标签: ffmpeg音频处理 音频重采样cc++
2016-07-28 21:37 1481人阅读 收藏 举报
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,
- AV_SAMPLE_FMT_S16,
- AV_SAMPLE_FMT_S32,
- AV_SAMPLE_FMT_FLT,
- AV_SAMPLE_FMT_DBL,
-
- AV_SAMPLE_FMT_U8P,
- AV_SAMPLE_FMT_S16P,
- AV_SAMPLE_FMT_S32P,
- AV_SAMPLE_FMT_FLTP,
- AV_SAMPLE_FMT_DBLP,
-
- AV_SAMPLE_FMT_NB
- };
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
-
-
-
-
-
-
-
- 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;
-
-
-
- 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)
- {
-
- 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);
- }
-
-
-
- swr_ctx = swr_alloc();
- if (!swr_ctx)
- {
- fprintf(stderr, "Could not allocate resampler context\n");
- ret = AVERROR(ENOMEM);
- goto end;
- }
-
-
-
- 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);
-
-
- if ((ret = swr_init(swr_ctx)) < 0)
- {
- fprintf(stderr, "Failed to initialize the resampling context\n");
- goto end;
- }
-
-
-
- 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;
- }
-
-
-
-
-
-
- max_dst_nb_samples = dst_nb_samples = av_rescale_rnd(src_nb_samples, dst_rate, src_rate, AV_ROUND_UP);
-
-
- 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 {
-
- fill_samples((double *)src_data[0], src_nb_samples, src_nb_channels, src_rate, &t);
-
-
-
- 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;
- }
-
-
-
- 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