MPEG音频编码

一、MPEG音频编码标准

基本思想

分析信号，去掉不能被感知的部分【声音压缩算法可以确立这种特性的模型来取消更多的冗余数据】

子带分析滤波器组：使信号具有高的时间分辨率【短暂冲击信号情况下，编码的声音信号具有足够高的质量】
FFT运算：使信号具有高的频率分辨率
比特分配：低频子带分配较多的位数【保护音调和共振峰的结构】；高频自带分配较少的位数【摩擦音和类似噪声的声音】

最核心的模块：心理声学模型

输出信掩比，和码率一起控制动态比特分配模块，输出每个子带的量化比特数，使整帧和每个子带噪掩比最小

main函数

int main (int argc, char **argv)
{
   
  typedef double SBS[2][3][SCALE_BLOCK][SBLIMIT];
  SBS *sb_sample;
  typedef double JSBS[3][SCALE_BLOCK][SBLIMIT];
  JSBS *j_sample;
  typedef double IN[2][HAN_SIZE];
  IN *win_que;
  typedef unsigned int SUB[2][3][SCALE_BLOCK][SBLIMIT];
  SUB *subband;
  frame_info frame;
  frame_header header;
  char original_file_name[MAX_NAME_SIZE];
  char encoded_file_name[MAX_NAME_SIZE];
  short **win_buf;
  static short buffer[2][1152];
  static unsigned int bit_alloc[2][SBLIMIT], scfsi[2][SBLIMIT];
  static unsigned int scalar[2][3][SBLIMIT], j_scale[3][SBLIMIT];
  static double smr[2][SBLIMIT], lgmin[2][SBLIMIT], max_sc[2][SBLIMIT];
  // FLOAT snr32[32];
  short sam[2][1344];  /* was [1056]; */
  int model, nch, error_protection;
  static unsigned int crc;
  int sb, ch, adb;
  unsigned long frameBits, sentBits = 0;
  unsigned long num_samples;
  int lg_frame;
  int i;
  /* Used to keep the SNR values for the fast/quick psy models */
  static FLOAT smrdef[2][32];
  static int psycount = 0;
  extern int minimum;
  time_t start_time, end_time;
  int total_time;
  sb_sample = (SBS *) mem_alloc (sizeof (SBS), "sb_sample");
  j_sample = (JSBS *) mem_alloc (sizeof (JSBS), "j_sample");
  win_que = (IN *) mem_alloc (sizeof (IN), "Win_que");
  subband = (SUB *) mem_alloc (sizeof (SUB), "subband");
  win_buf = (short **) mem_alloc (sizeof (short *) * 2, "win_buf");
  /* clear buffers */
  memset ((char *) buffer, 0, sizeof (buffer));
  memset ((char *) bit_alloc, 0, sizeof (bit_alloc));
  memset ((char *) scalar, 0, sizeof (scalar));
  memset ((char *) j_scale, 0, sizeof (j_scale));
  memset ((char *) scfsi, 0, sizeof (scfsi));
  memset ((char *) smr, 0, sizeof (smr));
  memset ((char *) lgmin, 0, sizeof (lgmin));
  memset ((char *) max_sc, 0, sizeof (max_sc));
  //memset ((char *) snr32, 0, sizeof (snr32));
  memset ((char *) sam, 0, sizeof (sam));
  global_init ();  
  header.extension = 0;
  frame.header = &header;
  frame.tab_num = -1;  /* no table loaded */
  frame.alloc = NULL;
  header.version = MPEG_AUDIO_ID; /* Default: MPEG-1 */
  total_time = 0;
  time(&start_time);     
  programName = argv[0];
  if (argc == 1)  /* no command-line args */
    short_usage ();
  else
    parse_args (argc, argv, &frame, &model, &num_samples, original_file_name,
  encoded_file_name);
  print_config (&frame, &model, original_file_name, encoded_file_name);
  /* this will load the alloc tables and do some other stuff */
  hdr_to_frps (&frame);
  nch = frame.nch;
  error_protection = header.error_protection;
  while (get_audio (musicin, buffer, num_samples, nch, &header) >