什么是重采样?

所谓的重采样,就是改变⾳频的采样率、sampleformat、声道数等参数,使之按照我们期望的参数输出。

为什么要重采样?

 为什么要重采样?当然是原有的⾳频参数不满⾜我们的需求,⽐如在FFmpeg解码⾳频的时候,不同的⾳源有不同的格式,采样率等,在解码后的数据中的这些参数也会不⼀致(最新FFmpeg解码⾳频后,⾳频格式为AV_SAMPLE_FMT_FLTP,这个参数应该是⼀致的),如果我们接下来需要使⽤解码后的⾳频数据做其他操作,⽽这些参数的不⼀致导致会有很多额外⼯作,此时直接对其进⾏重采样,获取我们制定的⾳频参数,这样就会⽅便很多。再⽐如在将⾳频进⾏SDL播放时候,因为当前的SDL2.0不⽀持planar格式,也不⽀持浮点型的,⽽最新的FFMPEG16年会将⾳频解码为AV_SAMPLE_FMT_FLTP格式,因此此时就需要我们对其重采样,使之可以在SDL2.0上进⾏播放。

 怎样重采样?

利用ffmpeg内部的重采样器进行重采样

 注意事项

1.关于音频质量损失问题
我们在进行如44.1khz采样率向48khz采样率的音频进行转换时 因为我们要求重采样后音频的时长不能发生变化 而在时长相同时 48khz采样率肯定比44.1khz采样率的采样点要多的多 所以必然会带来精度的损失 但是44.1khz转换为48khz 就算损失了 人耳还是听不出来的
2.ffmpeg中内部支持互相转换的采样格式和声道分布
enum AVSampleFormat {
    AV_SAMPLE_FMT_NONE = -1,
    AV_SAMPLE_FMT_U8,          ///< unsigned 8 bits
    AV_SAMPLE_FMT_S16,         ///< signed 16 bits
    AV_SAMPLE_FMT_S32,         ///< signed 32 bits
    AV_SAMPLE_FMT_FLT,         ///< float
    AV_SAMPLE_FMT_DBL,         ///< double

    AV_SAMPLE_FMT_U8P,         ///< unsigned 8 bits, planar
    AV_SAMPLE_FMT_S16P,        ///< signed 16 bits, planar
    AV_SAMPLE_FMT_S32P,        ///< signed 32 bits, planar
    AV_SAMPLE_FMT_FLTP,        ///< float, planar
    AV_SAMPLE_FMT_DBLP,        ///< double, planar
    AV_SAMPLE_FMT_S64,         ///< signed 64 bits
    AV_SAMPLE_FMT_S64P,        ///< signed 64 bits, planar

    AV_SAMPLE_FMT_NB           ///< Number of sample formats. DO NOT USE if linking dynamically
};#define AV_CH_LAYOUT_MONO              (AV_CH_FRONT_CENTER)
#define AV_CH_LAYOUT_STEREO            (AV_CH_FRONT_LEFT|AV_CH_FRONT_RIGHT)
#define AV_CH_LAYOUT_2POINT1           (AV_CH_LAYOUT_STEREO|AV_CH_LOW_FREQUENCY)
#define AV_CH_LAYOUT_2_1               (AV_CH_LAYOUT_STEREO|AV_CH_BACK_CENTER)
#define AV_CH_LAYOUT_SURROUND          (AV_CH_LAYOUT_STEREO|AV_CH_FRONT_CENTER)
#define AV_CH_LAYOUT_3POINT1           (AV_CH_LAYOUT_SURROUND|AV_CH_LOW_FREQUENCY)
#define AV_CH_LAYOUT_4POINT0           (AV_CH_LAYOUT_SURROUND|AV_CH_BACK_CENTER)
#define AV_CH_LAYOUT_4POINT1           (AV_CH_LAYOUT_4POINT0|AV_CH_LOW_FREQUENCY)
#define AV_CH_LAYOUT_2_2               (AV_CH_LAYOUT_STEREO|AV_CH_SIDE_LEFT|AV_CH_SIDE_RIGHT)
#define AV_CH_LAYOUT_QUAD              (AV_CH_LAYOUT_STEREO|AV_CH_BACK_LEFT|AV_CH_BACK_RIGHT)
#define AV_CH_LAYOUT_5POINT0           (AV_CH_LAYOUT_SURROUND|AV_CH_SIDE_LEFT|AV_CH_SIDE_RIGHT)
#define AV_CH_LAYOUT_5POINT1           (AV_CH_LAYOUT_5POINT0|AV_CH_LOW_FREQUENCY)
#define AV_CH_LAYOUT_5POINT0_BACK      (AV_CH_LAYOUT_SURROUND|AV_CH_BACK_LEFT|AV_CH_BACK_RIGHT)
#define AV_CH_LAYOUT_5POINT1_BACK      (AV_CH_LAYOUT_5POINT0_BACK|AV_CH_LOW_FREQUENCY)
#define AV_CH_LAYOUT_6POINT0           (AV_CH_LAYOUT_5POINT0|AV_CH_BACK_CENTER)
#define AV_CH_LAYOUT_6POINT0_FRONT     (AV_CH_LAYOUT_2_2|AV_CH_FRONT_LEFT_OF_CENTER|AV_CH_FRONT_RIGHT_OF_CENTER)
#define AV_CH_LAYOUT_HEXAGONAL         (AV_CH_LAYOUT_5POINT0_BACK|AV_CH_BACK_CENTER)
#define AV_CH_LAYOUT_6POINT1           (AV_CH_LAYOUT_5POINT1|AV_CH_BACK_CENTER)
#define AV_CH_LAYOUT_6POINT1_BACK      (AV_CH_LAYOUT_5POINT1_BACK|AV_CH_BACK_CENTER)
#define AV_CH_LAYOUT_6POINT1_FRONT     (AV_CH_LAYOUT_6POINT0_FRONT|AV_CH_LOW_FREQUENCY)
#define AV_CH_LAYOUT_7POINT0           (AV_CH_LAYOUT_5POINT0|AV_CH_BACK_LEFT|AV_CH_BACK_RIGHT)
#define AV_CH_LAYOUT_7POINT0_FRONT     (AV_CH_LAYOUT_5POINT0|AV_CH_FRONT_LEFT_OF_CENTER|AV_CH_FRONT_RIGHT_OF_CENTER)
#define AV_CH_LAYOUT_7POINT1           (AV_CH_LAYOUT_5POINT1|AV_CH_BACK_LEFT|AV_CH_BACK_RIGHT)
#define AV_CH_LAYOUT_7POINT1_WIDE      (AV_CH_LAYOUT_5POINT1|AV_CH_FRONT_LEFT_OF_CENTER|AV_CH_FRONT_RIGHT_OF_CENTER)
#define AV_CH_LAYOUT_7POINT1_WIDE_BACK (AV_CH_LAYOUT_5POINT1_BACK|AV_CH_FRONT_LEFT_OF_CENTER|AV_CH_FRONT_RIGHT_OF_CENTER)
#define AV_CH_LAYOUT_OCTAGONAL         (AV_CH_LAYOUT_5POINT0|AV_CH_BACK_LEFT|AV_CH_BACK_CENTER|AV_CH_BACK_RIGHT)
#define AV_CH_LAYOUT_HEXADECAGONAL     (AV_CH_LAYOUT_OCTAGONAL|AV_CH_WIDE_LEFT|AV_CH_WIDE_RIGHT|AV_CH_TOP_BACK_LEFT|AV_CH_TOP_BACK_RIGHT|AV_CH_TOP_BACK_CENTER|AV_CH_TOP_FRONT_CENTER|AV_CH_TOP_FRONT_LEFT|AV_CH_TOP_FRONT_RIGHT)
#define AV_CH_LAYOUT_STEREO_DOWNMIX    (AV_CH_STEREO_LEFT|AV_CH_STEREO_RIGHT)
3.存储格式的不同 交错模式和平面模式
以双声道为例,带P(plane)的数据格式在存储时,其左声道和右声道的数据是分开存储的,左声道的数据存储在data[0],右声道的数据存储在data[1],每个声道的所占⽤的字节数为linesize[0]和linesize[1];不带P(packed)的⾳频数据在存储时,是按照LRLRLR...的格式交替存储在data[0]中,linesize[0]表示总的数据量。
4.linesize和nb_samples
linesize表示一个平面内总比特数(经过内存对齐) nb_samples表示一帧音频帧的采样点数
5.swr_get_delay


重采样器上下文中会缓冲一些还没有重采样的采样点 通过这个函数拿到

关于重采样的代码具体实现 ffmpeg官方例子加上中文注释

extern "C"
{
#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. 交错模式的
 */
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)
{
    // 输入参数
    int64_t src_ch_layout = AV_CH_LAYOUT_STEREO;
    int src_rate = 48000;
    enum AVSampleFormat src_sample_fmt = AV_SAMPLE_FMT_DBL;
    int src_nb_channels = 0;
    uint8_t** src_data = NULL;  // 二级指针
    int src_linesize;
    int src_nb_samples = 1024;


    // 输出参数
    int64_t dst_ch_layout = AV_CH_LAYOUT_STEREO;
    int dst_rate = 44100;
    enum AVSampleFormat dst_sample_fmt = AV_SAMPLE_FMT_S16;
    int dst_nb_channels = 0;
    uint8_t** dst_data = NULL;  //二级指针
    //为什么我们这里是二级指针呢 因为存储格式的不同可能导致存储有多个平面 所以我们需要到dst_data[0]和dst_data[1]拿数据
    int dst_linesize;
    int dst_nb_samples;
    int max_dst_nb_samples;

    // 输出文件
    const char* dst_filename = NULL;    // 保存输出的pcm到本地,然后播放验证
    FILE* dst_file;


    int dst_bufsize;
    const char* fmt;

    // 重采样实例
    struct SwrContext* swr_ctx;

    double t;
    int ret;

    //这里随便填 我填的是我本地的一个文件
    dst_filename = "c://out.pcm";

    dst_file = fopen(dst_filename, "wb");
    if (!dst_file) {
        fprintf(stderr, "Could not open destination file %s\n", dst_filename);
        exit(1);
    }

    // 创建重采样器
    /* create resampler context */
    swr_ctx = swr_alloc();
    if (!swr_ctx) {
        fprintf(stderr, "Could not allocate resampler context\n");
        ret = AVERROR(ENOMEM);
        goto end;
    }

    // 设置重采样参数
    /* set options */
    // 输入参数
    av_opt_set_int(swr_ctx, "in_channel_layout", src_ch_layout, 0);//源通道数    
    av_opt_set_int(swr_ctx, "in_sample_rate", src_rate, 0);//源采样率
    av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt", src_sample_fmt, 0);//源采样格式
    // 输出参数
    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);

    // 初始化重采样
    /* 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 */
    // 计算出输入源的通道数量
    src_nb_channels = av_get_channel_layout_nb_channels(src_ch_layout);
    // 给输入源分配内存空间 为什么会是三级指针呢 因为需要给src[0] src[1]分配内存
    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 */
     // 计算一帧音频输出采样数量
    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);
    // 分配输出缓存内存
    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 */
        // 生成输入源 这里是自定义的输入源 一个正弦波 你不用管 本来这里也可以用你读出来的AVFrame里的数据来填充
        fill_samples((double*)src_data[0], src_nb_samples, src_nb_channels, src_rate, &t);

        /* compute destination number of samples */
        int64_t delay = swr_get_delay(swr_ctx, src_rate);//拿到swr_ctx中缓存的采样点数量
        dst_nb_samples = av_rescale_rnd(delay + src_nb_samples, dst_rate, src_rate, AV_ROUND_UP);//重新计算输出音频帧一帧采样点数量
        if (dst_nb_samples > max_dst_nb_samples) {//如果大于 释放内存后重新分配内存
            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;
        }
      
        ret = swr_convert(swr_ctx, dst_data, dst_nb_samples, (const uint8_t**)src_data, src_nb_samples);//真正的转换函数
        if (ret < 0) {
            fprintf(stderr, "Error while converting\n");
            goto end;
        }
        //拿到输出字节数
        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);
    //拿到swr中剩下的采样点 上文也提及到了 可能swr内部会有缓存的
    ret = swr_convert(swr_ctx, dst_data, dst_nb_samples, NULL, 0);
    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("flush in:%d out:%d\n", 0, ret);
    fwrite(dst_data[0], 1, dst_bufsize, dst_file);


    if ((ret = get_format_from_sample_fmt(&fmt, dst_sample_fmt)) < 0)
        goto end;
  

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;
}