, 32000, dst_rate, AV_ROUND_UP);
if (dst_nb_samples2 > max_dst_nb_samples2) {
av_freep(&dst_data2[0]);
ret = av_samples_alloc(dst_data2, &dst_linesize, dst_nb_channels,
dst_nb_samples2, dst_sample_fmt, 1);
if (ret < 0)
break;
max_dst_nb_samples2 = dst_nb_samples2;
}
/* convert to destination format */
ret = swr_convert(swr_ctx2, dst_data2, dst_nb_samples2, (const uint8_t **)dst_data, dst_nb_samples);
if (ret < 0) {
fprintf(stderr, "Error while converting 2\n");
goto end;
}
dst_bufsize2 = av_samples_get_buffer_size(&dst_linesize, dst_nb_channels,
ret, dst_sample_fmt, 1);
if (dst_bufsize2 < 0) {
fprintf(stderr, "Could not get sample buffer size 2\n");
goto end;
}
printf("t:%f in:%d out:%d\n", t, dst_nb_samples, ret);
fwrite(dst_data2[0], 1, dst_bufsize2, dst_file2);
} while (t < 10);
if ((ret = get_format_from_sample_fmt(&fmt, dst_sample_fmt)) < 0)
goto end;
fprintf(stderr, "Resampling succeeded. Play the output file with the command:\n"
"ffplay -f %s -channel_layout %"PRId64" -channels %d -ar %d %s\n",
fmt, dst_ch_layout, dst_nb_channels, dst_rate, dst_filename);
end:
fclose(dst_file);
if (src_data)
av_freep(&src_data[0]);
av_freep(&src_data);
if (dst_data)
av_freep(&dst_data[0]);
av_freep(&dst_data);
swr_free(&swr_ctx);
return ret < 0;
}
答案 0 :(得分：1)
我会检查一下，确保每次调用swr_convert（）时都将正确的缓冲区传递到输入中。请记住，您需要刷新swr_convert（）的输出，因此，如果要将对swr_convert（）的调用的输出传递给 second 调用，请确保先刷新第一个swr_context。