文章目录
一、实验内容
1. 输出音频的采样率和目标码率
选择三个不同特性的音频文件：噪声、音乐、混合噪声和音乐。输出它们的音频的采样率和目标码率。
2. 分析某一数据帧
输出该帧所分配的比特数、该帧的比例因子、该帧的比特分配结果。
二、实验思路
MPEG-1的Layer II的编码器框图
第一条线是时域分析，将PCM码流分解成32个子带,对其分别进行编码处理后再合成为全频带信号。
第二条线是频域分析，依据人耳听觉阈值和听觉掩蔽特性建立，分析听阈曲线，保证满足人耳听觉感受的前提下，减少码率，建立心理声学模型。
多相滤波器组(Polyphase Filter Bank)
将PCM样本变换到32个子带的频域信号，如果输入的采样频率为48kHz，那么子带的频率宽度为48/（2*32）=0.75Hz
比例因子的选择和编码
对各个子带每12个样点进行一次比例因子的计算，先找出12个样点中绝对值的最大值。查比例因子表中比这个最大值大的最小值作为比例因子。用6bit表示。
MPEG-2的一帧对应36个子带样值，是MPEG-1的3倍，原则上要传3个比例因子，但为了降低比例因子的传输码率，采用了人耳时域掩蔽特性的编码策略，每个块（12个样点）找出一个最大的作为比例因子，然后比较三个块的比例因子，如果一个比例因子和下一个只有很小的差别，就只传送大的一个，这种情况对于稳态信号经常出现。。
1024点FFT
引入FFT补偿频率分辨率不足的问题。
心理声学模型(Psychoacoustic Model)
计算信号中不可听觉感知的部分，计算噪声遮蔽效应
听觉系统中存在一个听觉阈值电平，低于这个电平的声音信号就听不到，听觉阈值的大小随声音频率的改变而改变。
一个人是否听到声音取决于声音的频率，以及声音的幅度是否高于这种频率下的听觉阈值。听觉掩蔽特性即听觉阈值电平是自适应的，会随听到的不同频率声音而发生变化。
*利用心理声学模型可以消除更多的冗余数据，人耳听不见的部分和引入的低于听觉阈值量化噪声不编码，主要声音成分用较多的比特数表示，从而获得更大的压缩效率。
动态比特分配(Bit Allocator)
根据心理声学模型的计算结果，为每个子带信号分配比特数。
在调整到固定的码率之前，先确定可用于样值编码的有效比特数，这个数值取决于比例因子、比例因子选择信息、比特分配信息以及辅助数据所需比特数。
比特分配的过程：
对每个子带计算掩蔽-噪声比MNR，即：MNR = SNR –SMR
其中SNR是信噪比 ，SMR是信掩比；对最低MNR的子带分配比特，使获益最大的子带的量化级别增加一级；重新计算分配了更多比特子带的MNR，循环，直到没有比特可用。
装帧(Frame Creation)
产生MPEG-I兼容的比特流
三、代码实现
1. 主函数
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;
//add
int gr;
FILE *out_txt=NULL;
unsigned char *outTXT=NULL;
out_txt=fopen("output.txt","w");
//end
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 ();//初始化
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);
//输出配置信息等内容
/* this will load the alloc tables and do some other stuff */
hdr_to_frps (&frame);
nch = frame.nch;
error_protection = header.error_protection;
//从数据流获取音频
while (get_audio (musicin, buffer, num_samples, nch, &header) > 0) {
if (glopts.verbosity > 1)
if (++frameNum % 10 == 0)
fprintf (stderr, "[%4u]\r", frameNum);
fflush (stderr);
win_buf[0] = &buffer[0][0];
win_buf[1] = &buffer[1][0];
adb = available_bits (&header, &glopts);
lg_frame = adb / 8;
if (header.dab_extension) {
/* in 24 kHz we always have 4 bytes */
if (header.sampling_frequency == 1)
header.dab_extension = 4;
/* You must have one frame in memory if you are in DAB mode */
/* in conformity of the norme ETS 300 401 http://www.etsi.org */
/* see bitstream.c */
if (frameNum == 1)
minimum = lg_frame + MINIMUM;
adb -= header.dab_extension * 8 + header.dab_length * 8 + 16;
}
{
int gr, bl, ch;
/* New polyphase filter
Combines windowing and filtering. Ricardo Feb'03 */
for( gr = 0; gr < 3; gr++ )
for ( bl = 0; bl < 12; bl++ )
for ( ch = 0; ch < nch; ch++ )
WindowFilterSubband( &buffer[ch][gr * 12 * 32 + 32 * bl], ch,
&(*sb_sample)[ch][gr][bl][0] );
}
2. 输出音频的采样率和目标码率
/************************************************************************
*
* print_config
*
* PURPOSE: Prints the encoding parameters used
*
************************************************************************/
void print_config (frame_info * frame, int *psy, char *inPath,
char *outPath)
{
frame_header *header = frame->header;
if (glopts.verbosity == 0)
return;
fprintf (stderr, "--------------------------------------------\n");
fprintf (stderr, "Input File : '%s' %.1f kHz\n",
(strcmp (inPath, "-") ? inPath : "stdin"),
s_freq[header->version][header->sampling_frequency]);
fprintf (stderr, "Output File: '%s'\n",
(strcmp (outPath, "-") ? outPath : "stdout"));
fprintf (stderr, "%d kbps ", bitrate[header->version][header->bitrate_index]);
fprintf (stderr, "%s ", version_names[header->version]);
if (header->mode != MPG_MD_JOINT_STEREO)
fprintf (stderr, "Layer II %s Psycho model=%d (Mode_Extension=%d)\n",
mode_names[header->mode], *psy, header->mode_ext);
else
fprintf (stderr, "Layer II %s Psy model %d \n", mode_names[header->mode],
*psy);
fprintf (stderr, "[De-emph:%s\tCopyright:%s\tOriginal:%s\tCRC:%s]\n",
((header->emphasis) ? "On" : "Off"),
((header->copyright) ? "Yes" : "No"),
((header->original) ? "Yes" : "No"),
((header->error_protection) ? "On" : "Off"));
fprintf (stderr, "[Padding:%s\tByte-swap:%s\tChanswap:%s\tDAB:%s]\n",
((glopts.usepadbit) ? "Normal" : "Off"),
((glopts.byteswap) ? "On" : "Off"),
((glopts.channelswap) ? "On" : "Off"),
((glopts.dab) ? "On" : "Off"));
if (glopts.vbr == TRUE)
fprintf (stderr, "VBR Enabled. Using MNR boost of %f\n", glopts.vbrlevel);
fprintf(stderr,"ATH adjustment %f\n",glopts.athlevel);
fprintf (stderr, "--------------------------------------------\n");
}
3. 输出某个帧的比特数、比例因子、比特分配结果
#ifdef NEWENCODE
sf_transmission_pattern (scalar, scfsi, &frame);
main_bit_allocation_new (smr, scfsi, bit_alloc, &adb, &frame, &glopts);
//main_bit_allocation (smr, scfsi, bit_alloc, &adb, &frame, &glopts);
if (error_protection)
CRC_calc (&frame, bit_alloc, scfsi, &crc);
write_header (&frame, &bs);
//encode_info (&frame, &bs);
if (error_protection)
putbits (&bs, crc, 16);
write_bit_alloc (bit_alloc, &frame, &bs);
//encode_bit_alloc (bit_alloc, &frame, &bs);
write_scalefactors(bit_alloc, scfsi, scalar, &frame, &bs);
//encode_scale (bit_alloc, scfsi, scalar, &frame, &bs);
subband_quantization_new (scalar, *sb_sample, j_scale, *j_sample, bit_alloc,
*subband, &frame);
//subband_quantization (scalar, *sb_sample, j_scale, *j_sample, bit_alloc,
// *subband, &frame);
write_samples_new(*subband, bit_alloc, &frame, &bs);
//sample_encoding (*subband, bit_alloc, &frame, &bs);
#else
transmission_pattern (scalar, scfsi, &frame);
main_bit_allocation (smr, scfsi, bit_alloc, &adb, &frame, &glopts);
if (error_protection)
CRC_calc (&frame, bit_alloc, scfsi, &crc);
encode_info (&frame, &bs);
if (error_protection)
encode_CRC (crc, &bs);
encode_bit_alloc (bit_alloc, &frame, &bs);
encode_scale (bit_alloc, scfsi, scalar, &frame, &bs);
subband_quantization (scalar, *sb_sample, j_scale, *j_sample, bit_alloc,
*subband, &frame);
sample_encoding (*subband, bit_alloc, &frame, &bs);
#endif
/* If not all the bits were used, write out a stack of zeros */
for (i = 0; i < adb; i++)
put1bit (&bs, 0);
if (header.dab_extension) {
/* Reserve some bytes for X-PAD in DAB mode */
putbits (&bs, 0, header.dab_length * 8);
for (i = header.dab_extension - 1; i >= 0; i--) {
CRC_calcDAB (&frame, bit_alloc, scfsi, scalar, &crc, i);
/* this crc is for the previous frame in DAB mode */
if (bs.buf_byte_idx + lg_frame < bs.buf_size)
bs.buf[bs.buf_byte_idx + lg_frame] = crc;
/* reserved 2 bytes for F-PAD in DAB mode */
putbits (&bs, crc, 8);
}
putbits (&bs, 0, 16);
}
frameBits = sstell (&bs) - sentBits;
if (frameBits % 8) { /* a program failure */
fprintf (stderr, "Sent %ld bits = %ld slots plus %ld\n", frameBits,
frameBits / 8, frameBits % 8);
fprintf (stderr, "If you are reading this, the program is broken\n");
fprintf (stderr, "email [mfc at NOTplanckenerg.com] without the NOT\n");
fprintf (stderr, "with the command line arguments and other info\n");
exit (0);
}
sentBits += frameBits;
}
close_bit_stream_w (&bs);
if ((glopts.verbosity > 1) && (glopts.vbr == TRUE)) {
int i;
#ifdef NEWENCODE
extern int vbrstats_new[15];
#else
extern int vbrstats[15];
#endif
fprintf (stdout, "VBR stats:\n");
for (i = 1; i < 15; i++)
fprintf (stdout, "%4i ", bitrate[header.version][i]);
fprintf (stdout, "\n");
for (i = 1; i < 15; i++)
#ifdef NEWENCODE
fprintf (stdout,"%4i ",vbrstats_new[i]);
#else
fprintf (stdout, "%4i ", vbrstats[i]);
#endif
fprintf (stdout, "\n");
}
fprintf (stderr,"Avg slots/frame = %.3f; b/smp = %.2f; bitrate = %.3f kbps\n",
(FLOAT) sentBits / (frameNum * 8),
(FLOAT) sentBits / (frameNum * 1152),
(FLOAT) sentBits / (frameNum * 1152) *
s_freq[header.version][header.sampling_frequency]);
if (fclose (musicin) != 0)
{
fprintf (stderr, "Could not close \"%s\".\n", original_file_name);
exit (2);
}
fprintf (stderr, "\nDone\n");
//add
fprintf(out_txt, "该音频声道数：%d\n", nch);
fprintf(out_txt, "观测第 %d 帧\n", frameNum);
fprintf(out_txt, "本帧所分配比特：%d bits\n", adb);
fprintf(out_txt, "该帧比例因子和比特分配结果如下：\n");
for (ch = 0; ch < nch; ch++)
{
fprintf(out_txt, "--- 声道%2d ----\n", ch + 1);
for (sb = 0; sb < frame.sblimit; sb++)
{
fprintf(out_txt, "子带[%2d]比例因子:\t", sb + 1);
for (gr = 0; gr < 3; gr++)
{
fprintf(out_txt, "%2d\t", scalar[ch][gr][sb]);
}
fprintf(out_txt, "\n");
fprintf(out_txt, "子带[%2d]比特分配表:\t%2d\n", sb + 1, bit_alloc[ch][sb]);
fprintf(out_txt, "\n");
}
}
//end
time(&end_time);
total_time = end_time - start_time;
printf("total time is %d\n", total_time);
free(outTXT);
fclose(out_txt);
system("pause");
exit (0);
}
四、实验结果
1. 音乐
2. 噪声
3. 音乐+噪声
4. 结论
噪声（均匀底噪）和音乐+噪声（均匀底噪）的各个子带所被分配到的比特数分布比较均匀，说明这种信号分布较为均匀。
音乐在高频部分所被分配的比特数较少，原因是人类发声的语音范围有限。
290
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
