FFmpeg从入门到牛掰（五）：音频重采样(resample)讲解

转载请注明出处：https://blog.csdn.net/impingo
项目地址：https://github.com/im-pingo/pingos

描述

前两篇文章分别介绍了使用ffmpeg对音频解码和编码的过程，但是实际音频转码过程中我们大多情况下需要对声道数（channels）采样率（sample rate）采样长度（AVSampleFormat）等等参数进行调整，这时候就不能直接对解码后的pcm编码成我们想要的编码格式，而是需要重新采样。
重新采样可以制定我们希望输出的声道数（channels）采样率（sample rate）采样长度（AVSampleFormat）。

操作流程

通过前面的文章已经知道对于容器操作（转封装）需要通过 AVFormatContext 进行操作，对于转码需要通过AVCodecContext进行操作。
同样地，对于重采样来说也有对应的操作上下文 SwrContext，重采样的原理是输入pcm数据然后根据输入的pcm数据和输入输出参数生成新的pcm数据。

需要注意的是，重采样操作需要开发者分别设置输入和输入pcm的channel_layout、sample_rate、sample_fmt参数，这里一定不能设置错，否则重采样后的pcm声音会坏掉。
一般情况下，对于channel_layout参数而言，如果已知声道数可以通过函数channel_layout = av_get_default_channel_layout(channels); 当然也可指定，关于这个参数的含义请参考我的另一篇文章【FFmpeg从入门到牛掰（基础）：编解码基础讲解】。
采样率（sample_rate）参数需要手动指定
采样模式（sample_fmt），这个参数主要用来设置每个采样的物理存储大小，例如8字节、16字节、32字节，数据类型为signed或unsigned类型。

操作流程如下：

1. swr_alloc() 创建SwrContext 上下文
2. 通过 av_opt_set_int() 和 av_opt_set_sample_fmt() 设置输入参数“in_channel_layout”、“in_sample_rate”、“in_sample_fmt”
3. 通过 av_opt_set_int() 和 av_opt_set_sample_fmt() 设置输出参数“out_channel_layout”、“out_sample_rate”、“out_sample_fmt”
4. 调用swr_init()初始化SwrContext
5. 循环调用swr_convert()函数将输入pcm转换成输出pcm

函数接口

struct SwrContext *swr_alloc(void)

创建SwrContext指针。

int64_t src_ch_layout = AV_CH_LAYOUT_STEREO;
int64_t dst_ch_layout = AV_CH_LAYOUT_SURROUND;
int src_rate = 48000, dst_rate = 44100;
enum AVSampleFormat src_sample_fmt = AV_SAMPLE_FMT_DBL;
enum AVSampleFormat dst_sample_fmt = AV_SAMPLE_FMT_S16;

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);

通过以上操作设置输入音频的参数和输出音频（重采样之后的音频）的参数。

int swr_init(struct SwrContext *s)

设置完输入和输出参数之后，一定要调用该函数进行初始化。

int swr_convert(struct SwrContext *s, uint8_t *out_arg[SWR_CH_MAX], int out_count,const uint8_t *in_arg [SWR_CH_MAX], int  in_count);

通过这个函数将输入pcm重新采样后生成新的pcm数据，输出pcm保存在out_arg中。
关于swr_convert的使用方式请参考以下示例代码。

示例代码

/**
 * @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;
    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;
    enum AVSampleFormat src_sample_fmt = AV_SAMPLE_FMT_DBL, dst_sample_fmt = AV_SAMPLE_FMT_S16;
    const char *dst_filename = NULL;
    FILE *dst_file;
    int dst_bufsize;
    const char *fmt;
    struct SwrContext *swr_ctx;
    double t;
    int ret;

    if (argc != 2) {
        fprintf(stderr, "Usage: %s output_file\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_file = fopen(dst_filename, "wb");
    if (!dst_file) {
        fprintf(stderr, "Could not open destination file %s\n", dst_filename);
        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;
    }

    /* 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;
    }

    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);
    } 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;
}

QQ交流群：697773082