音频处理基本概念及音频重采样
生活随笔
收集整理的這篇文章主要介紹了
音频处理基本概念及音频重采样
小編覺得挺不錯的,現在分享給大家,幫大家做個參考.
音頻處理基本概念及音頻重采樣
目錄
1. 重點問題
2. 重采樣
1. 什么是重采樣
2. 為什么要重采樣
3. 可調節的參數
3. 對應參數解析
1. 采樣率
2. 采樣格式及量化精度（位寬）
3. 分?（plane）和打包（packed）
4. 聲道分布（channel_layout)
5. ?頻幀的數據量計算
6. ?頻播放時間計算
（1）10241000/44100=23.21995464852608ms ->約等于 23.2ms，精度損失了0.011995464852608ms，如果累計10萬幀，誤差>1199毫秒，如果有視頻?起的就會有?視頻同步的問題。 如果按著23.2去計算pts（0 23.2 46.4 ）就會有累積誤差。
（2）1024*1000/48000=21.33333333333333ms
4. FFmpeg重采樣API
5. ?頻重采樣?程范例
1. 簡單范例（resample）
/** Copyright (c) 2012 Stefano Sabatini** Permission is hereby granted, free of charge, to any person obtaining a copy* of this software and associated documentation files (the "Software"), to deal* in the Software without restriction, including without limitation the rights* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell* copies of the Software, and to permit persons to whom the Software is* furnished to do so, subject to the following conditions:** The above copyright notice and this permission notice shall be included in* all copies or substantial portions of the Software.** THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN* THE SOFTWARE.*//*** @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. 交錯模式的*/ 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) {// 輸入參數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; // 二級指針int src_linesize;int src_nb_samples = 1024;// 輸出參數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; //二級指針int dst_linesize;int dst_nb_samples;int max_dst_nb_samples;// 輸出文件const char *dst_filename = NULL; // 保存輸出的pcm到本地，然后播放驗證FILE *dst_file;int dst_bufsize;const char *fmt;// 重采樣實例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 = "/Users/lijinwang/Downloads/course/study/believe.pcm";dst_file = fopen(dst_filename, "wb");if (!dst_file) {fprintf(stderr, "Could not open destination file %s\n", dst_filename);exit(1);}// 創建重采樣器/* create resampler context */swr_ctx = swr_alloc();if (!swr_ctx) {fprintf(stderr, "Could not allocate resampler context\n");ret = AVERROR(ENOMEM);goto end;}// 設置重采樣參數/* set options */// 輸入參數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);// 輸出參數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);// 初始化重采樣/* 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 */// 計算出輸入源的通道數量src_nb_channels = av_get_channel_layout_nb_channels(src_ch_layout);// 給輸入源分配內存空間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 */// 計算輸出采樣數量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);// 分配輸出緩存內存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 */// 生成輸入源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);dst_nb_samples = av_rescale_rnd(delay + 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;}// int fifo_size = swr_get_out_samples(swr_ctx,src_nb_samples);// printf("fifo_size:%d\n", fifo_size);// if(fifo_size < 1024)// continue;/* convert to destination format */// ret = swr_convert(swr_ctx, dst_data, dst_nb_samples, (const uint8_t **)src_data, src_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);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;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; }2. 復雜范例
總結
以上是生活随笔為你收集整理的音频处理基本概念及音频重采样的全部內容，希望文章能夠幫你解決所遇到的問題。
- 上一篇： AVIO内存输入模式
- 下一篇： 音频编码案例