ffplay音频重采样 - 教程

⾳频重采样在 audio_decode_frame() 中实现， audio_decode_frame() 就是从⾳频frame队列中取出⼀个frame，按指定格式经过重采样后输出（解码不是在该函数进⾏）。

重采样的细节很琐碎，直接看注释：

static int audio_decode_frame(VideoState *is)
{
int data_size, resampled_data_size;
int64_t dec_channel_layout;
av_unused double audio_clock0;
int wanted_nb_samples;
Frame *af;
if (is->paused)
return -1;
do {
#if defined(_WIN32)
while (frame_queue_nb_remaining(&is->sampq) == 0) {
if ((av_gettime_relative() - audio_callback_time) >
1000000LL * is->audio_hw_buf_size / is->audio_tgt.bytes_per_sec / 2)
return -1;
av_usleep (1000);
}
#endif
// 若队列头部可读，则由af指向可读帧
if (!(af = frame_queue_peek_readable(&is->sampq)))
return -1;
frame_queue_next(&is->sampq);
} while (af->serial != is->audioq.serial);
// 根据farme中指定的音频参数获取缓冲区的大小
data_size = av_samples_get_buffer_size(NULL, af->frame->channels,
af->frame->nb_samples,
af->frame->format, 1);
// 获取声道布局
dec_channel_layout =
(af->frame->channel_layout && af->frame->channels == av_get_channel_layout_nb_channels(af->frame->channel_layout)) ?
af->frame->channel_layout : av_get_default_channel_layout(af->frame->channels);
wanted_nb_samples = synchronize_audio(is, af->frame->nb_samples);
if (af->frame->format != is->audio_src.fmt ||
dec_channel_layout != is->audio_src.channel_layout ||
af->frame->sample_rate != is->audio_src.freq ||
(wanted_nb_samples != af->frame->nb_samples &&
!is->swr_ctx)) {
swr_free(&is->swr_ctx);
is->swr_ctx = swr_alloc_set_opts(NULL,
is->audio_tgt.channel_layout, is->audio_tgt.fmt, is->audio_tgt.freq,
dec_channel_layout, af->frame->format, af->frame->sample_rate,
0, NULL);
if (!is->swr_ctx || swr_init(is->swr_ctx) <
0) {
av_log(NULL, AV_LOG_ERROR,
"Cannot create sample rate converter for conversion of %d Hz %s %d channels to %d Hz %s %d channels!\n",
af->frame->sample_rate, av_get_sample_fmt_name(af->frame->format), af->frame->channels,
is->audio_tgt.freq, av_get_sample_fmt_name(is->audio_tgt.fmt), is->audio_tgt.channels);
swr_free(&is->swr_ctx);
return -1;
}
is->audio_src.channel_layout = dec_channel_layout;
is->audio_src.channels = af->frame->channels;
is->audio_src.freq = af->frame->sample_rate;
is->audio_src.fmt = af->frame->format;
}
if (is->swr_ctx) {
const uint8_t **in = (const uint8_t **)af->frame->extended_data;
uint8_t **out = &is->audio_buf1;
int out_count = (int64_t)wanted_nb_samples * is->audio_tgt.freq / af->frame->sample_rate + 256;
int out_size = av_samples_get_buffer_size(NULL, is->audio_tgt.channels, out_count, is->audio_tgt.fmt, 0);
int len2;
if (out_size <
0) {
av_log(NULL, AV_LOG_ERROR, "av_samples_get_buffer_size() failed\n");
return -1;
}
if (wanted_nb_samples != af->frame->nb_samples) {
if (swr_set_compensation(is->swr_ctx, (wanted_nb_samples - af->frame->nb_samples) * is->audio_tgt.freq / af->frame->sample_rate,
wanted_nb_samples * is->audio_tgt.freq / af->frame->sample_rate) <
0) {
av_log(NULL, AV_LOG_ERROR, "swr_set_compensation() failed\n");
return -1;
}
}
av_fast_malloc(&is->audio_buf1, &is->audio_buf1_size, out_size);
if (!is->audio_buf1)
return AVERROR(ENOMEM);
len2 = swr_convert(is->swr_ctx, out, out_count, in, af->frame->nb_samples);
if (len2 <
0) {
av_log(NULL, AV_LOG_ERROR, "swr_convert() failed\n");
return -1;
}
if (len2 == out_count) {
av_log(NULL, AV_LOG_WARNING, "audio buffer is probably too small\n");
if (swr_init(is->swr_ctx) <
0)
swr_free(&is->swr_ctx);
}
// 重采样返回的⼀帧⾳频数据⼤⼩(以字节为单位)
is->audio_buf = is->audio_buf1;
resampled_data_size = len2 * is->audio_tgt.channels * av_get_bytes_per_sample(is->audio_tgt.fmt);
} else {
// 未经过重采样，则将指针指向frame中的音频数据
is->audio_buf = af->frame->data[0];
resampled_data_size = data_size;
}
audio_clock0 = is->audio_clock;
/* update the audio clock with the pts */
if (!isnan(af->pts))
is->audio_clock = af->pts + (double) af->frame->nb_samples / af->frame->sample_rate;
else
is->audio_clock = NAN;
is->audio_clock_serial = af->serial;
#ifdef DEBUG
{
static double last_clock;
printf("audio: delay=%0.3f clock=%0.3f clock0=%0.3f\n",
is->audio_clock - last_clock,
is->audio_clock, audio_clock0);
last_clock = is->audio_clock;
}
#endif
return resampled_data_size;
}

样本补偿

swr_set_compensation说明

/**
* @}
*
* @name Low-level option setting functions
* These functons provide a means to set low-level options that is not possible
* with the AVOption API.
* @{
*/
/**
* Activate resampling compensation ("soft" compensation). This function is
* internally called when needed in swr_next_pts().
*
* @param[in,out] s allocated Swr context. If it is not initialized,
* or SWR_FLAG_RESAMPLE is not set, swr_init() is
* called with the flag set.
每个样本增量，单位pts
* @param[in] sample_delta delta in PTS per sample
要补偿的样本数
* @param[in] compensation_distance number of samples to compensate for
* @return >= 0 on success, AVERROR error codes if:
* @li @c s is NULL,
* @li @c compensation_distance is less than 0,
* @li @c compensation_distance is 0 but sample_delta is not,
* @li compensation unsupported by resampler, or
* @li swr_init() fails when called.
*/
int swr_set_compensation(struct SwrContext *s, int sample_delta, int compensation_distance);

参考资料：https://github.com/0voice