概要

本文介紹使用 FFmpeg，將MP3或WAV文件解碼成PCM文件的方法。

整體架構(gòu)流程

首先，使用的 FFmpeg 庫要支持 MP3/WAV 解碼功能，即編譯的時(shí)候要加上（編譯 FFmpeg 庫可以參考：Windows編譯和使用ffmpeg）：

--enable-decoder=mp3float --enable-decoder=pcm_s16le --enable-demuxer=mp3 --enable-demuxer=wav

下面的函數(shù)就是利用 FFmpeg 接口，實(shí)現(xiàn)將 MP3 或 WAV 文件解碼成PCM文件：

#ifdef __cplusplus
extern "C" {
#endif
#include "libavutil/imgutils.h"
#include "libavcodec/avcodec.h"
#include "libavformat/avformat.h"
#include "libswresample/swresample.h"
#ifndef __linux__
#include "libswscale/swscale.h"
#endif
#include "libavutil/opt.h"
#ifdef __cplusplus
}
#endif#pragma comment(lib, "libavcodec.a")
#pragma comment(lib, "libavformat.a")
#pragma comment(lib, "libavutil.a")
#pragma comment(lib, "libswresample.a")int DecodedAudioFile(const char *pFileName) {FILE *pFile = fopen("tmp.pcm", "wb");  // 輸出文件AVFormatContext *pFormatCtx;AVCodecContext *pCodecCtx;AVCodec *pCodec;AVPacket *packet;AVFrame *pFrame;struct SwrContext *au_convert_ctx = NULL;av_register_all();avformat_network_init();pFormatCtx = avformat_alloc_context();if (avformat_open_input(&pFormatCtx, pFileName, NULL, NULL) != 0) {OutputDebugStringA("Couldn't open input stream.\n");return -1;}if (avformat_find_stream_info(pFormatCtx, NULL) < 0) {OutputDebugStringA("Couldn't find stream information.\n");return -1;}av_dump_format(pFormatCtx, 0, pFileName, false);// Find the first audio streamint audioStream = -1;for (int i = 0; i < pFormatCtx->nb_streams; i++) {if (pFormatCtx->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO) {audioStream = i;break;}}if (audioStream == -1) {OutputDebugStringA("Didn't find a audio stream.\n");return -1;}// Get a pointer to the codec context for the audio streampCodecCtx = pFormatCtx->streams[audioStream]->codec;// Find the decoder for the audio streampCodec = avcodec_find_decoder(pCodecCtx->codec_id);if (pCodec == NULL) {OutputDebugStringA("Codec not found.\n");return -1;}// Open codecif (avcodec_open2(pCodecCtx, pCodec, NULL) < 0) {OutputDebugStringA("Could not open codec.\n");return -1;}int64_t in_channel_layout = av_get_default_channel_layout(pCodecCtx->channels);packet = (AVPacket*)av_malloc(sizeof(AVPacket));av_init_packet(packet);// Out Audio Paramuint64_t out_channel_layout = in_channel_layout;int out_nb_samples = pCodecCtx->frame_size;AVSampleFormat out_sample_fmt = AV_SAMPLE_FMT_S16;int out_sample_rate = pCodecCtx->sample_rate;int out_channels = pCodecCtx->channels;// Out Buffer Sizeint out_buffer_size = av_samples_get_buffer_size(NULL, out_channels, out_nb_samples, out_sample_fmt, 1);uint8_t *out_buffer = (uint8_t*)av_malloc(MAX_AUDIO_FRAME_SIZE * 2);pFrame = av_frame_alloc();// 如果輸入文件格式不是AV_SAMPLE_FMT_S16才需要if (pCodecCtx->sample_fmt != AV_SAMPLE_FMT_S16) {au_convert_ctx = swr_alloc();au_convert_ctx = swr_alloc_set_opts(au_convert_ctx, out_channel_layout, out_sample_fmt, out_sample_rate,in_channel_layout, pCodecCtx->sample_fmt, pCodecCtx->sample_rate, 0, NULL);swr_init(au_convert_ctx);}while (av_read_frame(pFormatCtx, packet) >= 0) {if (packet->stream_index == audioStream) {int got_picture;int ret = avcodec_decode_audio4(pCodecCtx, pFrame, &got_picture, packet);if (ret < 0) {OutputDebugStringA("Error in decoding audio frame.\n");return -1;}if (got_picture > 0) {if (au_convert_ctx) {  // MP3文件格式通常是AV_SAMPLE_FMT_FLTP，要重采樣、格式轉(zhuǎn)換等swr_convert(au_convert_ctx, &out_buffer, MAX_AUDIO_FRAME_SIZE, (const uint8_t**)pFrame->data, pFrame->nb_samples);// Write PCMfwrite(out_buffer, 1, out_buffer_size, pFile);} else {  // WAV文件格式通常是AV_SAMPLE_FMT_S16，與輸出文件一致，直接保存fwrite(pFrame->data[0], 1, pFrame->nb_samples * pCodecCtx->channels * 2, pFile);}}}av_free_packet(packet);}swr_free(&au_convert_ctx);fclose(pFile);av_free(out_buffer);avcodec_close(pCodecCtx);avformat_close_input(&pFormatCtx);return 0;
}int main() {DecodedAudioFile("test.mp3");DecodedAudioFile("test.wav");return 0;
}

技術(shù)細(xì)節(jié)

WAV 文件通常是未壓縮的 PCM 音頻，解碼的步驟與壓縮格式（如 MP3）有所不同。在解碼 WAV 文件時(shí)，解碼器可能會直接輸出 PCM 數(shù)據(jù)，而不是像 MP3 那樣的壓縮數(shù)據(jù)。對于 WAV 文件，如果格式是 AV_SAMPLE_FMT_S16，則不需要使用 swr_convert，因?yàn)橐纛l數(shù)據(jù)已經(jīng)是 PCM 格式，可以直接寫入文件。例如上述代碼中，對文件格式的檢查：

// ...
// 如果輸入文件格式不是AV_SAMPLE_FMT_S16才需要
if (pCodecCtx->sample_fmt != AV_SAMPLE_FMT_S16) {au_convert_ctx = swr_alloc();au_convert_ctx = swr_alloc_set_opts(au_convert_ctx, out_channel_layout, out_sample_fmt, out_sample_rate,in_channel_layout, pCodecCtx->sample_fmt, pCodecCtx->sample_rate, 0, NULL);swr_init(au_convert_ctx);
}
// ...
if (au_convert_ctx) {  // MP3文件格式通常是AV_SAMPLE_FMT_FLTP，要重采樣、格式轉(zhuǎn)換等swr_convert(au_convert_ctx, &out_buffer, MAX_AUDIO_FRAME_SIZE, (const uint8_t**)pFrame->data, pFrame->nb_samples);// Write PCMfwrite(out_buffer, 1, out_buffer_size, pFile);
} else {  // WAV文件格式通常是AV_SAMPLE_FMT_S16，與輸出文件一致，直接保存fwrite(pFrame->data[0], 1, pFrame->nb_samples * pCodecCtx->channels * 2, pFile);
}
// ...