ffmepg音频重采样

1.概述

在进行音频播放时，有时视频流不能满足播放要求，需要对声音的相关属性如：通道数，采样率，样本存储方式进行变更播放，也就是音频重采样。ffmpeg提供了SwrContext进行转换。

      typedef struct SwrContext SwrContext; 

2.基本概念

2.1通道数

声音在录制时在不同空间位置用不同录音设备采样的声音信号，声音在播放时采用相应个数的扬声器播放。采用多通道的方式是为了丰富声音的现场感。常用的立体声有2个通道，环绕立体声3个通道。数字音频就是有一连串的样本流组成，立体声每次采用要采两次。有点类似视频中的YUV各个分量。

2.2采样率

把模拟信号转换成数字信号在计算机中处理，需要按照一定的采样率采样，样本值就是声音波形中的一个值。音频在播放时按照采样率进行，采样率越高声音的连续性就越好，由于人的听觉器官分辨能力的局限，往往这些数值达到某种程度就可以满足人对“连续”性的需求了。例如22050和44100的采样率就是电台和CD 常用的采样率。类似视频中的帧率。

2.3比特率（bps或kbps）

单位时间所需的空间存储。比特率反应的是视频或者音频一个样本所有的信息量，越大含有的信息量就大。视频中，图像分辨率越大，一帧就越大，实时解码就容易饥渴，传输带宽需要越大，存储空间就越大。音频中描述一个样本就越准确。

2.4帧

视频中帧就是一个图片采样。音频中一帧一般包含多个样本，如AAC格式会包含1024个样本。

2.5样本格式

音频中一个样本存储方式。列举ffmpeg中的样本格式

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_NB           ///< Number of sample formats. DO NOT USE if linking dynamically};

讲一下AV_SAMPLE_FMT_S16和AV_SAMPLE_FMT_S16P格式，AV_SAMPLE_FMT_S16保存一个样本采用有符号16bit交叉存储的方式，AV_SAMPLE_FMT_S16P保存一个样本采用有符号16bit平面存储的方式。举例有两个通道，通道1数据流 c1 c1 c1c1... , 通道2数据流 c2 c2 c2 c2...

平面存储方式：c1 c1 c1c1... c2 c2 c2 c2...

交叉存储方式：c1, c2,c1, c2, c1, c2, ...

AVFrame中平面方式planar每个通道数据存储在data[0], data[1]中，长度为linesize[0],linesize[1],交叉方式则所有的数据都存储在data[0],长度为linesize[0]。

3.ffmepg实例

例程是ffmpeg2.4源代码目录下的doc/examples/resampling_audio.c文件，为便于学习做部分修改。

3.1 根据样本格式返回样本格式字符串

 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);}

 

3.2获取声音

/*** Fill dst buffer with nb_samples, generated starting from t.*相当于是声源 产生一个正弦波形的声波* dst 保存声音数据返回个调用者 nb_samples 采用的样本数 nb_channels 声音通道数，表明单次采样的样本数 t采用开始时间*正弦波形就是一个生源，实际中复杂的声音都是通过波形叠加成的。*以 sample_rate采样率，从时间t开始采样，采样通道为2，每个通道的数据相同，从频率为440HZ的波形上采样，形成声源*/static void fill_samples(double *dst, int nb_samples, int nb_channels, int sample_rate, double *t){int i, j;//采样时间间隔    tincrdouble tincr = 1.0 / sample_rate, *dstp = dst;//正弦波y=Asin（ωx+φ）+h 最小正周期T=2π/|ω| 所以440HZ是正弦波的频率const double c = 2 * M_PI * 440.0;/* generate sin tone with 440Hz frequency and duplicated channels *///填充每个通道数据 采用交叉存储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;}}

3.2主函数

int main(int argc, char **argv){// AV_CH_LAYOUT_STEREO 声音布局立体声   AV_CH_LAYOUT_SURROUND 声音布局环绕立体声int64_t src_ch_layout = AV_CH_LAYOUT_STEREO, dst_ch_layout = AV_CH_LAYOUT_SURROUND;//声音采样率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;//每次采用样本数int src_nb_samples = 1024, dst_nb_samples, max_dst_nb_samples;//样本存储格式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;//重采样上下文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 *///初始化常采样上下文swr_ctx = swr_alloc();if (!swr_ctx) {fprintf(stderr, "Could not allocate resampler context\n");ret = AVERROR(ENOMEM);goto end;}/* set options *///设置源通道布局av_opt_set_int(swr_ctx, "in_channel_layout",    src_ch_layout, 0);//设置源通道采样率av_opt_set_int(swr_ctx, "in_sample_rate",       src_rate, 0);//设置源通道样本格式av_opt_set_sample_fmt(swr_ctx, "in_sample_fmt", src_sample_fmt, 0);//目标通道布局av_opt_set_int(swr_ctx, "out_channel_layout",    dst_ch_layout, 0);//目标采用率av_opt_set_int(swr_ctx, "out_sample_rate",       dst_rate, 0);//目标样本格式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 *///获取源通道数src_nb_channels = av_get_channel_layout_nb_channels(src_ch_layout);//分配源声音所需要空间  src_linesize= src_nb_channels× src_nb_samples×sizeof(double)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 *///计算目标样本数  转换前后的样本数不一样  抓住一点 采样时间相等//src_nb_samples/src_rate=dst_nb_samples/dst_ratemax_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 *///swr_get_delay(swr_ctx, src_rate)延迟时间 源采样率为单位的样本数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 实际转换得到的样本数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 %lld -channels %d -ar %d %s\n",fmt, dst_ch_layout, dst_nb_channels, dst_rate, dst_filename);while(1){Sleep(50);}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;}

编译环境：Win7_32bit+VS2010

FFMPEG版本：ffmpeg-2.4

源代码下载地址：http://download.csdn.net/detail/hiwubihe/9593005

技术在于交流、沟通，转载请注明出处并保持作品的完整性。

原文：//http://blog.csdn.net/hiwubihe/article/details/52059378