1/* 2 * G.723.1 common header and data tables 3 * Copyright (c) 2006 Benjamin Larsson 4 * Copyright (c) 2010 Mohamed Naufal Basheer 5 * 6 * This file is part of FFmpeg. 7 * 8 * FFmpeg is free software; you can redistribute it and/or 9 * modify it under the terms of the GNU Lesser General Public 10 * License as published by the Free Software Foundation; either 11 * version 2.1 of the License, or (at your option) any later version. 12 * 13 * FFmpeg is distributed in the hope that it will be useful, 14 * but WITHOUT ANY WARRANTY; without even the implied warranty of 15 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 16 * Lesser General Public License for more details. 17 * 18 * You should have received a copy of the GNU Lesser General Public 19 * License along with FFmpeg; if not, write to the Free Software 20 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 21 */ 22 23/** 24 * @file 25 * G.723.1 types, functions and data tables 26 */ 27 28#ifndef AVCODEC_G723_1_H 29#define AVCODEC_G723_1_H 30 31#include <stdint.h> 32 33#include "libavutil/log.h" 34 35#define SUBFRAMES 4 36#define SUBFRAME_LEN 60 37#define FRAME_LEN (SUBFRAME_LEN << 2) 38#define HALF_FRAME_LEN (FRAME_LEN / 2) 39#define LPC_FRAME (HALF_FRAME_LEN + SUBFRAME_LEN) 40#define LPC_ORDER 10 41#define LSP_BANDS 3 42#define LSP_CB_SIZE 256 43#define PITCH_MIN 18 44#define PITCH_MAX (PITCH_MIN + 127) 45#define PITCH_ORDER 5 46#define GRID_SIZE 2 47#define PULSE_MAX 6 48#define GAIN_LEVELS 24 49#define COS_TBL_SIZE 512 50 51/** 52 * Bitexact implementation of 2ab scaled by 1/2^16. 53 * 54 * @param a 32 bit multiplicand 55 * @param b 16 bit multiplier 56 */ 57#define MULL2(a, b) \ 58 ((((a) >> 16) * (b) * 2) + (((a) & 0xffff) * (b) >> 15)) 59 60/** 61 * G723.1 frame types 62 */ 63enum FrameType { 64 ACTIVE_FRAME, ///< Active speech 65 SID_FRAME, ///< Silence Insertion Descriptor frame 66 UNTRANSMITTED_FRAME 67}; 68 69/** 70 * G723.1 rate values 71 */ 72enum Rate { 73 RATE_6300, 74 RATE_5300 75}; 76 77/** 78 * G723.1 unpacked data subframe 79 */ 80typedef struct G723_1_Subframe { 81 int ad_cb_lag; ///< adaptive codebook lag 82 int ad_cb_gain; 83 int dirac_train; 84 int pulse_sign; 85 int grid_index; 86 int amp_index; 87 int pulse_pos; 88} G723_1_Subframe; 89 90/** 91 * Pitch postfilter parameters 92 */ 93typedef struct PPFParam { 94 int index; ///< postfilter backward/forward lag 95 int16_t opt_gain; ///< optimal gain 96 int16_t sc_gain; ///< scaling gain 97} PPFParam; 98 99/** 100 * Harmonic filter parameters 101 */ 102typedef struct HFParam { 103 int index; 104 int gain; 105} HFParam; 106 107/** 108 * Optimized fixed codebook excitation parameters 109 */ 110typedef struct FCBParam { 111 int min_err; 112 int amp_index; 113 int grid_index; 114 int dirac_train; 115 int pulse_pos[PULSE_MAX]; 116 int pulse_sign[PULSE_MAX]; 117} FCBParam; 118 119typedef struct G723_1_ChannelContext { 120 G723_1_Subframe subframe[4]; 121 enum FrameType cur_frame_type; 122 enum FrameType past_frame_type; 123 enum Rate cur_rate; 124 uint8_t lsp_index[LSP_BANDS]; 125 int pitch_lag[2]; 126 int erased_frames; 127 128 int16_t prev_lsp[LPC_ORDER]; 129 int16_t sid_lsp[LPC_ORDER]; 130 int16_t prev_excitation[PITCH_MAX]; 131 int16_t excitation[PITCH_MAX + FRAME_LEN + 4]; 132 int16_t synth_mem[LPC_ORDER]; 133 int16_t fir_mem[LPC_ORDER]; 134 int iir_mem[LPC_ORDER]; 135 136 int random_seed; 137 int cng_random_seed; 138 int interp_index; 139 int interp_gain; 140 int sid_gain; 141 int cur_gain; 142 int reflection_coef; 143 int pf_gain; ///< formant postfilter 144 ///< gain scaling unit memory 145 int16_t audio[FRAME_LEN + LPC_ORDER + PITCH_MAX + 4]; 146 147 /* encoder */ 148 int16_t prev_data[HALF_FRAME_LEN]; 149 int16_t prev_weight_sig[PITCH_MAX]; 150 151 int16_t hpf_fir_mem; ///< highpass filter fir 152 int hpf_iir_mem; ///< and iir memories 153 int16_t perf_fir_mem[LPC_ORDER]; ///< perceptual filter fir 154 int16_t perf_iir_mem[LPC_ORDER]; ///< and iir memories 155 156 int16_t harmonic_mem[PITCH_MAX]; 157} G723_1_ChannelContext; 158 159typedef struct G723_1_Context { 160 AVClass *class; 161 int postfilter; 162 163 G723_1_ChannelContext ch[2]; 164} G723_1_Context; 165 166 167/** 168 * Scale vector contents based on the largest of their absolutes. 169 */ 170int ff_g723_1_scale_vector(int16_t *dst, const int16_t *vector, int length); 171 172/** 173 * Calculate the number of left-shifts required for normalizing the input. 174 * 175 * @param num input number 176 * @param width width of the input, 16 bits(0) / 32 bits(1) 177 */ 178int ff_g723_1_normalize_bits(int num, int width); 179 180int ff_g723_1_dot_product(const int16_t *a, const int16_t *b, int length); 181 182/** 183 * Get delayed contribution from the previous excitation vector. 184 */ 185void ff_g723_1_get_residual(int16_t *residual, int16_t *prev_excitation, 186 int lag); 187 188/** 189 * Generate a train of dirac functions with period as pitch lag. 190 */ 191void ff_g723_1_gen_dirac_train(int16_t *buf, int pitch_lag); 192 193 194/** 195 * Generate adaptive codebook excitation. 196 */ 197void ff_g723_1_gen_acb_excitation(int16_t *vector, int16_t *prev_excitation, 198 int pitch_lag, G723_1_Subframe *subfrm, 199 enum Rate cur_rate); 200/** 201 * Quantize LSP frequencies by interpolation and convert them to 202 * the corresponding LPC coefficients. 203 * 204 * @param lpc buffer for LPC coefficients 205 * @param cur_lsp the current LSP vector 206 * @param prev_lsp the previous LSP vector 207 */ 208void ff_g723_1_lsp_interpolate(int16_t *lpc, int16_t *cur_lsp, 209 int16_t *prev_lsp); 210 211/** 212 * Perform inverse quantization of LSP frequencies. 213 * 214 * @param cur_lsp the current LSP vector 215 * @param prev_lsp the previous LSP vector 216 * @param lsp_index VQ indices 217 * @param bad_frame bad frame flag 218 */ 219void ff_g723_1_inverse_quant(int16_t *cur_lsp, int16_t *prev_lsp, 220 uint8_t *lsp_index, int bad_frame); 221 222static const uint8_t frame_size[4] = { 24, 20, 4, 1 }; 223 224/** 225 * LSP DC component 226 */ 227static const int16_t dc_lsp[LPC_ORDER] = { 228 0x0c3b, 229 0x1271, 230 0x1e0a, 231 0x2a36, 232 0x3630, 233 0x406f, 234 0x4d28, 235 0x56f4, 236 0x638c, 237 0x6c46 238}; 239 240/* Cosine table scaled by 2^14 */ 241extern const int16_t ff_g723_1_cos_tab[COS_TBL_SIZE + 1]; 242#define G723_1_COS_TAB_FIRST_ELEMENT 16384 243 244/** 245 * LSP VQ tables 246 */ 247extern const int16_t ff_g723_1_lsp_band0[LSP_CB_SIZE][3]; 248extern const int16_t ff_g723_1_lsp_band1[LSP_CB_SIZE][3]; 249extern const int16_t ff_g723_1_lsp_band2[LSP_CB_SIZE][4]; 250 251/** 252 * Used for the coding/decoding of the pulses positions 253 * for the MP-MLQ codebook 254 */ 255extern const int32_t ff_g723_1_combinatorial_table[PULSE_MAX][SUBFRAME_LEN/GRID_SIZE]; 256 257/** 258 * Number of non-zero pulses in the MP-MLQ excitation 259 */ 260static const int8_t pulses[4] = {6, 5, 6, 5}; 261 262extern const int16_t ff_g723_1_fixed_cb_gain[GAIN_LEVELS]; 263 264extern const int16_t ff_g723_1_adaptive_cb_gain85 [ 85 * 20]; 265extern const int16_t ff_g723_1_adaptive_cb_gain170[170 * 20]; 266 267#endif /* AVCODEC_G723_1_H */ 268