数据压缩实验六——MPEG音频编码
一、实验要求
1,理解程序设计的整体框架
2,理解感知音频编码的设计思想(两条线、时-频分析的矛盾)
3,理解心理声学模型的实现过程(临界频带的概念、掩蔽值计算的思路)
4,理解码率分配的实现思路
5,输出音频的采样率和目标码率
6,选择三个不同特性的音频文件(噪声(持续噪声、突发噪声)、音乐、混合)
7,某个数据帧,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
音频编码的设计思想:
编码器分为两条线:
第一条线,将输入的音频子带分解,形成32个子带。我们希望对于每个频带中的所有点使用相同的量化bit数进行量化,这就要求每个频带中的点的值不能相差太大,于是我们应将信号时间取得很短,由于语音信号的短时平稳性,每个频带中的点就比较接近了。
第二条线,对于输入的音频信号,我们希望找到能够表征它的性质的心理声学模型,心理声学模型的横坐标是频率,纵坐标是阈值。为了使模型与实际更为接近,我们希望频率分得越细越好,即频率分辨率越高越好,这就与第一条线中对于时域分辨率的要求相矛盾了。
心理声学模型
·通过子带分析滤波器组使信号具有高的时间分辨率,确保在短暂冲击信号情况下,编码的声音信号具有足够高的质量
·又可以使信号通过FFT运算具有高的频率分辨率,因为掩蔽阈值是从功率谱密度推出来的。
·在低频子带中,为了保护音调和共振峰的结构,就要求用较小的量化阶、较多的量化级数,即分配较多的位数来表示样本值。而话音中的摩擦音和类似噪声的声音,通常出现在高频子带中,对它分配较少的位数
MPEG-I 标准定义了两个模型
◼ 心理声学模型1:
计算复杂度低
但对假设用户听不到的部分压缩太严重
◼ 心理声学模型2 :
提供了适合Layer III编码的更多特征
◼ 实际实现的模型复杂度取决所需要的压缩因子
如大的压缩因子不重要,则可以完全不用心理声学模型。此时位分配算法不使用SMR( Signal Mask Ratio ),而是使用SNR。
临界频带:
临界频带是指当某个纯音被以它为中心频率、且具有一定带宽的连续噪声所掩蔽时,如果该纯音刚好被听到时的功率等于这一频带内的噪声功率,这个带宽为临界频带宽度。
掩蔽值的计算:
缩放因子(比例因子):每个子带的3个组尽可能共用缩放因子
Layer I: 1个/12个样本
Layer II: 1个/(24/36)个样本
◼ 1/2/3个缩放因子和缩放因子选择信息(scale factorselection information, SCFSI) (每子带2比特)一起传送
如果缩放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
如果要给瞬态信号编码,则要在瞬态的前、后沿传送两个或所有三个比例因子
码率分配的思路:
三、实验代码
先在print_config()函数中输出一些输入、输出文件的主要参数
#if FRAME_TRACE
fprintf(output_txt, "========== 基本信息 ==========\n");
fprintf(output_txt, "输入文件:%s\n", inPath);
fprintf(output_txt, "输出文件:%s\n", outPath);
fprintf(output_txt, "采样频率:%.1f kHz\n", s_freq[header->version][header->sampling_frequency]);
fprintf(output_txt, "输出文件码率:%d kbps\n", bitrate[header->version][header->bitrate_index]);
#endif
在main()中添加以下函数:输出比例因子和比特分配表
#else
scale_factor_calc (*sb_sample, scalar, nch, frame.sblimit);//计算比例因子
pick_scale (scalar, &frame, max_sc);//拾取比例因子
{int sb,gr,ch;
if (frameNum == 280)
{
fprintf(output_txt, "声道数:%d\n", nch);
fprintf(output_txt, "目前观测第 %d 帧\n", frameNum);
fprintf(output_txt, "本帧比特预算:%d bits\n", adb);
fprintf(output_txt, "\n");
fprintf(output_txt, "========== 比例因子 ==========\n");
for (ch = 0; ch < nch; ch++)
{
fprintf(output_txt, "------ 声道%2d ------\n", ch + 1);
for (sb = 0; sb < frame.sblimit; sb++)
{
fprintf(output_txt, "子带[%2d]:\t", sb + 1);
for (gr = 0; gr < 3; gr++)
{
fprintf(output_txt, "%2d\t", scalar[ch][gr][sb]);
}
fprintf(output_txt, "\n");
}
}
fprintf(output_txt, "\n");
}
}
...
#else
transmission_pattern (scalar, scfsi, &frame);
main_bit_allocation (smr, scfsi, bit_alloc, &adb, &frame, &glopts);
if (frameNum == 280)
{
fprintf(output_txt, "========== 比特分配表 ==========\n");
{int ch, sb;
for (ch = 0; ch < nch; ch++)
{
fprintf(output_txt, "------ 声道%2d ------\n", ch + 1);
for (sb = 0; sb < frame.sblimit; sb++)
{
fprintf(output_txt, "子带[%2d]:\t%2d\n", sb, bit_alloc[ch][sb]);
}
fprintf(output_txt, "\n");
}
}
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; // 包含头信息、比特分配表、声道数、子带数等内容
frame_header header; // 包含采样频率等信息
char original_file_name[MAX_NAME_SIZE]; // 输入文件名
char encoded_file_name[MAX_NAME_SIZE]; // 输出文件名
short** win_buf;
static short buffer[2][1152];
static unsigned int bit_alloc[2][SBLIMIT]; // 存放双声道各个子带的比特分配表
static unsigned int scfsi[2][SBLIMIT];
static unsigned int scalar[2][3][SBLIMIT]; // 存放双声道3组12个样值的各个子带的比例因子
static unsigned int 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;
int nch; // 声道数
int error_protection;
static unsigned int crc;
int sb, ch;
int adb; // 比特预算 (i.e., number of bits available)
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]; // exe文件名称
if (argc == 1) /* no command-line args */
short_usage();
else
parse_args(argc, argv, &frame, &model, &num_samples, original_file_name, encoded_file_name); // 解析命令行参数
print_config(&frame, &model, original_file_name, encoded_file_name); // print文件参数到窗口
/* 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) {
/* 从输入的文件读取数据到buffer */
if (glopts.verbosity > 1)
if (++frameNum % 10 == 0) /* 出错 */
fprintf(stderr, "[%4u]\r", frameNum);
fflush(stderr);
win_buf[0] = &buffer[0][0];
win_buf[1] = &buffer[1][0];
adb = available_bits(&header, &glopts); // 计算比特预算
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++) /* 36个样值分为3组 */
for (bl = 0; bl < 12; bl++) /* 每组做12次子带分解 */
for (ch = 0; ch < nch; ch++)
WindowFilterSubband(&buffer[ch][gr * 12 * 32 + 32 * bl], ch, &(*sb_sample)[ch][gr][bl][0]); /* 多相滤波器组 */
}
#ifdef REFERENCECODE
{
/* Old code. left here for reference */
int gr, bl, ch;
for (gr = 0; gr < 3; gr++)
for (bl = 0; bl < SCALE_BLOCK; bl++)
for (ch = 0; ch < nch; ch++) {
window_subband(&win_buf[ch], &(*win_que)[ch][0], ch);
filter_subband(&(*win_que)[ch][0], &(*sb_sample)[ch][gr][bl][0]);
}
}
#endif
#ifdef NEWENCODE
scalefactor_calc_new(*sb_sample, scalar, nch, frame.sblimit);
find_sf_max(scalar, &frame, max_sc);
if (frame.actual_mode == MPG_MD_JOINT_STEREO) {
/* this way we calculate more mono than we need */
/* but it is cheap */
combine_LR_new(*sb_sample, *j_sample, frame.sblimit);
scalefactor_calc_new(j_sample, &j_scale, 1, frame.sblimit);
}
#else
scale_factor_calc(*sb_sample, scalar, nch, frame.sblimit); // 计算比例因子
pick_scale(scalar, &frame, max_sc); // 选择比例因子
if (frame.actual_mode == MPG_MD_JOINT_STEREO) { /* 先忽略 */
/* this way we calculate more mono than we need */
/* but it is cheap */
combine_LR(*sb_sample, *j_sample, frame.sblimit);
scale_factor_calc(j_sample, &j_scale, 1, frame.sblimit);
}
#endif
/* 选择心理声学模型,计算SMR */
if ((glopts.quickmode == TRUE) && (++psycount % glopts.quickcount != 0)) {
/* We're using quick mode, so we're only calculating the model every
'quickcount' frames. Otherwise, just copy the old ones across */
for (ch = 0; ch < nch; ch++) {
for (sb = 0; sb < SBLIMIT; sb++)
smr[ch][sb] = smrdef[ch][sb];
}
} else {
/* calculate the psymodel */
switch (model) {
case -1:
psycho_n1(smr, nch);
break;
case 0: /* Psy Model A */
psycho_0(smr, nch, scalar, (FLOAT)s_freq[header.version][header.sampling_frequency] * 1000); // smr为输出
break;
case 1:
psycho_1(buffer, max_sc, smr, &frame);
break;
case 2:
for (ch = 0; ch < nch; ch++) {
psycho_2(&buffer[ch][0], &sam[ch][0], ch, &smr[ch][0], //snr32,
(FLOAT)s_freq[header.version][header.sampling_frequency] *
1000, &glopts);
}
break;
case 3:
/* Modified psy model 1 */
psycho_3(buffer, max_sc, smr, &frame, &glopts);
break;
case 4:
/* Modified Psycho Model 2 */
for (ch = 0; ch < nch; ch++) {
psycho_4(&buffer[ch][0], &sam[ch][0], ch, &smr[ch][0], // snr32,
(FLOAT)s_freq[header.version][header.sampling_frequency] *
1000, &glopts);
}
break;
case 5:
/* Model 5 comparse model 1 and 3 */
psycho_1(buffer, max_sc, smr, &frame);
fprintf(stdout, "1 ");
smr_dump(smr, nch);
psycho_3(buffer, max_sc, smr, &frame, &glopts);
fprintf(stdout, "3 ");
smr_dump(smr, nch);
break;
case 6:
/* Model 6 compares model 2 and 4 */
for (ch = 0; ch < nch; ch++)
psycho_2(&buffer[ch][0], &sam[ch][0], ch, &smr[ch][0], //snr32,
(FLOAT)s_freq[header.version][header.sampling_frequency] *
1000, &glopts);
fprintf(stdout, "2 ");
smr_dump(smr, nch);
for (ch = 0; ch < nch; ch++)
psycho_4(&buffer[ch][0], &sam[ch][0], ch, &smr[ch][0], // snr32,
(FLOAT)s_freq[header.version][header.sampling_frequency] *
1000, &glopts);
fprintf(stdout, "4 ");
smr_dump(smr, nch);
break;
case 7:
fprintf(stdout, "Frame: %i\n", frameNum);
/* Dump the SMRs for all models */
psycho_1(buffer, max_sc, smr, &frame);
fprintf(stdout, "1");
smr_dump(smr, nch);
psycho_3(buffer, max_sc, smr, &frame, &glopts);
fprintf(stdout, "3");
smr_dump(smr, nch);
for (ch = 0; ch < nch; ch++)
psycho_2(&buffer[ch][0], &sam[ch][0], ch, &smr[ch][0], //snr32,
(FLOAT)s_freq[header.version][header.sampling_frequency] *
1000, &glopts);
fprintf(stdout, "2");
smr_dump(smr, nch);
for (ch = 0; ch < nch; ch++)
psycho_4(&buffer[ch][0], &sam[ch][0], ch, &smr[ch][0], // snr32,
(FLOAT)s_freq[header.version][header.sampling_frequency] *
1000, &glopts);
fprintf(stdout, "4");
smr_dump(smr, nch);
break;
case 8:
/* Compare 0 and 4 */
psycho_n1(smr, nch);
fprintf(stdout, "0");
smr_dump(smr, nch);
for (ch = 0; ch < nch; ch++)
psycho_4(&buffer[ch][0], &sam[ch][0], ch, &smr[ch][0], // snr32,
(FLOAT)s_freq[header.version][header.sampling_frequency] *
1000, &glopts);
fprintf(stdout, "4");
smr_dump(smr, nch);
break;
default:
fprintf(stderr, "Invalid psy model specification: %i\n", model);
exit(0);
}
if (glopts.quickmode == TRUE)
/* copy the smr values and reuse them later */
for (ch = 0; ch < nch; ch++) {
for (sb = 0; sb < SBLIMIT; sb++)
smrdef[ch][sb] = smr[ch][sb];
}
if (glopts.verbosity > 4)
smr_dump(smr, nch);
}
#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); // 比特分配
if (error_protection)
CRC_calc(&frame, bit_alloc, scfsi, &crc);
encode_info(&frame, &bs); // 编码
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); // 量化
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");
time(&end_time);
total_time = end_time - start_time;
printf("total time is %d\n", total_time);
exit(0);
}
四、输出结果
音乐:
噪音:
混合: