ffmpeg 音频解码

FFmpeg是一个开源的音视频处理库，可以用来解码、编码、转码、播放等等。它支持多种格式的音频文件解码，包括但不限于mp3、aac、wav等。

使用FFmpeg解码音频文件通常需要以下步骤：

1. 初始化FFmpeg库，包括注册解码器、分配AVFormatContext、打开输入文件等操作。

2. 查找音频解码器并打开音频解码器。

3. 分配AVPacket和AVFrame结构体用于存储音频数据。

4. 循环读取音频数据流，将读取的数据存储在AVPacket结构体中。

5. 将AVPacket结构体中的音频数据解码为AVFrame结构体。

6. 对AVFrame进行后续处理，如音频重采样、格式转换等。

7. 释放资源，包括关闭输入文件、释放AVPacket和AVFrame结构体等。

具体实现可以参考FFmpeg的相关文档和示例代码。

相关问题

ffmpeg音频解码av_frame_alloc

av_frame_alloc函数用于为AVFrame结构体分配内存空间，AVFrame结构体用于存储解码后的音视频数据。在音频解码中，可以通过调用该函数为AVFrame结构体分配内存空间，然后将解码后的音频数据存储到该结构体中，最后再进行后续的处理操作。

具体使用方法如下：

AVFrame *frame = av_frame_alloc();
if (!frame) {
    // 内存分配失败处理
}

其中，AVFrame结构体的定义如下：

typedef struct AVFrame {
    /**
     * pointers to the data planes/channels.
     * This might be different from the first allocated byte
     */
    uint8_t *data[AV_NUM_DATA_POINTERS];
    /**
     * For video, size in bytes of each picture line.
     * For audio, size in bytes of each plane.
     */
    int linesize[AV_NUM_DATA_POINTERS];
    /**
     * pointers to the start of each picture line.
     * This is used for both video and audio.
     */
    uint8_t **extended_data;
    /**
     * width and height of the video frame
     */
    int width, height;
    /**
     * number of audio samples (per channel) described by this frame
     */
    int nb_samples;
    /**
     * format of the frame, -1 if unknown or unset
     * Values correspond to enum AVPixelFormat for video frames,
     * enum AVSampleFormat for audio)
     */
    int format;
    /**
     * 1 -> keyframe, 0-> not
     */
    int key_frame;
    /**
     * Picture type of the frame.
     */
    enum AVPictureType pict_type;
    /**
     * Quality (between 1 (good) and FF_LAMBDA_MAX (bad)).
     */
    int quality;
    /**
     * for AV_PIX_FMT_*_BE formats, linesize alignment
     */
    int64_t     best_effort_timestamp;
    /**
     * PTS copied from the AVPacket that was decoded to produce this frame.
     */
    int64_t     pkt_pts;
    /**
     * DTS copied from the AVPacket that triggered returning this frame.
     */
    int64_t     pkt_dts;
    /**
     * duration of the corresponding packet, expressed in
     * AVStream->time_base units, 0 if unknown.
     */
    int64_t     pkt_duration;
    uint64_t    metadata;
    int         decode_error_flags;
    /**
     * number of audio channels
     */
    int         channels;
    /**
     * size of the corresponding packet containing the compressed
     * frame. It is set to a negative value if unknown.
     */
    int         pkt_size;
    /**
     * data type
     */
    enum AVSampleFormat  sample_fmt;
    /**
     * presentation timestamp in timebase units
     * (time when frame should be shown to user)
     * If AV_NOPTS_VALUE then frame_rate = 1/time_base will be assumed.
     */
    int64_t     pts;
    /**
     * reordered PTS from the last AVPacket that has been input into the decoder
     */
    int64_t     best_effort_timestamp;
    /**
     * sample aspect ratio (0 if unknown)
     * - encoding: Set by user.
     * - decoding: Set by libavcodec.
     */
    AVRational  sample_aspect_ratio;
    /**
     * motion vector table, used for MPEG1/2/4 and H.263 decoding
     */
    struct AVPanScan *pan_scan;
    /**
     * macroblock decision mode
     */
    int         coded_picture_number;
    int         display_picture_number;
    /**
     * quality (between 1 (good) and FF_LAMBDA_MAX (bad))
     */
    int         quality;
    /**
     * buffer age (1->was last buffer and dint change, 2->..., ...)
     */
    int         age;
    /**
     * is this picture used as reference
     */
    int reference;
    /**
     * QP table
     */
    int8_t *qp_table_buf;
    /**
     * QP store stride
     */
    int     qp_table_linesize;
    /**
     * QP values for each macroblock
     */
    int8_t *qp_table;
    /**
     * For hwaccel-format frames, this should be a reference to the
     * AVHWFramesContext describing the frame.
     * For normal-format frames, this should be NULL.
     */
    AVBufferRef *hw_frames_ctx;
} AVFrame;

需要注意的是，AVFrame结构体中的成员变量很多，具体使用哪些成员变量取决于具体的应用场景和需求。

ffmpeg音频解码成wav格式实现代码

以下是使用FFmpeg将音频解码为WAV格式的示例代码：

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <stdint.h>
#include <inttypes.h>
#include <math.h>

#include <libavutil/channel_layout.h>
#include <libavutil/common.h>
#include <libavutil/frame.h>
#include <libavutil/opt.h>
#include <libavutil/samplefmt.h>
#include <libavutil/timestamp.h>

#include <libavcodec/avcodec.h>
#include <libavformat/avformat.h>
#include <libswresample/swresample.h>

#define AUDIO_INBUF_SIZE 20480
#define AUDIO_REFILL_THRESH 4096

static void decode(AVCodecContext *dec_ctx, AVPacket *pkt, AVFrame *frame,
                   FILE *outfile)
{
    int i, ch;
    int ret, data_size;

    /* send the packet with the compressed data to the decoder */
    ret = avcodec_send_packet(dec_ctx, pkt);
    if (ret < 0) {
        fprintf(stderr, "Error submitting the packet to the decoder\n");
        exit(1);
    }

    /* read all the output frames (in general there may be any number of them) */
    while (ret >= 0) {
        ret = avcodec_receive_frame(dec_ctx, frame);
        if (ret == AVERROR(EAGAIN) || ret == AVERROR_EOF)
            return;
        else if (ret < 0) {
            fprintf(stderr, "Error during decoding\n");
            exit(1);
        }

        data_size = av_get_bytes_per_sample(dec_ctx->sample_fmt);
        if (data_size < 0) {
            /* This should not occur, checking just for paranoia */
            fprintf(stderr, "Failed to calculate data size\n");
            exit(1);
        }
        for (i = 0; i < frame->nb_samples; i++)
            for (ch = 0; ch < dec_ctx->channels; ch++)
                fwrite(frame->data[ch] + data_size*i, 1, data_size, outfile);
    }
}

int main(int argc, char **argv)
{
    AVCodec *codec;
    AVCodecContext *codec_ctx = NULL;
    AVCodecParserContext *parser = NULL;
    AVFormatContext *fmt_ctx = NULL;
    AVPacket *pkt = NULL;
    AVFrame *frame = NULL;
    uint8_t inbuf[AUDIO_INBUF_SIZE + AV_INPUT_BUFFER_PADDING_SIZE];
    int inbuf_size;
    int64_t pts;
    int ret;
    int i;

    if (argc <= 1) {
        fprintf(stderr, "Usage: %s <input file>\n", argv[0]);
        exit(0);
    }

    /* register all the codecs */
    av_register_all();

    /* allocate the input buffer */
    pkt = av_packet_alloc();
    if (!pkt) {
        fprintf(stderr, "Failed to allocate packet\n");
        exit(1);
    }

    /* open the input file */
    ret = avformat_open_input(&fmt_ctx, argv[1], NULL, NULL);
    if (ret < 0) {
        fprintf(stderr, "Cannot open input file '%s'\n", argv[1]);
        exit(1);
    }

    /* retrieve stream information */
    ret = avformat_find_stream_info(fmt_ctx, NULL);
    if (ret < 0) {
        fprintf(stderr, "Cannot find stream information\n");
        exit(1);
    }

    /* select the audio stream */
    ret = av_find_best_stream(fmt_ctx, AVMEDIA_TYPE_AUDIO, -1, -1, &codec, 0);
    if (ret < 0) {
        fprintf(stderr, "Cannot find an audio stream in the input file\n");
        exit(1);
    }
    int audio_stream_idx = ret;

    /* allocate the codec context */
    codec_ctx = avcodec_alloc_context3(codec);
    if (!codec_ctx) {
        fprintf(stderr, "Failed to allocate codec context\n");
        exit(1);
    }

    /* fill the codec context based on the stream information */
    ret = avcodec_parameters_to_context(codec_ctx, fmt_ctx->streams[audio_stream_idx]->codecpar);
    if (ret < 0) {
        fprintf(stderr, "Failed to copy codec parameters to codec context\n");
        exit(1);
    }

    /* init the codec context */
    ret = avcodec_open2(codec_ctx, codec, NULL);
    if (ret < 0) {
        fprintf(stderr, "Failed to open codec\n");
        exit(1);
    }

    /* allocate the frame */
    frame = av_frame_alloc();
    if (!frame) {
        fprintf(stderr, "Failed to allocate frame\n");
        exit(1);
    }

    /* init the packet parser */
    parser = av_parser_init(codec_ctx->codec_id);
    if (!parser) {
        fprintf(stderr, "Failed to init packet parser\n");
        exit(1);
    }

    /* open the output file */
    FILE *outfile = fopen("output.wav", "wb");
    if (!outfile) {
        fprintf(stderr, "Failed to open output file\n");
        exit(1);
    }

    /* read packets from the input file */
    while (1) {
        /* get more data from the input file */
        ret = av_read_frame(fmt_ctx, pkt);
        if (ret < 0)
            break;

        /* if this is not the audio stream, ignore it */
        if (pkt->stream_index != audio_stream_idx) {
            av_packet_unref(pkt);
            continue;
        }

        /* send the packet to the parser */
        inbuf_size = pkt->size;
        memcpy(inbuf, pkt->data, inbuf_size);
        while (inbuf_size > 0) {
            ret = av_parser_parse2(parser, codec_ctx, &pkt->data, &pkt->size,
                                   inbuf, inbuf_size, AV_NOPTS_VALUE, AV_NOPTS_VALUE, 0);
            if (ret < 0) {
                fprintf(stderr, "Error while parsing\n");
                exit(1);
            }
            inbuf += ret;
            inbuf_size -= ret;

            /* if we have a complete frame, decode it */
            if (pkt->size > 0) {
                decode(codec_ctx, pkt, frame, outfile);
            }
        }

        av_packet_unref(pkt);
    }

    /* flush the decoder */
    decode(codec_ctx, NULL, frame, outfile);

    /* close the output file */
    fclose(outfile);

    /* free the resources */
    av_parser_close(parser);
    avcodec_free_context(&codec_ctx);
    av_frame_free(&frame);
    av_packet_free(&pkt);
    avformat_close_input(&fmt_ctx);

    return 0;
}

这个程序使用FFmpeg库将音频文件解码为WAV格式，并将解码后的数据写入到一个输出文件中。你可以将输入文件的路径作为程序的参数来运行它。