ffmpeg AAC转WAV格式(C/C++代码实现)

代码主要实现的功能是将一段aac的音频转换成wav

因为是新版的ffmpeg，所以使用了avcodec_decode_audio4解码音频，这样的话只能获取到一帧音频包，所以代码使用了 音频重采样swr_convert，将frame转换成buff

main.cpp

#include 
#include "audio.h"//这两个头文件在下面
#include "neaacdec.h"

extern "C"
{
#include 
#include 
#include 
}

#pragma comment (lib, "avcodec.lib")
#pragma comment (lib, "avformat.lib")
#pragma comment (lib, "avutil.lib")
#pragma comment (lib, "swresample.lib")

#define AVCODEC_MAX_AUDIO_FRAME_SIZE 19200

int main(int argc, char* argv[])
{
	AVFormatContext *in_fctx = nullptr;
	AVCodecContext *in_ast_cctx;
	AVCodec *in_ast_codec;
	AVPacket packet;
	audio_file *aufile;
	AVFrame *frame;
	int out_size = 0;
	int samples = 0;
	int ret = 0;
	int ast_idx = -1;
	int i, first_time = 1;
	char *filename = "F://Test.aac";//这个是文件输入的acc路径
	char *wavfile = "F://Ouput.wav";//这个是输出wav的文件路径
	ret = avformat_open_input(&in_fctx, filename, NULL, NULL);
	if (ret != 0) {
		printf("open input audio file[%s] fail", filename);
		return -1;
	}
	ret = avformat_find_stream_info(in_fctx, NULL);
	if (ret < 0) {
		printf("find stream in audio file[%s] fail", filename);
		return -1;
	}
	//这里我们假设，如果一个文件包含多个音频流，
	//只对第一个音频流做转码，而对于视频流则忽略
	for (i = 0; i<(int)in_fctx->nb_streams; ++i) {
		if (in_fctx->streams[i]->codec->codec_type == AVMEDIA_TYPE_AUDIO) {
			ast_idx = i;
			break;
		}
	}
	if (ast_idx == -1) {
		printf("there is not any audio stream in [%s]", filename);
		return 0;
	}
	else {
		printf("find audio stream in [%s]\n", filename);
	}
	in_ast_cctx = in_fctx->streams[ast_idx]->codec;
	in_ast_codec = avcodec_find_decoder(in_ast_cctx->codec_id);
	if (!in_ast_codec) {
		printf("find decoder for codec_id[%d] fail, file[%s]", in_ast_cctx->codec_id, filename);
		return -1;
	}
	ret = avcodec_open2(in_ast_cctx, in_ast_codec, NULL);
	if (ret >= 0) {
		printf("open codec[name:%s] for stream[idx:%d] of file[%s]\n", in_ast_codec->name, ast_idx, filename);
	}
	//如果需要谨慎的话，这些创建的都需要判断一下是否创建成功
	SwrContext *swrCtx = swr_alloc();

	//获取解码器
	AVCodecContext *codecCtx = in_fctx->streams[ast_idx]->codec;
	//输入的采样格式
	enum AVSampleFormat in_sample_fmt = codecCtx->sample_fmt;
	//输入采样率
	int in_sample_rate = codecCtx->sample_rate;
	//获取输入的声道布局
	uint64_t in_ch_layout = codecCtx->channel_layout;

	//输出采样格式16bit PCM
	enum AVSampleFormat out_sample_fmt = AV_SAMPLE_FMT_S16;
	//输出采样率
	int out_sample_rate = 16000;
	//输出的声道布局（立体声）
	uint64_t out_ch_layout = AV_CH_LAYOUT_MONO;

	swr_alloc_set_opts(swrCtx,
		out_ch_layout, out_sample_fmt, out_sample_rate,
		in_ch_layout, in_sample_fmt, in_sample_rate,
		0, NULL);
	//音频重采样初始化
	swr_init(swrCtx);

	frame = av_frame_alloc();
	if (!frame)
		return AVERROR(ENOMEM);
	//这buff用于存储解码后，解析frame得到的buff
	uint8_t *out_buffer = (uint8_t *)av_malloc(AVCODEC_MAX_AUDIO_FRAME_SIZE);
	if (!out_buffer)
		return AVERROR(ENOMEM);
	while (av_read_frame(in_fctx, &packet) >= 0) {
		ret = avcodec_decode_audio4(in_ast_cctx, frame, &out_size, &packet);
		if (first_time) {
			aufile = open_audio_file(wavfile, in_ast_cctx->sample_rate, in_ast_cctx->channels, FAAD_FMT_16BIT, OUTPUT_WAV, 0);
			first_time = 0;
		}
		swr_convert(swrCtx, &out_buffer, AVCODEC_MAX_AUDIO_FRAME_SIZE, (const uint8_t **)frame->data, frame->nb_samples);
		samples = in_ast_cctx->frame_size * in_ast_cctx->channels;
		write_audio_file(aufile, out_buffer, samples, 0);
		av_free_packet(&packet);
	}
	if (!first_time)
		close_audio_file(aufile);
	swr_free(&swrCtx);
	av_frame_free(&frame);
	avcodec_close(in_ast_cctx);
	avformat_close_input(&in_fctx);
	av_free(out_buffer);
	return 0;
}

audio.c

/*
** FAAD2 - Freeware Advanced Audio (AAC) Decoder including SBR decoding
** Copyright (C) 2003-2005 M. Bakker, Nero AG, http://www.nero.com
**  
** This program is free software; you can redistribute it and/or modify
** it under the terms of the GNU General Public License as published by
** the Free Software Foundation; either version 2 of the License, or
** (at your option) any later version.
** 
** This program is distributed in the hope that it will be useful,
** but WITHOUT ANY WARRANTY; without even the implied warranty of
** MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
** GNU General Public License for more details.
** 
** You should have received a copy of the GNU General Public License
** along with this program; if not, write to the Free Software 
** Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
**
** Any non-GPL usage of this software or parts of this software is strictly
** forbidden.
**
** The "appropriate copyright message" mentioned in section 2c of the GPLv2
** must read: "Code from FAAD2 is copyright (c) Nero AG, www.nero.com"
**
** Commercial non-GPL licensing of this software is possible.
** For more info contact Nero AG through [email protected].
**
** $Id: audio.c,v 1.29 2008/09/19 22:50:17 menno Exp $
**/

#ifdef _WIN32
#include 
#endif
#include 
#include 
#include 
#include 
#include "neaacdec.h"
#include "audio.h"


audio_file *open_audio_file(char *infile, int samplerate, int channels,
                            int outputFormat, int fileType, long channelMask)
{
    audio_file *aufile = (audio_file*)malloc(sizeof(audio_file));

    aufile->outputFormat = outputFormat;

    aufile->samplerate = samplerate;
    aufile->channels = channels;
    aufile->total_samples = 0;
    aufile->fileType = fileType;
    aufile->channelMask = channelMask;

    switch (outputFormat)
    {
    case FAAD_FMT_16BIT:
        aufile->bits_per_sample = 16;
        break;
    case FAAD_FMT_24BIT:
        aufile->bits_per_sample = 24;
        break;
    case FAAD_FMT_32BIT:
    case FAAD_FMT_FLOAT:
        aufile->bits_per_sample = 32;
        break;
    default:
        if (aufile) free(aufile);
        return NULL;
    }

    if(infile[0] == '-')
    {
#ifdef _WIN32
        setmode(fileno(stdout), O_BINARY);
#endif
        aufile->sndfile = stdout;
        aufile->toStdio = 1;
    } else {
        aufile->toStdio = 0;
        aufile->sndfile = fopen(infile, "wb");
    }

    if (aufile->sndfile == NULL)
    {
        if (aufile) free(aufile);
        return NULL;
    }

    if (aufile->fileType == OUTPUT_WAV)
    {
        if (aufile->channelMask)
            write_wav_extensible_header(aufile, aufile->channelMask);
        else
            write_wav_header(aufile);
    }

    return aufile;
}

int write_audio_file(audio_file *aufile, void *sample_buffer, int samples, int offset)
{
    char *buf = (char *)sample_buffer;
    switch (aufile->outputFormat)
    {
    case FAAD_FMT_16BIT:
        return write_audio_16bit(aufile, buf + offset*2, samples);
    case FAAD_FMT_24BIT:
        return write_audio_24bit(aufile, buf + offset*4, samples);
    case FAAD_FMT_32BIT:
        return write_audio_32bit(aufile, buf + offset*4, samples);
    case FAAD_FMT_FLOAT:
        return write_audio_float(aufile, buf + offset*4, samples);
    default:
        return 0;
    }

    return 0;
}

void close_audio_file(audio_file *aufile)
{
    if ((aufile->fileType == OUTPUT_WAV) && (aufile->toStdio == 0))
    {
        fseek(aufile->sndfile, 0, SEEK_SET);

        if (aufile->channelMask)
            write_wav_extensible_header(aufile, aufile->channelMask);
        else
            write_wav_header(aufile);
    }

    if (aufile->toStdio == 0)
        fclose(aufile->sndfile);

    if (aufile) free(aufile);
}

static int write_wav_header(audio_file *aufile)
{
    unsigned char header[44];
    unsigned char* p = header;
    unsigned int bytes = (aufile->bits_per_sample + 7) / 8;
    float data_size = (float)bytes * aufile->total_samples;
    unsigned long word32;

    *p++ = 'R'; *p++ = 'I'; *p++ = 'F'; *p++ = 'F';

    word32 = (data_size + (44 - 8) < (float)MAXWAVESIZE) ?
        (unsigned long)data_size + (44 - 8)  :  (unsigned long)MAXWAVESIZE;
    *p++ = (unsigned char)(word32 >>  0);
    *p++ = (unsigned char)(word32 >>  8);
    *p++ = (unsigned char)(word32 >> 16);
    *p++ = (unsigned char)(word32 >> 24);

    *p++ = 'W'; *p++ = 'A'; *p++ = 'V'; *p++ = 'E';

    *p++ = 'f'; *p++ = 'm'; *p++ = 't'; *p++ = ' ';

    *p++ = 0x10; *p++ = 0x00; *p++ = 0x00; *p++ = 0x00;

    if (aufile->outputFormat == FAAD_FMT_FLOAT)
    {
        *p++ = 0x03; *p++ = 0x00;
    } else {
        *p++ = 0x01; *p++ = 0x00;
    }

    *p++ = (unsigned char)(aufile->channels >> 0);
    *p++ = (unsigned char)(aufile->channels >> 8);

    word32 = (unsigned long)(aufile->samplerate + 0.5);
    *p++ = (unsigned char)(word32 >>  0);
    *p++ = (unsigned char)(word32 >>  8);
    *p++ = (unsigned char)(word32 >> 16);
    *p++ = (unsigned char)(word32 >> 24);

    word32 = aufile->samplerate * bytes * aufile->channels;
    *p++ = (unsigned char)(word32 >>  0);
    *p++ = (unsigned char)(word32 >>  8);
    *p++ = (unsigned char)(word32 >> 16);
    *p++ = (unsigned char)(word32 >> 24);

    word32 = bytes * aufile->channels;
    *p++ = (unsigned char)(word32 >>  0);
    *p++ = (unsigned char)(word32 >>  8);

    *p++ = (unsigned char)(aufile->bits_per_sample >> 0);
    *p++ = (unsigned char)(aufile->bits_per_sample >> 8);

    *p++ = 'd'; *p++ = 'a'; *p++ = 't'; *p++ = 'a';

    word32 = data_size < MAXWAVESIZE ?
        (unsigned long)data_size : (unsigned long)MAXWAVESIZE;
    *p++ = (unsigned char)(word32 >>  0);
    *p++ = (unsigned char)(word32 >>  8);
    *p++ = (unsigned char)(word32 >> 16);
    *p++ = (unsigned char)(word32 >> 24);

    return fwrite(header, sizeof(header), 1, aufile->sndfile);
}

static int write_wav_extensible_header(audio_file *aufile, long channelMask)
{
    unsigned char header[68];
    unsigned char* p = header;
    unsigned int bytes = (aufile->bits_per_sample + 7) / 8;
    float data_size = (float)bytes * aufile->total_samples;
    unsigned long word32;

    *p++ = 'R'; *p++ = 'I'; *p++ = 'F'; *p++ = 'F';

    word32 = (data_size + (68 - 8) < (float)MAXWAVESIZE) ?
        (unsigned long)data_size + (68 - 8)  :  (unsigned long)MAXWAVESIZE;
    *p++ = (unsigned char)(word32 >>  0);
    *p++ = (unsigned char)(word32 >>  8);
    *p++ = (unsigned char)(word32 >> 16);
    *p++ = (unsigned char)(word32 >> 24);

    *p++ = 'W'; *p++ = 'A'; *p++ = 'V'; *p++ = 'E';

    *p++ = 'f'; *p++ = 'm'; *p++ = 't'; *p++ = ' ';

    *p++ = /*0x10*/0x28; *p++ = 0x00; *p++ = 0x00; *p++ = 0x00;

    /* WAVE_FORMAT_EXTENSIBLE */
    *p++ = 0xFE; *p++ = 0xFF;

    *p++ = (unsigned char)(aufile->channels >> 0);
    *p++ = (unsigned char)(aufile->channels >> 8);

    word32 = (unsigned long)(aufile->samplerate + 0.5);
    *p++ = (unsigned char)(word32 >>  0);
    *p++ = (unsigned char)(word32 >>  8);
    *p++ = (unsigned char)(word32 >> 16);
    *p++ = (unsigned char)(word32 >> 24);

    word32 = aufile->samplerate * bytes * aufile->channels;
    *p++ = (unsigned char)(word32 >>  0);
    *p++ = (unsigned char)(word32 >>  8);
    *p++ = (unsigned char)(word32 >> 16);
    *p++ = (unsigned char)(word32 >> 24);

    word32 = bytes * aufile->channels;
    *p++ = (unsigned char)(word32 >>  0);
    *p++ = (unsigned char)(word32 >>  8);

    *p++ = (unsigned char)(aufile->bits_per_sample >> 0);
    *p++ = (unsigned char)(aufile->bits_per_sample >> 8);

    /* cbSize */
    *p++ = (unsigned char)(22);
    *p++ = (unsigned char)(0);

    /* WAVEFORMATEXTENSIBLE */

    /* wValidBitsPerSample */
    *p++ = (unsigned char)(aufile->bits_per_sample >> 0);
    *p++ = (unsigned char)(aufile->bits_per_sample >> 8);

    /* dwChannelMask */
    word32 = channelMask;
    *p++ = (unsigned char)(word32 >>  0);
    *p++ = (unsigned char)(word32 >>  8);
    *p++ = (unsigned char)(word32 >> 16);
    *p++ = (unsigned char)(word32 >> 24);

    /* SubFormat */
    if (aufile->outputFormat == FAAD_FMT_FLOAT)
    {
        /* KSDATAFORMAT_SUBTYPE_IEEE_FLOAT: 00000003-0000-0010-8000-00aa00389b71 */
        *p++ = 0x03;
        *p++ = 0x00;
        *p++ = 0x00;
        *p++ = 0x00;
        *p++ = 0x00; *p++ = 0x00; *p++ = 0x10; *p++ = 0x00; *p++ = 0x80; *p++ = 0x00;
        *p++ = 0x00; *p++ = 0xaa; *p++ = 0x00; *p++ = 0x38; *p++ = 0x9b; *p++ = 0x71;
    } else {
        /* KSDATAFORMAT_SUBTYPE_PCM: 00000001-0000-0010-8000-00aa00389b71 */
        *p++ = 0x01;
        *p++ = 0x00;
        *p++ = 0x00;
        *p++ = 0x00;
        *p++ = 0x00; *p++ = 0x00; *p++ = 0x10; *p++ = 0x00; *p++ = 0x80; *p++ = 0x00;
        *p++ = 0x00; *p++ = 0xaa; *p++ = 0x00; *p++ = 0x38; *p++ = 0x9b; *p++ = 0x71;
    }

    /* end WAVEFORMATEXTENSIBLE */

    *p++ = 'd'; *p++ = 'a'; *p++ = 't'; *p++ = 'a';

    word32 = data_size < MAXWAVESIZE ?
        (unsigned long)data_size : (unsigned long)MAXWAVESIZE;
    *p++ = (unsigned char)(word32 >>  0);
    *p++ = (unsigned char)(word32 >>  8);
    *p++ = (unsigned char)(word32 >> 16);
    *p++ = (unsigned char)(word32 >> 24);

    return fwrite(header, sizeof(header), 1, aufile->sndfile);
}

static int write_audio_16bit(audio_file *aufile, void *sample_buffer,
                             unsigned int samples)
{
    int ret;
    unsigned int i;
    short *sample_buffer16 = (short*)sample_buffer;
    char *data = (char*)malloc(samples*aufile->bits_per_sample*sizeof(char)/8);

    aufile->total_samples += samples;

    if (aufile->channels == 6 && aufile->channelMask)
    {
        for (i = 0; i < samples; i += aufile->channels)
        {
            short r1, r2, r3, r4, r5, r6;
            r1 = sample_buffer16[i];
            r2 = sample_buffer16[i+1];
            r3 = sample_buffer16[i+2];
            r4 = sample_buffer16[i+3];
            r5 = sample_buffer16[i+4];
            r6 = sample_buffer16[i+5];
            sample_buffer16[i] = r2;
            sample_buffer16[i+1] = r3;
            sample_buffer16[i+2] = r1;
            sample_buffer16[i+3] = r6;
            sample_buffer16[i+4] = r4;
            sample_buffer16[i+5] = r5;
        }
    }

    for (i = 0; i < samples; i++)
    {
        data[i*2] = (char)(sample_buffer16[i] & 0xFF);
        data[i*2+1] = (char)((sample_buffer16[i] >> 8) & 0xFF);
    }

    ret = fwrite(data, samples, aufile->bits_per_sample/8, aufile->sndfile);

    if (data) free(data);

    return ret;
}

static int write_audio_24bit(audio_file *aufile, void *sample_buffer,
                             unsigned int samples)
{
    int ret;
    unsigned int i;
    long *sample_buffer24 = (long*)sample_buffer;
    char *data = (char*)malloc(samples*aufile->bits_per_sample*sizeof(char)/8);

    aufile->total_samples += samples;

    if (aufile->channels == 6 && aufile->channelMask)
    {
        for (i = 0; i < samples; i += aufile->channels)
        {
            long r1, r2, r3, r4, r5, r6;
            r1 = sample_buffer24[i];
            r2 = sample_buffer24[i+1];
            r3 = sample_buffer24[i+2];
            r4 = sample_buffer24[i+3];
            r5 = sample_buffer24[i+4];
            r6 = sample_buffer24[i+5];
            sample_buffer24[i] = r2;
            sample_buffer24[i+1] = r3;
            sample_buffer24[i+2] = r1;
            sample_buffer24[i+3] = r6;
            sample_buffer24[i+4] = r4;
            sample_buffer24[i+5] = r5;
        }
    }

    for (i = 0; i < samples; i++)
    {
        data[i*3] = (char)(sample_buffer24[i] & 0xFF);
        data[i*3+1] = (char)((sample_buffer24[i] >> 8) & 0xFF);
        data[i*3+2] = (char)((sample_buffer24[i] >> 16) & 0xFF);
    }

    ret = fwrite(data, samples, aufile->bits_per_sample/8, aufile->sndfile);

    if (data) free(data);

    return ret;
}

static int write_audio_32bit(audio_file *aufile, void *sample_buffer,
                             unsigned int samples)
{
    int ret;
    unsigned int i;
    long *sample_buffer32 = (long*)sample_buffer;
    char *data = (char*)malloc(samples*aufile->bits_per_sample*sizeof(char)/8);

    aufile->total_samples += samples;

    if (aufile->channels == 6 && aufile->channelMask)
    {
        for (i = 0; i < samples; i += aufile->channels)
        {
            long r1, r2, r3, r4, r5, r6;
            r1 = sample_buffer32[i];
            r2 = sample_buffer32[i+1];
            r3 = sample_buffer32[i+2];
            r4 = sample_buffer32[i+3];
            r5 = sample_buffer32[i+4];
            r6 = sample_buffer32[i+5];
            sample_buffer32[i] = r2;
            sample_buffer32[i+1] = r3;
            sample_buffer32[i+2] = r1;
            sample_buffer32[i+3] = r6;
            sample_buffer32[i+4] = r4;
            sample_buffer32[i+5] = r5;
        }
    }

    for (i = 0; i < samples; i++)
    {
        data[i*4] = (char)(sample_buffer32[i] & 0xFF);
        data[i*4+1] = (char)((sample_buffer32[i] >> 8) & 0xFF);
        data[i*4+2] = (char)((sample_buffer32[i] >> 16) & 0xFF);
        data[i*4+3] = (char)((sample_buffer32[i] >> 24) & 0xFF);
    }

    ret = fwrite(data, samples, aufile->bits_per_sample/8, aufile->sndfile);

    if (data) free(data);

    return ret;
}

static int write_audio_float(audio_file *aufile, void *sample_buffer,
                             unsigned int samples)
{
    int ret;
    unsigned int i;
    float *sample_buffer_f = (float*)sample_buffer;
    unsigned char *data = (unsigned char *)malloc(samples*aufile->bits_per_sample*sizeof(char)/8);

    aufile->total_samples += samples;

    if (aufile->channels == 6 && aufile->channelMask)
    {
        for (i = 0; i < samples; i += aufile->channels)
        {
            float r1, r2, r3, r4, r5, r6;
            r1 = sample_buffer_f[i];
            r2 = sample_buffer_f[i+1];
            r3 = sample_buffer_f[i+2];
            r4 = sample_buffer_f[i+3];
            r5 = sample_buffer_f[i+4];
            r6 = sample_buffer_f[i+5];
            sample_buffer_f[i] = r2;
            sample_buffer_f[i+1] = r3;
            sample_buffer_f[i+2] = r1;
            sample_buffer_f[i+3] = r6;
            sample_buffer_f[i+4] = r4;
            sample_buffer_f[i+5] = r5;
        }
    }

    for (i = 0; i < samples; i++)
    {
        int exponent, mantissa, negative = 0 ;
        float in = sample_buffer_f[i];

        data[i*4] = 0; data[i*4+1] = 0; data[i*4+2] = 0; data[i*4+3] = 0;
        if (in == 0.0)
            continue;

        if (in < 0.0)
        {
            in *= -1.0;
            negative = 1;
        }
        in = (float)frexp(in, &exponent);
        exponent += 126;
        in *= (float)0x1000000;
        mantissa = (((int)in) & 0x7FFFFF);

        if (negative)
            data[i*4+3] |= 0x80;

        if (exponent & 0x01)
            data[i*4+2] |= 0x80;

        data[i*4] = mantissa & 0xFF;
        data[i*4+1] = (mantissa >> 8) & 0xFF;
        data[i*4+2] |= (mantissa >> 16) & 0x7F;
        data[i*4+3] |= (exponent >> 1) & 0x7F;
    }

    ret = fwrite(data, samples, aufile->bits_per_sample/8, aufile->sndfile);

    if (data) free(data);

    return ret;
}

audio.h

/*
** FAAD2 - Freeware Advanced Audio (AAC) Decoder including SBR decoding
** Copyright (C) 2003-2005 M. Bakker, Nero AG, http://www.nero.com
**  
** This program is free software; you can redistribute it and/or modify
** it under the terms of the GNU General Public License as published by
** the Free Software Foundation; either version 2 of the License, or
** (at your option) any later version.
** 
** This program is distributed in the hope that it will be useful,
** but WITHOUT ANY WARRANTY; without even the implied warranty of
** MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
** GNU General Public License for more details.
** 
** You should have received a copy of the GNU General Public License
** along with this program; if not, write to the Free Software 
** Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
**
** Any non-GPL usage of this software or parts of this software is strictly
** forbidden.
**
** The "appropriate copyright message" mentioned in section 2c of the GPLv2
** must read: "Code from FAAD2 is copyright (c) Nero AG, www.nero.com"
**
** Commercial non-GPL licensing of this software is possible.
** For more info contact Nero AG through [email protected].
**
** $Id: audio.h,v 1.19 2007/11/01 12:33:29 menno Exp $
**/

#ifndef AUDIO_H_INCLUDED
#define AUDIO_H_INCLUDED

#ifdef __cplusplus
extern "C" {
#endif

#define MAXWAVESIZE     4294967040LU

#define OUTPUT_WAV 1
#define OUTPUT_RAW 2

typedef struct
{
    int toStdio;
    int outputFormat;
    FILE *sndfile;
    unsigned int fileType;
    unsigned long samplerate;
    unsigned int bits_per_sample;
    unsigned int channels;
    unsigned long total_samples;
    long channelMask;
} audio_file;

audio_file *open_audio_file(char *infile, int samplerate, int channels,
                            int outputFormat, int fileType, long channelMask);
int write_audio_file(audio_file *aufile, void *sample_buffer, int samples, int offset);
void close_audio_file(audio_file *aufile);
static int write_wav_header(audio_file *aufile);
static int write_wav_extensible_header(audio_file *aufile, long channelMask);
static int write_audio_16bit(audio_file *aufile, void *sample_buffer,
                             unsigned int samples);
static int write_audio_24bit(audio_file *aufile, void *sample_buffer,
                             unsigned int samples);
static int write_audio_32bit(audio_file *aufile, void *sample_buffer,
                             unsigned int samples);
static int write_audio_float(audio_file *aufile, void *sample_buffer,
                             unsigned int samples);


#ifdef __cplusplus
}
#endif
#endif

neaacdec.h

/*
** FAAD2 - Freeware Advanced Audio (AAC) Decoder including SBR decoding
** Copyright (C) 2003-2005 M. Bakker, Nero AG, http://www.nero.com
**  
** This program is free software; you can redistribute it and/or modify
** it under the terms of the GNU General Public License as published by
** the Free Software Foundation; either version 2 of the License, or
** (at your option) any later version.
** 
** This program is distributed in the hope that it will be useful,
** but WITHOUT ANY WARRANTY; without even the implied warranty of
** MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
** GNU General Public License for more details.
** 
** You should have received a copy of the GNU General Public License
** along with this program; if not, write to the Free Software 
** Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
**
** Any non-GPL usage of this software or parts of this software is strictly
** forbidden.
**
** The "appropriate copyright message" mentioned in section 2c of the GPLv2
** must read: "Code from FAAD2 is copyright (c) Nero AG, www.nero.com"
**
** Commercial non-GPL licensing of this software is possible.
** For more info contact Nero AG through [email protected].
**
** $Id: neaacdec.h,v 1.13 2009/01/26 23:51:15 menno Exp $
**/

#ifndef __NEAACDEC_H__
#define __NEAACDEC_H__

#ifdef __cplusplus
extern "C" {
#endif /* __cplusplus */


#if 1
/* MACROS FOR BACKWARDS COMPATIBILITY */
/* structs */
#define faacDecHandle                  NeAACDecHandle
#define faacDecConfiguration           NeAACDecConfiguration
#define faacDecConfigurationPtr        NeAACDecConfigurationPtr
#define faacDecFrameInfo               NeAACDecFrameInfo
/* functions */
#define faacDecGetErrorMessage         NeAACDecGetErrorMessage
#define faacDecSetConfiguration        NeAACDecSetConfiguration
#define faacDecGetCurrentConfiguration NeAACDecGetCurrentConfiguration
#define faacDecInit                    NeAACDecInit
#define faacDecInit2                   NeAACDecInit2
#define faacDecInitDRM                 NeAACDecInitDRM
#define faacDecPostSeekReset           NeAACDecPostSeekReset
#define faacDecOpen                    NeAACDecOpen
#define faacDecClose                   NeAACDecClose
#define faacDecDecode                  NeAACDecDecode
#define AudioSpecificConfig            NeAACDecAudioSpecificConfig
#endif


#ifdef _WIN32
  #pragma pack(push, 8)
  #ifndef NEAACDECAPI
    #define NEAACDECAPI __cdecl
  #endif
#else
  #ifndef NEAACDECAPI
    #define NEAACDECAPI
  #endif
#endif

#define FAAD2_VERSION "2.7"

/* object types for AAC */
#define MAIN       1
#define LC         2
#define SSR        3
#define LTP        4
#define HE_AAC     5
#define ER_LC     17
#define ER_LTP    19
#define LD        23
#define DRM_ER_LC 27 /* special object type for DRM */

/* header types */
#define RAW        0
#define ADIF       1
#define ADTS       2
#define LATM       3

/* SBR signalling */
#define NO_SBR           0
#define SBR_UPSAMPLED    1
#define SBR_DOWNSAMPLED  2
#define NO_SBR_UPSAMPLED 3

/* library output formats */
#define FAAD_FMT_16BIT  1
#define FAAD_FMT_24BIT  2
#define FAAD_FMT_32BIT  3
#define FAAD_FMT_FLOAT  4
#define FAAD_FMT_FIXED  FAAD_FMT_FLOAT
#define FAAD_FMT_DOUBLE 5

/* Capabilities */
#define LC_DEC_CAP           (1<<0) /* Can decode LC */
#define MAIN_DEC_CAP         (1<<1) /* Can decode MAIN */
#define LTP_DEC_CAP          (1<<2) /* Can decode LTP */
#define LD_DEC_CAP           (1<<3) /* Can decode LD */
#define ERROR_RESILIENCE_CAP (1<<4) /* Can decode ER */
#define FIXED_POINT_CAP      (1<<5) /* Fixed point */

/* Channel definitions */
#define FRONT_CHANNEL_CENTER (1)
#define FRONT_CHANNEL_LEFT   (2)
#define FRONT_CHANNEL_RIGHT  (3)
#define SIDE_CHANNEL_LEFT    (4)
#define SIDE_CHANNEL_RIGHT   (5)
#define BACK_CHANNEL_LEFT    (6)
#define BACK_CHANNEL_RIGHT   (7)
#define BACK_CHANNEL_CENTER  (8)
#define LFE_CHANNEL          (9)
#define UNKNOWN_CHANNEL      (0)

/* DRM channel definitions */
#define DRMCH_MONO          1
#define DRMCH_STEREO        2
#define DRMCH_SBR_MONO      3
#define DRMCH_SBR_STEREO    4
#define DRMCH_SBR_PS_STEREO 5


/* A decode call can eat up to FAAD_MIN_STREAMSIZE bytes per decoded channel,
   so at least so much bytes per channel should be available in this stream */
#define FAAD_MIN_STREAMSIZE 768 /* 6144 bits/channel */


typedef void *NeAACDecHandle;

typedef struct mp4AudioSpecificConfig
{
    /* Audio Specific Info */
    unsigned char objectTypeIndex;
    unsigned char samplingFrequencyIndex;
    unsigned long samplingFrequency;
    unsigned char channelsConfiguration;

    /* GA Specific Info */
    unsigned char frameLengthFlag;
    unsigned char dependsOnCoreCoder;
    unsigned short coreCoderDelay;
    unsigned char extensionFlag;
    unsigned char aacSectionDataResilienceFlag;
    unsigned char aacScalefactorDataResilienceFlag;
    unsigned char aacSpectralDataResilienceFlag;
    unsigned char epConfig;

    char sbr_present_flag;
    char forceUpSampling;
    char downSampledSBR;
} mp4AudioSpecificConfig;

typedef struct NeAACDecConfiguration
{
    unsigned char defObjectType;
    unsigned long defSampleRate;
    unsigned char outputFormat;
    unsigned char downMatrix;
    unsigned char useOldADTSFormat;
    unsigned char dontUpSampleImplicitSBR;
} NeAACDecConfiguration, *NeAACDecConfigurationPtr;

typedef struct NeAACDecFrameInfo
{
    unsigned long bytesconsumed;
    unsigned long samples;
    unsigned char channels;
    unsigned char error;
    unsigned long samplerate;

    /* SBR: 0: off, 1: on; upsample, 2: on; downsampled, 3: off; upsampled */
    unsigned char sbr;

    /* MPEG-4 ObjectType */
    unsigned char object_type;

    /* AAC header type; MP4 will be signalled as RAW also */
    unsigned char header_type;

    /* multichannel configuration */
    unsigned char num_front_channels;
    unsigned char num_side_channels;
    unsigned char num_back_channels;
    unsigned char num_lfe_channels;
    unsigned char channel_position[64];

    /* PS: 0: off, 1: on */
    unsigned char ps;
} NeAACDecFrameInfo;

char* NEAACDECAPI NeAACDecGetErrorMessage(unsigned char errcode);

unsigned long NEAACDECAPI NeAACDecGetCapabilities(void);

NeAACDecHandle NEAACDECAPI NeAACDecOpen(void);

NeAACDecConfigurationPtr NEAACDECAPI NeAACDecGetCurrentConfiguration(NeAACDecHandle hDecoder);

unsigned char NEAACDECAPI NeAACDecSetConfiguration(NeAACDecHandle hDecoder,
                                                   NeAACDecConfigurationPtr config);

/* Init the library based on info from the AAC file (ADTS/ADIF) */
long NEAACDECAPI NeAACDecInit(NeAACDecHandle hDecoder,
                              unsigned char *buffer,
                              unsigned long buffer_size,
                              unsigned long *samplerate,
                              unsigned char *channels);

/* Init the library using a DecoderSpecificInfo */
char NEAACDECAPI NeAACDecInit2(NeAACDecHandle hDecoder,
                               unsigned char *pBuffer,
                               unsigned long SizeOfDecoderSpecificInfo,
                               unsigned long *samplerate,
                               unsigned char *channels);

/* Init the library for DRM */
char NEAACDECAPI NeAACDecInitDRM(NeAACDecHandle *hDecoder, unsigned long samplerate,
                                 unsigned char channels);

void NEAACDECAPI NeAACDecPostSeekReset(NeAACDecHandle hDecoder, long frame);

void NEAACDECAPI NeAACDecClose(NeAACDecHandle hDecoder);

void* NEAACDECAPI NeAACDecDecode(NeAACDecHandle hDecoder,
                                 NeAACDecFrameInfo *hInfo,
                                 unsigned char *buffer,
                                 unsigned long buffer_size);

void* NEAACDECAPI NeAACDecDecode2(NeAACDecHandle hDecoder,
                                  NeAACDecFrameInfo *hInfo,
                                  unsigned char *buffer,
                                  unsigned long buffer_size,
                                  void **sample_buffer,
                                  unsigned long sample_buffer_size);

char NEAACDECAPI NeAACDecAudioSpecificConfig(unsigned char *pBuffer,
                                             unsigned long buffer_size,
                                             mp4AudioSpecificConfig *mp4ASC);

#ifdef _WIN32
  #pragma pack(pop)
#endif

#ifdef __cplusplus
}
#endif /* __cplusplus */

#endif

如果懒得找ffmpeg库资源的话，这里有一个编好的资源,代码都一样的就是多了ffmpeg资源，能编译
使用VS2015（x64）可以直接编译通过，ffmpeg 4.3 版本
资源连接：https://download.csdn.net/download/qq_36351159/86890587

因下载的代码使用的ffmpeg版本是旧的，导致新版的不能使用，调整一下代码，确认能正常使用，便于需要使用的人参考(主要是没有CSND的下载B)，使用的音频解码接口是avcodec_decode_audio2.这样的话不需要音频重采样，可以获取一个buff