Layer I 编码

码率分配

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，是信噪比SNR–信掩比SMR，即：MNR = SNR–SMR

NMR=SMR-SNR

算法：使整帧和每个子带的总噪声—掩蔽比最小

计算噪声-掩蔽比(noise-to-mask ratio, NMR)：         NMR = SMR – SNR          (dB)

其中SNR 由MPEG-I标准给定 (为量化水平的函数)

NMR：表示波形误差与感知测量之间的误差

算法：循环，直到没有比特可用：

NMR = SMR– SNR (dB)

对最高NMR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NMR

装帧

Header：帧头格式

Layer II编码

与Layer I类似，但对Layer I有增强

装帧、缩放因子表示、量化 缩放因子(比例因子)一般从低频子带到高频子带出现连续下降

帧： 3 组/帧 x  12个样本/子带 x 32个子带/帧 = 1152个样本/帧 每个样本的overhead更少

缩放因子：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 factor selection 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

量化

Layer I：每个子带从相同的量化集合中选择

每个子带取共14个量化器中的一个

Layer II：

根据采样和码率量化，不同子带可以从不同的量化器集合中选择

·某些（高频）子带的比特数可能为0

对量化级别在3、5、9级时，采用“颗粒” 优化

·颗粒= 3 个样本，根据颗粒选择量化水平

装帧

Layer III 编码

MDCT 

        各种边界去块效应滤波器

◼ MDCT：改进的离散余弦变换(Modified Discrete CosineTransform) – 解决块边缘失真问题

◼ MDCT变换是一个非正交变换，必须采用时域混叠抵消技术(TDAC)来完成信号的重建

◼ 在实际处理时需要先加窗，再进行MDCT变换

IMDCT：

         分析过程中引进的混叠失真，可以在综合过程中抵消。

重构信号

        保留10个最大的系数  频域的量化噪声将扩展到变换的整个数据。

        对尖锐的短声音，需采用更小的块，以控制QE的扩散。

实验要求

理解程序设计的整体框架

理解感知音频编码的设计思想

·两条线

·时-频分析的矛盾！

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

理解码率分配的实现思路

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（持续噪声、突发噪声） 音乐 混合

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

实验结果

命令行参数设置

int main(int argc, char** argv)
{typedef double SBS[2][3][SCALE_BLOCK][SBLIMIT];   // SCALE_BLOCK=12，SBLIMIT=32SBS* sb_sample;typedef double JSBS[3][SCALE_BLOCK][SBLIMIT];JSBS* j_sample;typedef double IN[2][HAN_SIZE];   //HAN_SIZE=512IN* 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];     static unsigned int scfsi[2][SBLIMIT];static unsigned int scalar[2][3][SBLIMIT];     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, 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;FILE* result = NULL;result = fopen("result.txt", "wb");/* 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 */     //MPEG_AUDIO_ID=1total_time = 0;time(&start_time);programName = argv[0];if (argc == 1)       /* no command-line args */  short_usage();elseparse_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) > 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);   //bit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 totalbit = adb;{int gr, bl, ch;/* New polyphase filterCombines 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]);     }if (frameNum == 5) {//输出提示信息fprintf(result, "第%d帧\n", frameNum);//输出可用比特数fprintf(result, "分配比特数：%d\n", totalbit);//输出比例因子fprintf(result, "比例因子：\n");for (int i = 0; i < nch; i++) {   fprintf(result, "声道[%d]:\n", i + 1);for (int j = 0; j < frame.sblimit; j++) {   if (j % 4 == 0 && j != 0) {fprintf(result, "\n");}fprintf(result, "子带%d:\t", j);for (int k = 0; k < 3; k++) {    fprintf(result, "%d\t", scalar[i][k][j]);}fprintf(result, "\t");}fprintf(result, "\n");}fprintf(result, "\n");//输出比特分配结果fprintf(result, "\n比特分配结果：\n");for (int i = 0; i < nch; i++) {   fprintf(result, "声道[%d]:\n", i + 1);for (int j = 0; j < frame.sblimit; j++) {   if (j % 4 == 0 && j != 0) {fprintf(result, "\n");}fprintf(result, "子带%d:\t%d\t", j, bit_alloc[i][j]);}fprintf(result, "\n");}fflush(result);}#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 NEWENCODEscalefactor_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);}
#elsescale_factor_calc(*sb_sample, scalar, nch, frame.sblimit);   pick_scale(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(*sb_sample, *j_sample, frame.sblimit);scale_factor_calc(j_sample, &j_scale, 1, frame.sblimit);}
#endifif ((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++) {    //nch表示通道数for (sb = 0; sb < SBLIMIT; sb++)    //SBLIMIT=32smr[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);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 NEWENCODEsf_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);
#elsetransmission_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);     /* If not all the bits were used, write out a stack of zeros */for (i = 0; i < adb; i++)    //写码流put1bit(&bs, 0);     //剩余未分配比特数写入stackif (header.dab_extension) {/* Reserve some bytes for X-PAD in DAB mode */putbits(&bs, 0, header.dab_length * 8);       //写码流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 NEWENCODEextern int vbrstats_new[15];
#elseextern int vbrstats[15];
#endiffprintf(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 NEWENCODEfprintf(stdout, "%4i ", vbrstats_new[i]);
#elsefprintf(stdout, "%4i ", vbrstats[i]);
#endiffprintf(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");fclose(result);time(&end_time);total_time = end_time - start_time;printf("total time is %d\n", total_time);exit(0);
}

持续性噪声

突发性噪声

乐音

混合

数据对比

类型	分配的比特数	比例因子	比特分配结果	压缩比
突发噪声	4608			530/66.3=8
持续噪声	4608			588/63.9=7.99
音乐	4608			780/97.8=7.98
混合	4608			782/97.8=8

遇到的问题

“/ZI”和“/Gy-”命令行选项不兼容 ”问题

1."项目”—>“属性”—>“C/C++” “常规”—>“调试信息格式”—>选择“程序数据库(/Zi)”或“无”
2."项目”—>“属性”—>“C/C++” “代码生成”—>“启用函数集链接”—>选择“是 (/Gy)”