FFmpeg: libavcodec/amrnbdec.c Source File

FFmpeg
amrnbdec.c
Go to the documentation of this file.
1 /*
2  * AMR narrowband decoder
3  * Copyright (c) 2006-2007 Robert Swain
4  * Copyright (c) 2009 Colin McQuillan
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 /**
25  * @file
26  * AMR narrowband decoder
27  *
28  * This decoder uses floats for simplicity and so is not bit-exact. One
29  * difference is that differences in phase can accumulate. The test sequences
30  * in 3GPP TS 26.074 can still be useful.
31  *
32  * - Comparing this file's output to the output of the ref decoder gives a
33  * PSNR of 30 to 80. Plotting the output samples shows a difference in
34  * phase in some areas.
35  *
36  * - Comparing both decoders against their input, this decoder gives a similar
37  * PSNR. If the test sequence homing frames are removed (this decoder does
38  * not detect them), the PSNR is at least as good as the reference on 140
39  * out of 169 tests.
40  */
41 
42 
43 #include <string.h>
44 #include <math.h>
45 
46 #include "libavutil/channel_layout.h"
47 #include "libavutil/float_dsp.h"
48 #include "avcodec.h"
49 #include "libavutil/common.h"
50 #include "libavutil/avassert.h"
51 #include "celp_math.h"
52 #include "celp_filters.h"
53 #include "acelp_filters.h"
54 #include "acelp_vectors.h"
55 #include "acelp_pitch_delay.h"
56 #include "lsp.h"
57 #include "amr.h"
58 #include "internal.h"
59 
60 #include "amrnbdata.h"
61 
62  #define AMR_BLOCK_SIZE 160 ///< samples per frame
63  #define AMR_SAMPLE_BOUND 32768.0 ///< threshold for synthesis overflow
64 
65 /**
66  * Scale from constructed speech to [-1,1]
67  *
68  * AMR is designed to produce 16-bit PCM samples (3GPP TS 26.090 4.2) but
69  * upscales by two (section 6.2.2).
70  *
71  * Fundamentally, this scale is determined by energy_mean through
72  * the fixed vector contribution to the excitation vector.
73  */
74  #define AMR_SAMPLE_SCALE (2.0 / 32768.0)
75 
76 /** Prediction factor for 12.2kbit/s mode */
77  #define PRED_FAC_MODE_12k2 0.65
78 
79  #define LSF_R_FAC (8000.0 / 32768.0) ///< LSF residual tables to Hertz
80  #define MIN_LSF_SPACING (50.0488 / 8000.0) ///< Ensures stability of LPC filter
81  #define PITCH_LAG_MIN_MODE_12k2 18 ///< Lower bound on decoded lag search in 12.2kbit/s mode
82 
83 /** Initial energy in dB. Also used for bad frames (unimplemented). */
84  #define MIN_ENERGY -14.0
85 
86 /** Maximum sharpening factor
87  *
88  * The specification says 0.8, which should be 13107, but the reference C code
89  * uses 13017 instead. (Amusingly the same applies to SHARP_MAX in g729dec.c.)
90  */
91  #define SHARP_MAX 0.79449462890625
92 
93 /** Number of impulse response coefficients used for tilt factor */
94  #define AMR_TILT_RESPONSE 22
95 /** Tilt factor = 1st reflection coefficient * gamma_t */
96  #define AMR_TILT_GAMMA_T 0.8
97 /** Adaptive gain control factor used in post-filter */
98  #define AMR_AGC_ALPHA 0.9
99 
100  typedef struct AMRContext {
101   AMRNBFrame frame; ///< decoded AMR parameters (lsf coefficients, codebook indexes, etc)
102   uint8_t bad_frame_indicator; ///< bad frame ? 1 : 0
103   enum Mode cur_frame_mode;
104 
105   int16_t prev_lsf_r[LP_FILTER_ORDER]; ///< residual LSF vector from previous subframe
106   double lsp[4][LP_FILTER_ORDER]; ///< lsp vectors from current frame
107   double prev_lsp_sub4[LP_FILTER_ORDER]; ///< lsp vector for the 4th subframe of the previous frame
108 
109   float lsf_q[4][LP_FILTER_ORDER]; ///< Interpolated LSF vector for fixed gain smoothing
110   float lsf_avg[LP_FILTER_ORDER]; ///< vector of averaged lsf vector
111 
112   float lpc[4][LP_FILTER_ORDER]; ///< lpc coefficient vectors for 4 subframes
113 
114   uint8_t pitch_lag_int; ///< integer part of pitch lag from current subframe
115 
116   float excitation_buf[PITCH_DELAY_MAX + LP_FILTER_ORDER + 1 + AMR_SUBFRAME_SIZE]; ///< current excitation and all necessary excitation history
117   float *excitation; ///< pointer to the current excitation vector in excitation_buf
118 
119   float pitch_vector[AMR_SUBFRAME_SIZE]; ///< adaptive code book (pitch) vector
120   float fixed_vector[AMR_SUBFRAME_SIZE]; ///< algebraic codebook (fixed) vector (must be kept zero between frames)
121 
122   float prediction_error[4]; ///< quantified prediction errors {20log10(^gamma_gc)} for previous four subframes
123   float pitch_gain[5]; ///< quantified pitch gains for the current and previous four subframes
124   float fixed_gain[5]; ///< quantified fixed gains for the current and previous four subframes
125 
126   float beta; ///< previous pitch_gain, bounded by [0.0,SHARP_MAX]
127   uint8_t diff_count; ///< the number of subframes for which diff has been above 0.65
128   uint8_t hang_count; ///< the number of subframes since a hangover period started
129 
130   float prev_sparse_fixed_gain; ///< previous fixed gain; used by anti-sparseness processing to determine "onset"
131   uint8_t prev_ir_filter_nr; ///< previous impulse response filter "impNr": 0 - strong, 1 - medium, 2 - none
132   uint8_t ir_filter_onset; ///< flag for impulse response filter strength
133 
134   float postfilter_mem[10]; ///< previous intermediate values in the formant filter
135   float tilt_mem; ///< previous input to tilt compensation filter
136   float postfilter_agc; ///< previous factor used for adaptive gain control
137   float high_pass_mem[2]; ///< previous intermediate values in the high-pass filter
138 
139   float samples_in[LP_FILTER_ORDER + AMR_SUBFRAME_SIZE]; ///< floating point samples
140 
141   ACELPFContext acelpf_ctx; ///< context for filters for ACELP-based codecs
142   ACELPVContext acelpv_ctx; ///< context for vector operations for ACELP-based codecs
143   CELPFContext celpf_ctx; ///< context for filters for CELP-based codecs
144   CELPMContext celpm_ctx; ///< context for fixed point math operations
145 
146 } AMRContext;
147 
148 /** Double version of ff_weighted_vector_sumf() */
149  static void weighted_vector_sumd(double *out, const double *in_a,
150  const double *in_b, double weight_coeff_a,
151  double weight_coeff_b, int length)
152 {
153  int i;
154 
155  for (i = 0; i < length; i++)
156  out[i] = weight_coeff_a * in_a[i]
157  + weight_coeff_b * in_b[i];
158 }
159 
160  static av_cold int amrnb_decode_init(AVCodecContext *avctx)
161 {
162  AMRContext *p = avctx->priv_data;
163  int i;
164 
165  if (avctx->channels > 1) {
166  avpriv_report_missing_feature(avctx, "multi-channel AMR");
167  return AVERROR_PATCHWELCOME;
168  }
169 
170  avctx->channels = 1;
171  avctx->channel_layout = AV_CH_LAYOUT_MONO;
172  if (!avctx->sample_rate)
173  avctx->sample_rate = 8000;
174  avctx->sample_fmt = AV_SAMPLE_FMT_FLT;
175 
176  // p->excitation always points to the same position in p->excitation_buf
177  p->excitation = &p->excitation_buf[PITCH_DELAY_MAX + LP_FILTER_ORDER + 1];
178 
179  for (i = 0; i < LP_FILTER_ORDER; i++) {
180  p->prev_lsp_sub4[i] = lsp_sub4_init[i] * 1000 / (float)(1 << 15);
181  p->lsf_avg[i] = p->lsf_q[3][i] = lsp_avg_init[i] / (float)(1 << 15);
182  }
183 
184  for (i = 0; i < 4; i++)
185  p->prediction_error[i] = MIN_ENERGY;
186 
187  ff_acelp_filter_init(&p->acelpf_ctx);
188  ff_acelp_vectors_init(&p->acelpv_ctx);
189  ff_celp_filter_init(&p->celpf_ctx);
190  ff_celp_math_init(&p->celpm_ctx);
191 
192  return 0;
193 }
194 
195 
196 /**
197  * Unpack an RFC4867 speech frame into the AMR frame mode and parameters.
198  *
199  * The order of speech bits is specified by 3GPP TS 26.101.
200  *
201  * @param p the context
202  * @param buf pointer to the input buffer
203  * @param buf_size size of the input buffer
204  *
205  * @return the frame mode
206  */
207  static enum Mode unpack_bitstream(AMRContext *p, const uint8_t *buf,
208  int buf_size)
209 {
210  enum Mode mode;
211 
212  // Decode the first octet.
213  mode = buf[0] >> 3 & 0x0F; // frame type
214  p->bad_frame_indicator = (buf[0] & 0x4) != 0x4; // quality bit
215 
216  if (mode >= N_MODES || buf_size < frame_sizes_nb[mode] + 1) {
217  return NO_DATA;
218  }
219 
220  if (mode < MODE_DTX)
221  ff_amr_bit_reorder((uint16_t *) &p->frame, sizeof(AMRNBFrame), buf + 1,
222  amr_unpacking_bitmaps_per_mode[mode]);
223 
224  return mode;
225 }
226 
227 
228 /// @name AMR pitch LPC coefficient decoding functions
229 /// @{
230 
231 /**
232  * Interpolate the LSF vector (used for fixed gain smoothing).
233  * The interpolation is done over all four subframes even in MODE_12k2.
234  *
235  * @param[in] ctx The Context
236  * @param[in,out] lsf_q LSFs in [0,1] for each subframe
237  * @param[in] lsf_new New LSFs in [0,1] for subframe 4
238  */
239  static void interpolate_lsf(ACELPVContext *ctx, float lsf_q[4][LP_FILTER_ORDER], float *lsf_new)
240 {
241  int i;
242 
243  for (i = 0; i < 4; i++)
244  ctx->weighted_vector_sumf(lsf_q[i], lsf_q[3], lsf_new,
245  0.25 * (3 - i), 0.25 * (i + 1),
246  LP_FILTER_ORDER);
247 }
248 
249 /**
250  * Decode a set of 5 split-matrix quantized lsf indexes into an lsp vector.
251  *
252  * @param p the context
253  * @param lsp output LSP vector
254  * @param lsf_no_r LSF vector without the residual vector added
255  * @param lsf_quantizer pointers to LSF dictionary tables
256  * @param quantizer_offset offset in tables
257  * @param sign for the 3 dictionary table
258  * @param update store data for computing the next frame's LSFs
259  */
260  static void lsf2lsp_for_mode12k2(AMRContext *p, double lsp[LP_FILTER_ORDER],
261  const float lsf_no_r[LP_FILTER_ORDER],
262  const int16_t *lsf_quantizer[5],
263  const int quantizer_offset,
264  const int sign, const int update)
265 {
266  int16_t lsf_r[LP_FILTER_ORDER]; // residual LSF vector
267  float lsf_q[LP_FILTER_ORDER]; // quantified LSF vector
268  int i;
269 
270  for (i = 0; i < LP_FILTER_ORDER >> 1; i++)
271  memcpy(&lsf_r[i << 1], &lsf_quantizer[i][quantizer_offset],
272  2 * sizeof(*lsf_r));
273 
274  if (sign) {
275  lsf_r[4] *= -1;
276  lsf_r[5] *= -1;
277  }
278 
279  if (update)
280  memcpy(p->prev_lsf_r, lsf_r, LP_FILTER_ORDER * sizeof(*lsf_r));
281 
282  for (i = 0; i < LP_FILTER_ORDER; i++)
283  lsf_q[i] = lsf_r[i] * (LSF_R_FAC / 8000.0) + lsf_no_r[i] * (1.0 / 8000.0);
284 
285  ff_set_min_dist_lsf(lsf_q, MIN_LSF_SPACING, LP_FILTER_ORDER);
286 
287  if (update)
288  interpolate_lsf(&p->acelpv_ctx, p->lsf_q, lsf_q);
289 
290  ff_acelp_lsf2lspd(lsp, lsf_q, LP_FILTER_ORDER);
291 }
292 
293 /**
294  * Decode a set of 5 split-matrix quantized lsf indexes into 2 lsp vectors.
295  *
296  * @param p pointer to the AMRContext
297  */
298  static void lsf2lsp_5(AMRContext *p)
299 {
300  const uint16_t *lsf_param = p->frame.lsf;
301  float lsf_no_r[LP_FILTER_ORDER]; // LSFs without the residual vector
302  const int16_t *lsf_quantizer[5];
303  int i;
304 
305  lsf_quantizer[0] = lsf_5_1[lsf_param[0]];
306  lsf_quantizer[1] = lsf_5_2[lsf_param[1]];
307  lsf_quantizer[2] = lsf_5_3[lsf_param[2] >> 1];
308  lsf_quantizer[3] = lsf_5_4[lsf_param[3]];
309  lsf_quantizer[4] = lsf_5_5[lsf_param[4]];
310 
311  for (i = 0; i < LP_FILTER_ORDER; i++)
312  lsf_no_r[i] = p->prev_lsf_r[i] * LSF_R_FAC * PRED_FAC_MODE_12k2 + lsf_5_mean[i];
313 
314  lsf2lsp_for_mode12k2(p, p->lsp[1], lsf_no_r, lsf_quantizer, 0, lsf_param[2] & 1, 0);
315  lsf2lsp_for_mode12k2(p, p->lsp[3], lsf_no_r, lsf_quantizer, 2, lsf_param[2] & 1, 1);
316 
317  // interpolate LSP vectors at subframes 1 and 3
318  weighted_vector_sumd(p->lsp[0], p->prev_lsp_sub4, p->lsp[1], 0.5, 0.5, LP_FILTER_ORDER);
319  weighted_vector_sumd(p->lsp[2], p->lsp[1] , p->lsp[3], 0.5, 0.5, LP_FILTER_ORDER);
320 }
321 
322 /**
323  * Decode a set of 3 split-matrix quantized lsf indexes into an lsp vector.
324  *
325  * @param p pointer to the AMRContext
326  */
327  static void lsf2lsp_3(AMRContext *p)
328 {
329  const uint16_t *lsf_param = p->frame.lsf;
330  int16_t lsf_r[LP_FILTER_ORDER]; // residual LSF vector
331  float lsf_q[LP_FILTER_ORDER]; // quantified LSF vector
332  const int16_t *lsf_quantizer;
333  int i, j;
334 
335  lsf_quantizer = (p->cur_frame_mode == MODE_7k95 ? lsf_3_1_MODE_7k95 : lsf_3_1)[lsf_param[0]];
336  memcpy(lsf_r, lsf_quantizer, 3 * sizeof(*lsf_r));
337 
338  lsf_quantizer = lsf_3_2[lsf_param[1] << (p->cur_frame_mode <= MODE_5k15)];
339  memcpy(lsf_r + 3, lsf_quantizer, 3 * sizeof(*lsf_r));
340 
341  lsf_quantizer = (p->cur_frame_mode <= MODE_5k15 ? lsf_3_3_MODE_5k15 : lsf_3_3)[lsf_param[2]];
342  memcpy(lsf_r + 6, lsf_quantizer, 4 * sizeof(*lsf_r));
343 
344  // calculate mean-removed LSF vector and add mean
345  for (i = 0; i < LP_FILTER_ORDER; i++)
346  lsf_q[i] = (lsf_r[i] + p->prev_lsf_r[i] * pred_fac[i]) * (LSF_R_FAC / 8000.0) + lsf_3_mean[i] * (1.0 / 8000.0);
347 
348  ff_set_min_dist_lsf(lsf_q, MIN_LSF_SPACING, LP_FILTER_ORDER);
349 
350  // store data for computing the next frame's LSFs
351  interpolate_lsf(&p->acelpv_ctx, p->lsf_q, lsf_q);
352  memcpy(p->prev_lsf_r, lsf_r, LP_FILTER_ORDER * sizeof(*lsf_r));
353 
354  ff_acelp_lsf2lspd(p->lsp[3], lsf_q, LP_FILTER_ORDER);
355 
356  // interpolate LSP vectors at subframes 1, 2 and 3
357  for (i = 1; i <= 3; i++)
358  for(j = 0; j < LP_FILTER_ORDER; j++)
359  p->lsp[i-1][j] = p->prev_lsp_sub4[j] +
360  (p->lsp[3][j] - p->prev_lsp_sub4[j]) * 0.25 * i;
361 }
362 
363 /// @}
364 
365 
366 /// @name AMR pitch vector decoding functions
367 /// @{
368 
369 /**
370  * Like ff_decode_pitch_lag(), but with 1/6 resolution
371  */
372  static void decode_pitch_lag_1_6(int *lag_int, int *lag_frac, int pitch_index,
373  const int prev_lag_int, const int subframe)
374 {
375  if (subframe == 0 || subframe == 2) {
376  if (pitch_index < 463) {
377  *lag_int = (pitch_index + 107) * 10923 >> 16;
378  *lag_frac = pitch_index - *lag_int * 6 + 105;
379  } else {
380  *lag_int = pitch_index - 368;
381  *lag_frac = 0;
382  }
383  } else {
384  *lag_int = ((pitch_index + 5) * 10923 >> 16) - 1;
385  *lag_frac = pitch_index - *lag_int * 6 - 3;
386  *lag_int += av_clip(prev_lag_int - 5, PITCH_LAG_MIN_MODE_12k2,
387  PITCH_DELAY_MAX - 9);
388  }
389 }
390 
391  static void decode_pitch_vector(AMRContext *p,
392  const AMRNBSubframe *amr_subframe,
393  const int subframe)
394 {
395  int pitch_lag_int, pitch_lag_frac;
396  enum Mode mode = p->cur_frame_mode;
397 
398  if (p->cur_frame_mode == MODE_12k2) {
399  decode_pitch_lag_1_6(&pitch_lag_int, &pitch_lag_frac,
400  amr_subframe->p_lag, p->pitch_lag_int,
401  subframe);
402  } else {
403  ff_decode_pitch_lag(&pitch_lag_int, &pitch_lag_frac,
404  amr_subframe->p_lag,
405  p->pitch_lag_int, subframe,
406  mode != MODE_4k75 && mode != MODE_5k15,
407  mode <= MODE_6k7 ? 4 : (mode == MODE_7k95 ? 5 : 6));
408  pitch_lag_frac *= 2;
409  }
410 
411  p->pitch_lag_int = pitch_lag_int; // store previous lag in a uint8_t
412 
413  pitch_lag_int += pitch_lag_frac > 0;
414 
415  /* Calculate the pitch vector by interpolating the past excitation at the
416  pitch lag using a b60 hamming windowed sinc function. */
417  p->acelpf_ctx.acelp_interpolatef(p->excitation,
418  p->excitation + 1 - pitch_lag_int,
419  ff_b60_sinc, 6,
420  pitch_lag_frac + 6 - 6*(pitch_lag_frac > 0),
421  10, AMR_SUBFRAME_SIZE);
422 
423  memcpy(p->pitch_vector, p->excitation, AMR_SUBFRAME_SIZE * sizeof(float));
424 }
425 
426 /// @}
427 
428 
429 /// @name AMR algebraic code book (fixed) vector decoding functions
430 /// @{
431 
432 /**
433  * Decode a 10-bit algebraic codebook index from a 10.2 kbit/s frame.
434  */
435  static void decode_10bit_pulse(int code, int pulse_position[8],
436  int i1, int i2, int i3)
437 {
438  // coded using 7+3 bits with the 3 LSBs being, individually, the LSB of 1 of
439  // the 3 pulses and the upper 7 bits being coded in base 5
440  const uint8_t *positions = base_five_table[code >> 3];
441  pulse_position[i1] = (positions[2] << 1) + ( code & 1);
442  pulse_position[i2] = (positions[1] << 1) + ((code >> 1) & 1);
443  pulse_position[i3] = (positions[0] << 1) + ((code >> 2) & 1);
444 }
445 
446 /**
447  * Decode the algebraic codebook index to pulse positions and signs and
448  * construct the algebraic codebook vector for MODE_10k2.
449  *
450  * @param fixed_index positions of the eight pulses
451  * @param fixed_sparse pointer to the algebraic codebook vector
452  */
453  static void decode_8_pulses_31bits(const int16_t *fixed_index,
454  AMRFixed *fixed_sparse)
455 {
456  int pulse_position[8];
457  int i, temp;
458 
459  decode_10bit_pulse(fixed_index[4], pulse_position, 0, 4, 1);
460  decode_10bit_pulse(fixed_index[5], pulse_position, 2, 6, 5);
461 
462  // coded using 5+2 bits with the 2 LSBs being, individually, the LSB of 1 of
463  // the 2 pulses and the upper 5 bits being coded in base 5
464  temp = ((fixed_index[6] >> 2) * 25 + 12) >> 5;
465  pulse_position[3] = temp % 5;
466  pulse_position[7] = temp / 5;
467  if (pulse_position[7] & 1)
468  pulse_position[3] = 4 - pulse_position[3];
469  pulse_position[3] = (pulse_position[3] << 1) + ( fixed_index[6] & 1);
470  pulse_position[7] = (pulse_position[7] << 1) + ((fixed_index[6] >> 1) & 1);
471 
472  fixed_sparse->n = 8;
473  for (i = 0; i < 4; i++) {
474  const int pos1 = (pulse_position[i] << 2) + i;
475  const int pos2 = (pulse_position[i + 4] << 2) + i;
476  const float sign = fixed_index[i] ? -1.0 : 1.0;
477  fixed_sparse->x[i ] = pos1;
478  fixed_sparse->x[i + 4] = pos2;
479  fixed_sparse->y[i ] = sign;
480  fixed_sparse->y[i + 4] = pos2 < pos1 ? -sign : sign;
481  }
482 }
483 
484 /**
485  * Decode the algebraic codebook index to pulse positions and signs,
486  * then construct the algebraic codebook vector.
487  *
488  * nb of pulses | bits encoding pulses
489  * For MODE_4k75 or MODE_5k15, 2 | 1-3, 4-6, 7
490  * MODE_5k9, 2 | 1, 2-4, 5-6, 7-9
491  * MODE_6k7, 3 | 1-3, 4, 5-7, 8, 9-11
492  * MODE_7k4 or MODE_7k95, 4 | 1-3, 4-6, 7-9, 10, 11-13
493  *
494  * @param fixed_sparse pointer to the algebraic codebook vector
495  * @param pulses algebraic codebook indexes
496  * @param mode mode of the current frame
497  * @param subframe current subframe number
498  */
499  static void decode_fixed_sparse(AMRFixed *fixed_sparse, const uint16_t *pulses,
500  const enum Mode mode, const int subframe)
501 {
502  av_assert1(MODE_4k75 <= (signed)mode && mode <= MODE_12k2);
503 
504  if (mode == MODE_12k2) {
505  ff_decode_10_pulses_35bits(pulses, fixed_sparse, gray_decode, 5, 3);
506  } else if (mode == MODE_10k2) {
507  decode_8_pulses_31bits(pulses, fixed_sparse);
508  } else {
509  int *pulse_position = fixed_sparse->x;
510  int i, pulse_subset;
511  const int fixed_index = pulses[0];
512 
513  if (mode <= MODE_5k15) {
514  pulse_subset = ((fixed_index >> 3) & 8) + (subframe << 1);
515  pulse_position[0] = ( fixed_index & 7) * 5 + track_position[pulse_subset];
516  pulse_position[1] = ((fixed_index >> 3) & 7) * 5 + track_position[pulse_subset + 1];
517  fixed_sparse->n = 2;
518  } else if (mode == MODE_5k9) {
519  pulse_subset = ((fixed_index & 1) << 1) + 1;
520  pulse_position[0] = ((fixed_index >> 1) & 7) * 5 + pulse_subset;
521  pulse_subset = (fixed_index >> 4) & 3;
522  pulse_position[1] = ((fixed_index >> 6) & 7) * 5 + pulse_subset + (pulse_subset == 3 ? 1 : 0);
523  fixed_sparse->n = pulse_position[0] == pulse_position[1] ? 1 : 2;
524  } else if (mode == MODE_6k7) {
525  pulse_position[0] = (fixed_index & 7) * 5;
526  pulse_subset = (fixed_index >> 2) & 2;
527  pulse_position[1] = ((fixed_index >> 4) & 7) * 5 + pulse_subset + 1;
528  pulse_subset = (fixed_index >> 6) & 2;
529  pulse_position[2] = ((fixed_index >> 8) & 7) * 5 + pulse_subset + 2;
530  fixed_sparse->n = 3;
531  } else { // mode <= MODE_7k95
532  pulse_position[0] = gray_decode[ fixed_index & 7];
533  pulse_position[1] = gray_decode[(fixed_index >> 3) & 7] + 1;
534  pulse_position[2] = gray_decode[(fixed_index >> 6) & 7] + 2;
535  pulse_subset = (fixed_index >> 9) & 1;
536  pulse_position[3] = gray_decode[(fixed_index >> 10) & 7] + pulse_subset + 3;
537  fixed_sparse->n = 4;
538  }
539  for (i = 0; i < fixed_sparse->n; i++)
540  fixed_sparse->y[i] = (pulses[1] >> i) & 1 ? 1.0 : -1.0;
541  }
542 }
543 
544 /**
545  * Apply pitch lag to obtain the sharpened fixed vector (section 6.1.2)
546  *
547  * @param p the context
548  * @param subframe unpacked amr subframe
549  * @param mode mode of the current frame
550  * @param fixed_sparse sparse representation of the fixed vector
551  */
552  static void pitch_sharpening(AMRContext *p, int subframe, enum Mode mode,
553  AMRFixed *fixed_sparse)
554 {
555  // The spec suggests the current pitch gain is always used, but in other
556  // modes the pitch and codebook gains are jointly quantized (sec 5.8.2)
557  // so the codebook gain cannot depend on the quantized pitch gain.
558  if (mode == MODE_12k2)
559  p->beta = FFMIN(p->pitch_gain[4], 1.0);
560 
561  fixed_sparse->pitch_lag = p->pitch_lag_int;
562  fixed_sparse->pitch_fac = p->beta;
563 
564  // Save pitch sharpening factor for the next subframe
565  // MODE_4k75 only updates on the 2nd and 4th subframes - this follows from
566  // the fact that the gains for two subframes are jointly quantized.
567  if (mode != MODE_4k75 || subframe & 1)
568  p->beta = av_clipf(p->pitch_gain[4], 0.0, SHARP_MAX);
569 }
570 /// @}
571 
572 
573 /// @name AMR gain decoding functions
574 /// @{
575 
576 /**
577  * fixed gain smoothing
578  * Note that where the spec specifies the "spectrum in the q domain"
579  * in section 6.1.4, in fact frequencies should be used.
580  *
581  * @param p the context
582  * @param lsf LSFs for the current subframe, in the range [0,1]
583  * @param lsf_avg averaged LSFs
584  * @param mode mode of the current frame
585  *
586  * @return fixed gain smoothed
587  */
588  static float fixed_gain_smooth(AMRContext *p , const float *lsf,
589  const float *lsf_avg, const enum Mode mode)
590 {
591  float diff = 0.0;
592  int i;
593 
594  for (i = 0; i < LP_FILTER_ORDER; i++)
595  diff += fabs(lsf_avg[i] - lsf[i]) / lsf_avg[i];
596 
597  // If diff is large for ten subframes, disable smoothing for a 40-subframe
598  // hangover period.
599  p->diff_count++;
600  if (diff <= 0.65)
601  p->diff_count = 0;
602 
603  if (p->diff_count > 10) {
604  p->hang_count = 0;
605  p->diff_count--; // don't let diff_count overflow
606  }
607 
608  if (p->hang_count < 40) {
609  p->hang_count++;
610  } else if (mode < MODE_7k4 || mode == MODE_10k2) {
611  const float smoothing_factor = av_clipf(4.0 * diff - 1.6, 0.0, 1.0);
612  const float fixed_gain_mean = (p->fixed_gain[0] + p->fixed_gain[1] +
613  p->fixed_gain[2] + p->fixed_gain[3] +
614  p->fixed_gain[4]) * 0.2;
615  return smoothing_factor * p->fixed_gain[4] +
616  (1.0 - smoothing_factor) * fixed_gain_mean;
617  }
618  return p->fixed_gain[4];
619 }
620 
621 /**
622  * Decode pitch gain and fixed gain factor (part of section 6.1.3).
623  *
624  * @param p the context
625  * @param amr_subframe unpacked amr subframe
626  * @param mode mode of the current frame
627  * @param subframe current subframe number
628  * @param fixed_gain_factor decoded gain correction factor
629  */
630  static void decode_gains(AMRContext *p, const AMRNBSubframe *amr_subframe,
631  const enum Mode mode, const int subframe,
632  float *fixed_gain_factor)
633 {
634  if (mode == MODE_12k2 || mode == MODE_7k95) {
635  p->pitch_gain[4] = qua_gain_pit [amr_subframe->p_gain ]
636  * (1.0 / 16384.0);
637  *fixed_gain_factor = qua_gain_code[amr_subframe->fixed_gain]
638  * (1.0 / 2048.0);
639  } else {
640  const uint16_t *gains;
641 
642  if (mode >= MODE_6k7) {
643  gains = gains_high[amr_subframe->p_gain];
644  } else if (mode >= MODE_5k15) {
645  gains = gains_low [amr_subframe->p_gain];
646  } else {
647  // gain index is only coded in subframes 0,2 for MODE_4k75
648  gains = gains_MODE_4k75[(p->frame.subframe[subframe & 2].p_gain << 1) + (subframe & 1)];
649  }
650 
651  p->pitch_gain[4] = gains[0] * (1.0 / 16384.0);
652  *fixed_gain_factor = gains[1] * (1.0 / 4096.0);
653  }
654 }
655 
656 /// @}
657 
658 
659 /// @name AMR preprocessing functions
660 /// @{
661 
662 /**
663  * Circularly convolve a sparse fixed vector with a phase dispersion impulse
664  * response filter (D.6.2 of G.729 and 6.1.5 of AMR).
665  *
666  * @param out vector with filter applied
667  * @param in source vector
668  * @param filter phase filter coefficients
669  *
670  * out[n] = sum(i,0,len-1){ in[i] * filter[(len + n - i)%len] }
671  */
672  static void apply_ir_filter(float *out, const AMRFixed *in,
673  const float *filter)
674 {
675  float filter1[AMR_SUBFRAME_SIZE], ///< filters at pitch lag*1 and *2
676  filter2[AMR_SUBFRAME_SIZE];
677  int lag = in->pitch_lag;
678  float fac = in->pitch_fac;
679  int i;
680 
681  if (lag < AMR_SUBFRAME_SIZE) {
682  ff_celp_circ_addf(filter1, filter, filter, lag, fac,
683  AMR_SUBFRAME_SIZE);
684 
685  if (lag < AMR_SUBFRAME_SIZE >> 1)
686  ff_celp_circ_addf(filter2, filter, filter1, lag, fac,
687  AMR_SUBFRAME_SIZE);
688  }
689 
690  memset(out, 0, sizeof(float) * AMR_SUBFRAME_SIZE);
691  for (i = 0; i < in->n; i++) {
692  int x = in->x[i];
693  float y = in->y[i];
694  const float *filterp;
695 
696  if (x >= AMR_SUBFRAME_SIZE - lag) {
697  filterp = filter;
698  } else if (x >= AMR_SUBFRAME_SIZE - (lag << 1)) {
699  filterp = filter1;
700  } else
701  filterp = filter2;
702 
703  ff_celp_circ_addf(out, out, filterp, x, y, AMR_SUBFRAME_SIZE);
704  }
705 }
706 
707 /**
708  * Reduce fixed vector sparseness by smoothing with one of three IR filters.
709  * Also know as "adaptive phase dispersion".
710  *
711  * This implements 3GPP TS 26.090 section 6.1(5).
712  *
713  * @param p the context
714  * @param fixed_sparse algebraic codebook vector
715  * @param fixed_vector unfiltered fixed vector
716  * @param fixed_gain smoothed gain
717  * @param out space for modified vector if necessary
718  */
719  static const float *anti_sparseness(AMRContext *p, AMRFixed *fixed_sparse,
720  const float *fixed_vector,
721  float fixed_gain, float *out)
722 {
723  int ir_filter_nr;
724 
725  if (p->pitch_gain[4] < 0.6) {
726  ir_filter_nr = 0; // strong filtering
727  } else if (p->pitch_gain[4] < 0.9) {
728  ir_filter_nr = 1; // medium filtering
729  } else
730  ir_filter_nr = 2; // no filtering
731 
732  // detect 'onset'
733  if (fixed_gain > 2.0 * p->prev_sparse_fixed_gain) {
734  p->ir_filter_onset = 2;
735  } else if (p->ir_filter_onset)
736  p->ir_filter_onset--;
737 
738  if (!p->ir_filter_onset) {
739  int i, count = 0;
740 
741  for (i = 0; i < 5; i++)
742  if (p->pitch_gain[i] < 0.6)
743  count++;
744  if (count > 2)
745  ir_filter_nr = 0;
746 
747  if (ir_filter_nr > p->prev_ir_filter_nr + 1)
748  ir_filter_nr--;
749  } else if (ir_filter_nr < 2)
750  ir_filter_nr++;
751 
752  // Disable filtering for very low level of fixed_gain.
753  // Note this step is not specified in the technical description but is in
754  // the reference source in the function Ph_disp.
755  if (fixed_gain < 5.0)
756  ir_filter_nr = 2;
757 
758  if (p->cur_frame_mode != MODE_7k4 && p->cur_frame_mode < MODE_10k2
759  && ir_filter_nr < 2) {
760  apply_ir_filter(out, fixed_sparse,
761  (p->cur_frame_mode == MODE_7k95 ?
762  ir_filters_lookup_MODE_7k95 :
763  ir_filters_lookup)[ir_filter_nr]);
764  fixed_vector = out;
765  }
766 
767  // update ir filter strength history
768  p->prev_ir_filter_nr = ir_filter_nr;
769  p->prev_sparse_fixed_gain = fixed_gain;
770 
771  return fixed_vector;
772 }
773 
774 /// @}
775 
776 
777 /// @name AMR synthesis functions
778 /// @{
779 
780 /**
781  * Conduct 10th order linear predictive coding synthesis.
782  *
783  * @param p pointer to the AMRContext
784  * @param lpc pointer to the LPC coefficients
785  * @param fixed_gain fixed codebook gain for synthesis
786  * @param fixed_vector algebraic codebook vector
787  * @param samples pointer to the output speech samples
788  * @param overflow 16-bit overflow flag
789  */
790  static int synthesis(AMRContext *p, float *lpc,
791  float fixed_gain, const float *fixed_vector,
792  float *samples, uint8_t overflow)
793 {
794  int i;
795  float excitation[AMR_SUBFRAME_SIZE];
796 
797  // if an overflow has been detected, the pitch vector is scaled down by a
798  // factor of 4
799  if (overflow)
800  for (i = 0; i < AMR_SUBFRAME_SIZE; i++)
801  p->pitch_vector[i] *= 0.25;
802 
803  p->acelpv_ctx.weighted_vector_sumf(excitation, p->pitch_vector, fixed_vector,
804  p->pitch_gain[4], fixed_gain, AMR_SUBFRAME_SIZE);
805 
806  // emphasize pitch vector contribution
807  if (p->pitch_gain[4] > 0.5 && !overflow) {
808  float energy = p->celpm_ctx.dot_productf(excitation, excitation,
809  AMR_SUBFRAME_SIZE);
810  float pitch_factor =
811  p->pitch_gain[4] *
812  (p->cur_frame_mode == MODE_12k2 ?
813  0.25 * FFMIN(p->pitch_gain[4], 1.0) :
814  0.5 * FFMIN(p->pitch_gain[4], SHARP_MAX));
815 
816  for (i = 0; i < AMR_SUBFRAME_SIZE; i++)
817  excitation[i] += pitch_factor * p->pitch_vector[i];
818 
819  ff_scale_vector_to_given_sum_of_squares(excitation, excitation, energy,
820  AMR_SUBFRAME_SIZE);
821  }
822 
823  p->celpf_ctx.celp_lp_synthesis_filterf(samples, lpc, excitation,
824  AMR_SUBFRAME_SIZE,
825  LP_FILTER_ORDER);
826 
827  // detect overflow
828  for (i = 0; i < AMR_SUBFRAME_SIZE; i++)
829  if (fabsf(samples[i]) > AMR_SAMPLE_BOUND) {
830  return 1;
831  }
832 
833  return 0;
834 }
835 
836 /// @}
837 
838 
839 /// @name AMR update functions
840 /// @{
841 
842 /**
843  * Update buffers and history at the end of decoding a subframe.
844  *
845  * @param p pointer to the AMRContext
846  */
847  static void update_state(AMRContext *p)
848 {
849  memcpy(p->prev_lsp_sub4, p->lsp[3], LP_FILTER_ORDER * sizeof(p->lsp[3][0]));
850 
851  memmove(&p->excitation_buf[0], &p->excitation_buf[AMR_SUBFRAME_SIZE],
852  (PITCH_DELAY_MAX + LP_FILTER_ORDER + 1) * sizeof(float));
853 
854  memmove(&p->pitch_gain[0], &p->pitch_gain[1], 4 * sizeof(float));
855  memmove(&p->fixed_gain[0], &p->fixed_gain[1], 4 * sizeof(float));
856 
857  memmove(&p->samples_in[0], &p->samples_in[AMR_SUBFRAME_SIZE],
858  LP_FILTER_ORDER * sizeof(float));
859 }
860 
861 /// @}
862 
863 
864 /// @name AMR Postprocessing functions
865 /// @{
866 
867 /**
868  * Get the tilt factor of a formant filter from its transfer function
869  *
870  * @param p The Context
871  * @param lpc_n LP_FILTER_ORDER coefficients of the numerator
872  * @param lpc_d LP_FILTER_ORDER coefficients of the denominator
873  */
874  static float tilt_factor(AMRContext *p, float *lpc_n, float *lpc_d)
875 {
876  float rh0, rh1; // autocorrelation at lag 0 and 1
877 
878  // LP_FILTER_ORDER prior zeros are needed for ff_celp_lp_synthesis_filterf
879  float impulse_buffer[LP_FILTER_ORDER + AMR_TILT_RESPONSE] = { 0 };
880  float *hf = impulse_buffer + LP_FILTER_ORDER; // start of impulse response
881 
882  hf[0] = 1.0;
883  memcpy(hf + 1, lpc_n, sizeof(float) * LP_FILTER_ORDER);
884  p->celpf_ctx.celp_lp_synthesis_filterf(hf, lpc_d, hf,
885  AMR_TILT_RESPONSE,
886  LP_FILTER_ORDER);
887 
888  rh0 = p->celpm_ctx.dot_productf(hf, hf, AMR_TILT_RESPONSE);
889  rh1 = p->celpm_ctx.dot_productf(hf, hf + 1, AMR_TILT_RESPONSE - 1);
890 
891  // The spec only specifies this check for 12.2 and 10.2 kbit/s
892  // modes. But in the ref source the tilt is always non-negative.
893  return rh1 >= 0.0 ? rh1 / rh0 * AMR_TILT_GAMMA_T : 0.0;
894 }
895 
896 /**
897  * Perform adaptive post-filtering to enhance the quality of the speech.
898  * See section 6.2.1.
899  *
900  * @param p pointer to the AMRContext
901  * @param lpc interpolated LP coefficients for this subframe
902  * @param buf_out output of the filter
903  */
904  static void postfilter(AMRContext *p, float *lpc, float *buf_out)
905 {
906  int i;
907  float *samples = p->samples_in + LP_FILTER_ORDER; // Start of input
908 
909  float speech_gain = p->celpm_ctx.dot_productf(samples, samples,
910  AMR_SUBFRAME_SIZE);
911 
912  float pole_out[AMR_SUBFRAME_SIZE + LP_FILTER_ORDER]; // Output of pole filter
913  const float *gamma_n, *gamma_d; // Formant filter factor table
914  float lpc_n[LP_FILTER_ORDER], lpc_d[LP_FILTER_ORDER]; // Transfer function coefficients
915 
916  if (p->cur_frame_mode == MODE_12k2 || p->cur_frame_mode == MODE_10k2) {
917  gamma_n = ff_pow_0_7;
918  gamma_d = ff_pow_0_75;
919  } else {
920  gamma_n = ff_pow_0_55;
921  gamma_d = ff_pow_0_7;
922  }
923 
924  for (i = 0; i < LP_FILTER_ORDER; i++) {
925  lpc_n[i] = lpc[i] * gamma_n[i];
926  lpc_d[i] = lpc[i] * gamma_d[i];
927  }
928 
929  memcpy(pole_out, p->postfilter_mem, sizeof(float) * LP_FILTER_ORDER);
930  p->celpf_ctx.celp_lp_synthesis_filterf(pole_out + LP_FILTER_ORDER, lpc_d, samples,
931  AMR_SUBFRAME_SIZE, LP_FILTER_ORDER);
932  memcpy(p->postfilter_mem, pole_out + AMR_SUBFRAME_SIZE,
933  sizeof(float) * LP_FILTER_ORDER);
934 
935  p->celpf_ctx.celp_lp_zero_synthesis_filterf(buf_out, lpc_n,
936  pole_out + LP_FILTER_ORDER,
937  AMR_SUBFRAME_SIZE, LP_FILTER_ORDER);
938 
939  ff_tilt_compensation(&p->tilt_mem, tilt_factor(p, lpc_n, lpc_d), buf_out,
940  AMR_SUBFRAME_SIZE);
941 
942  ff_adaptive_gain_control(buf_out, buf_out, speech_gain, AMR_SUBFRAME_SIZE,
943  AMR_AGC_ALPHA, &p->postfilter_agc);
944 }
945 
946 /// @}
947 
948  static int amrnb_decode_frame(AVCodecContext *avctx, void *data,
949  int *got_frame_ptr, AVPacket *avpkt)
950 {
951 
952  AMRContext *p = avctx->priv_data; // pointer to private data
953  AVFrame *frame = data;
954  const uint8_t *buf = avpkt->data;
955  int buf_size = avpkt->size;
956  float *buf_out; // pointer to the output data buffer
957  int i, subframe, ret;
958  float fixed_gain_factor;
959  AMRFixed fixed_sparse = {0}; // fixed vector up to anti-sparseness processing
960  float spare_vector[AMR_SUBFRAME_SIZE]; // extra stack space to hold result from anti-sparseness processing
961  float synth_fixed_gain; // the fixed gain that synthesis should use
962  const float *synth_fixed_vector; // pointer to the fixed vector that synthesis should use
963 
964  /* get output buffer */
965  frame->nb_samples = AMR_BLOCK_SIZE;
966  if ((ret = ff_get_buffer(avctx, frame, 0)) < 0)
967  return ret;
968  buf_out = (float *)frame->data[0];
969 
970  p->cur_frame_mode = unpack_bitstream(p, buf, buf_size);
971  if (p->cur_frame_mode == NO_DATA) {
972  av_log(avctx, AV_LOG_ERROR, "Corrupt bitstream\n");
973  return AVERROR_INVALIDDATA;
974  }
975  if (p->cur_frame_mode == MODE_DTX) {
976  avpriv_report_missing_feature(avctx, "dtx mode");
977  av_log(avctx, AV_LOG_INFO, "Note: libopencore_amrnb supports dtx\n");
978  return AVERROR_PATCHWELCOME;
979  }
980 
981  if (p->cur_frame_mode == MODE_12k2) {
982  lsf2lsp_5(p);
983  } else
984  lsf2lsp_3(p);
985 
986  for (i = 0; i < 4; i++)
987  ff_acelp_lspd2lpc(p->lsp[i], p->lpc[i], 5);
988 
989  for (subframe = 0; subframe < 4; subframe++) {
990  const AMRNBSubframe *amr_subframe = &p->frame.subframe[subframe];
991 
992  decode_pitch_vector(p, amr_subframe, subframe);
993 
994  decode_fixed_sparse(&fixed_sparse, amr_subframe->pulses,
995  p->cur_frame_mode, subframe);
996 
997  // The fixed gain (section 6.1.3) depends on the fixed vector
998  // (section 6.1.2), but the fixed vector calculation uses
999  // pitch sharpening based on the on the pitch gain (section 6.1.3).
1000  // So the correct order is: pitch gain, pitch sharpening, fixed gain.
1001  decode_gains(p, amr_subframe, p->cur_frame_mode, subframe,
1002  &fixed_gain_factor);
1003 
1004  pitch_sharpening(p, subframe, p->cur_frame_mode, &fixed_sparse);
1005 
1006  if (fixed_sparse.pitch_lag == 0) {
1007  av_log(avctx, AV_LOG_ERROR, "The file is corrupted, pitch_lag = 0 is not allowed\n");
1008  return AVERROR_INVALIDDATA;
1009  }
1010  ff_set_fixed_vector(p->fixed_vector, &fixed_sparse, 1.0,
1011  AMR_SUBFRAME_SIZE);
1012 
1013  p->fixed_gain[4] =
1014  ff_amr_set_fixed_gain(fixed_gain_factor,
1015  p->celpm_ctx.dot_productf(p->fixed_vector,
1016  p->fixed_vector,
1017  AMR_SUBFRAME_SIZE) /
1018  AMR_SUBFRAME_SIZE,
1019  p->prediction_error,
1020  energy_mean[p->cur_frame_mode], energy_pred_fac);
1021 
1022  // The excitation feedback is calculated without any processing such
1023  // as fixed gain smoothing. This isn't mentioned in the specification.
1024  for (i = 0; i < AMR_SUBFRAME_SIZE; i++)
1025  p->excitation[i] *= p->pitch_gain[4];
1026  ff_set_fixed_vector(p->excitation, &fixed_sparse, p->fixed_gain[4],
1027  AMR_SUBFRAME_SIZE);
1028 
1029  // In the ref decoder, excitation is stored with no fractional bits.
1030  // This step prevents buzz in silent periods. The ref encoder can
1031  // emit long sequences with pitch factor greater than one. This
1032  // creates unwanted feedback if the excitation vector is nonzero.
1033  // (e.g. test sequence T19_795.COD in 3GPP TS 26.074)
1034  for (i = 0; i < AMR_SUBFRAME_SIZE; i++)
1035  p->excitation[i] = truncf(p->excitation[i]);
1036 
1037  // Smooth fixed gain.
1038  // The specification is ambiguous, but in the reference source, the
1039  // smoothed value is NOT fed back into later fixed gain smoothing.
1040  synth_fixed_gain = fixed_gain_smooth(p, p->lsf_q[subframe],
1041  p->lsf_avg, p->cur_frame_mode);
1042 
1043  synth_fixed_vector = anti_sparseness(p, &fixed_sparse, p->fixed_vector,
1044  synth_fixed_gain, spare_vector);
1045 
1046  if (synthesis(p, p->lpc[subframe], synth_fixed_gain,
1047  synth_fixed_vector, &p->samples_in[LP_FILTER_ORDER], 0))
1048  // overflow detected -> rerun synthesis scaling pitch vector down
1049  // by a factor of 4, skipping pitch vector contribution emphasis
1050  // and adaptive gain control
1051  synthesis(p, p->lpc[subframe], synth_fixed_gain,
1052  synth_fixed_vector, &p->samples_in[LP_FILTER_ORDER], 1);
1053 
1054  postfilter(p, p->lpc[subframe], buf_out + subframe * AMR_SUBFRAME_SIZE);
1055 
1056  // update buffers and history
1057  ff_clear_fixed_vector(p->fixed_vector, &fixed_sparse, AMR_SUBFRAME_SIZE);
1058  update_state(p);
1059  }
1060 
1061  p->acelpf_ctx.acelp_apply_order_2_transfer_function(buf_out,
1062  buf_out, highpass_zeros,
1063  highpass_poles,
1064  highpass_gain * AMR_SAMPLE_SCALE,
1065  p->high_pass_mem, AMR_BLOCK_SIZE);
1066 
1067  /* Update averaged lsf vector (used for fixed gain smoothing).
1068  *
1069  * Note that lsf_avg should not incorporate the current frame's LSFs
1070  * for fixed_gain_smooth.
1071  * The specification has an incorrect formula: the reference decoder uses
1072  * qbar(n-1) rather than qbar(n) in section 6.1(4) equation 71. */
1073  p->acelpv_ctx.weighted_vector_sumf(p->lsf_avg, p->lsf_avg, p->lsf_q[3],
1074  0.84, 0.16, LP_FILTER_ORDER);
1075 
1076  *got_frame_ptr = 1;
1077 
1078  /* return the amount of bytes consumed if everything was OK */
1079  return frame_sizes_nb[p->cur_frame_mode] + 1; // +7 for rounding and +8 for TOC
1080 }
1081 
1082 
1083  AVCodec ff_amrnb_decoder = {
1084  .name = "amrnb",
1085  .long_name = NULL_IF_CONFIG_SMALL("AMR-NB (Adaptive Multi-Rate NarrowBand)"),
1086  .type = AVMEDIA_TYPE_AUDIO,
1087  .id = AV_CODEC_ID_AMR_NB,
1088  .priv_data_size = sizeof(AMRContext),
1089  .init = amrnb_decode_init,
1090  .decode = amrnb_decode_frame,
1091  .capabilities = AV_CODEC_CAP_DR1,
1092  .sample_fmts = (const enum AVSampleFormat[]){ AV_SAMPLE_FMT_FLT,
1093  AV_SAMPLE_FMT_NONE },
1094 };
AV_CODEC_ID_AMR_NB
Definition: avcodec.h:534
AMR_SAMPLE_SCALE
#define AMR_SAMPLE_SCALE
Scale from constructed speech to [-1,1].
Definition: amrnbdec.c:74
celp_filters.h
ff_decode_pitch_lag
void ff_decode_pitch_lag(int *lag_int, int *lag_frac, int pitch_index, const int prev_lag_int, const int subframe, int third_as_first, int resolution)
Decode the adaptive codebook index to the integer and fractional parts of the pitch lag for one subfr...
Definition: acelp_pitch_delay.c:148
AMR_BLOCK_SIZE
#define AMR_BLOCK_SIZE
samples per frame
Definition: amrnbdec.c:62
AVERROR_INVALIDDATA
#define AVERROR_INVALIDDATA
Invalid data found when processing input.
Definition: error.h:59
AVFrame
This structure describes decoded (raw) audio or video data.
Definition: frame.h:218
AMRContext::lsf_avg
float lsf_avg[LP_FILTER_ORDER]
vector of averaged lsf vector
Definition: amrnbdec.c:110
data
ptrdiff_t const GLvoid * data
Definition: opengl_enc.c:101
ff_decode_10_pulses_35bits
void ff_decode_10_pulses_35bits(const int16_t *fixed_index, AMRFixed *fixed_sparse, const uint8_t *gray_decode, int half_pulse_count, int bits)
Decode the algebraic codebook index to pulse positions and signs and construct the algebraic codebook...
Definition: acelp_vectors.c:152
amrnb_decode_frame
static int amrnb_decode_frame(AVCodecContext *avctx, void *data, int *got_frame_ptr, AVPacket *avpkt)
Definition: amrnbdec.c:948
pitch_sharpening
static void pitch_sharpening(AMRContext *p, int subframe, enum Mode mode, AMRFixed *fixed_sparse)
Apply pitch lag to obtain the sharpened fixed vector (section 6.1.2)
Definition: amrnbdec.c:552
temp
else temp
Definition: vf_mcdeint.c:256
init
static av_cold int init(AVCodecContext *avctx)
Definition: avrndec.c:35
AMRNBFrame
AMRNB unpacked data frame.
Definition: amrnbdata.h:68
ff_clear_fixed_vector
void ff_clear_fixed_vector(float *out, const AMRFixed *in, int size)
Clear array values set by set_fixed_vector.
Definition: acelp_vectors.c:253
base_five_table
static const uint8_t base_five_table[128][3]
Base-5 representation for values 0-124.
Definition: amrnbdata.h:367
pulses
static const int8_t pulses[4]
Number of non-zero pulses in the MP-MLQ excitation.
Definition: g723_1.h:720
AMRFixed::x
int x[10]
Definition: acelp_vectors.h:55
AVPacket::size
int size
Definition: avcodec.h:1431
float_dsp.h
ACELPFContext::acelp_apply_order_2_transfer_function
void(* acelp_apply_order_2_transfer_function)(float *out, const float *in, const float zero_coeffs[2], const float pole_coeffs[2], float gain, float mem[2], int n)
Apply an order 2 rational transfer function in-place.
Definition: acelp_filters.h:47
lsf_3_1
static const int16_t lsf_3_1[256][3]
Definition: amrnbdata.h:633
AV_SAMPLE_FMT_NONE
Definition: samplefmt.h:59
decode_fixed_sparse
static void decode_fixed_sparse(AMRFixed *fixed_sparse, const uint16_t *pulses, const enum Mode mode, const int subframe)
Decode the algebraic codebook index to pulse positions and signs, then construct the algebraic codebo...
Definition: amrnbdec.c:499
track_position
static const uint8_t track_position[16]
track start positions for algebraic code book routines
Definition: amrnbdata.h:1433
AMRContext::bad_frame_indicator
uint8_t bad_frame_indicator
bad frame ? 1 : 0
Definition: amrnbdec.c:102
MODE_DTX
silent frame
Definition: amrnbdata.h:48
ff_set_fixed_vector
void ff_set_fixed_vector(float *out, const AMRFixed *in, float scale, int size)
Add fixed vector to an array from a sparse representation.
Definition: acelp_vectors.c:235
AMRFixed::pitch_fac
float pitch_fac
Definition: acelp_vectors.h:59
AV_SAMPLE_FMT_FLT
float
Definition: samplefmt.h:63
fixed_gain_smooth
static float fixed_gain_smooth(AMRContext *p, const float *lsf, const float *lsf_avg, const enum Mode mode)
fixed gain smoothing Note that where the spec specifies the "spectrum in the q domain" in section 6...
Definition: amrnbdec.c:588
lsf_3_2
static const int16_t lsf_3_2[512][3]
Definition: amrnbdata.h:723
CELPMContext::dot_productf
float(* dot_productf)(const float *a, const float *b, int length)
Return the dot product.
Definition: celp_math.h:37
synthesis
static int synthesis(AMRContext *p, float *lpc, float fixed_gain, const float *fixed_vector, float *samples, uint8_t overflow)
Conduct 10th order linear predictive coding synthesis.
Definition: amrnbdec.c:790
AVCodec
AVCodec.
Definition: avcodec.h:3408
weighted_vector_sumd
static void weighted_vector_sumd(double *out, const double *in_a, const double *in_b, double weight_coeff_a, double weight_coeff_b, int length)
Double version of ff_weighted_vector_sumf()
Definition: amrnbdec.c:149
decode
static void decode(AVCodecContext *dec_ctx, AVPacket *pkt, AVFrame *frame, FILE *outfile)
Definition: decode_audio.c:42
amrnb_decode_init
static av_cold int amrnb_decode_init(AVCodecContext *avctx)
Definition: amrnbdec.c:160
AMRContext::prev_lsp_sub4
double prev_lsp_sub4[LP_FILTER_ORDER]
lsp vector for the 4th subframe of the previous frame
Definition: amrnbdec.c:107
postfilter
static void postfilter(AMRContext *p, float *lpc, float *buf_out)
Perform adaptive post-filtering to enhance the quality of the speech.
Definition: amrnbdec.c:904
lsf_5_1
static const int16_t lsf_5_1[128][4]
Definition: amrnbdata.h:1071
AMRContext::postfilter_agc
float postfilter_agc
previous factor used for adaptive gain control
Definition: amrnbdec.c:136
NO_DATA
no transmission
Definition: amrnbdata.h:50
filter
static void filter(int16_t *output, ptrdiff_t out_stride, int16_t *low, ptrdiff_t low_stride, int16_t *high, ptrdiff_t high_stride, int len, int clip)
Definition: cfhd.c:114
AVCodecContext::sample_fmt
enum AVSampleFormat sample_fmt
audio sample format
Definition: avcodec.h:2181
uint8_t
uint8_t
Definition: audio_convert.c:194
av_cold
#define av_cold
Definition: attributes.h:82
AMRFixed
Sparse representation for the algebraic codebook (fixed) vector.
Definition: acelp_vectors.h:53
qua_gain_code
static const uint16_t qua_gain_code[32]
scalar quantized fixed gain table for 7.95 and 12.2 kbps modes
Definition: amrnbdata.h:1450
CELPFContext::celp_lp_synthesis_filterf
void(* celp_lp_synthesis_filterf)(float *out, const float *filter_coeffs, const float *in, int buffer_length, int filter_length)
LP synthesis filter.
Definition: celp_filters.h:45
Mode
Mode
Frame type (Table 1a in 3GPP TS 26.101)
Definition: amrnbdata.h:39
qua_gain_pit
static const uint16_t qua_gain_pit[16]
scalar quantized pitch gain table for 7.95 and 12.2 kbps modes
Definition: amrnbdata.h:1444
PITCH_DELAY_MAX
#define PITCH_DELAY_MAX
Definition: acelp_pitch_delay.h:31
lsf2lsp_3
static void lsf2lsp_3(AMRContext *p)
Decode a set of 3 split-matrix quantized lsf indexes into an lsp vector.
Definition: amrnbdec.c:327
energy_pred_fac
static const float energy_pred_fac[4]
4-tap moving average prediction coefficients in reverse order
Definition: amrnbdata.h:1463
AMRNBSubframe::fixed_gain
uint16_t fixed_gain
index to decode the fixed gain factor, for MODE_12k2 and MODE_7k95
Definition: amrnbdata.h:61
frame
static AVFrame * frame
Definition: demuxing_decoding.c:53
lsp_sub4_init
static const int8_t lsp_sub4_init[LP_FILTER_ORDER]
Values for the lsp vector from the 4th subframe of the previous subframe values.
Definition: amrnbdata.h:395
MODE_5k9
5.90 kbit/s
Definition: amrnbdata.h:42
AMRContext::lsp
double lsp[4][LP_FILTER_ORDER]
lsp vectors from current frame
Definition: amrnbdec.c:106
AVPacket::data
uint8_t * data
Definition: avcodec.h:1430
apply_ir_filter
static void apply_ir_filter(float *out, const AMRFixed *in, const float *filter)
Circularly convolve a sparse fixed vector with a phase dispersion impulse response filter (D...
Definition: amrnbdec.c:672
AMRContext::frame
AMRNBFrame frame
decoded AMR parameters (lsf coefficients, codebook indexes, etc)
Definition: amrnbdec.c:101
ff_adaptive_gain_control
void ff_adaptive_gain_control(float *out, const float *in, float speech_energ, int size, float alpha, float *gain_mem)
Adaptive gain control (as used in AMR postfiltering)
Definition: acelp_vectors.c:203
filter1
static void filter1(SUINT32 *dst, const int32_t *src, int32_t coeff, ptrdiff_t len)
Definition: dcadsp.c:358
ff_amr_bit_reorder
static void ff_amr_bit_reorder(uint16_t *out, int size, const uint8_t *data, const R_TABLE_TYPE *ord_table)
Fill the frame structure variables from bitstream by parsing the given reordering table that uses the...
Definition: amr.h:51
AMRNBFrame::lsf
uint16_t lsf[5]
lsf parameters: 5 parameters for MODE_12k2, only 3 for other modes
Definition: amrnbdata.h:69
av_log
#define av_log(a,...)
Definition: tableprint_vlc.h:28
AMRContext::prev_ir_filter_nr
uint8_t prev_ir_filter_nr
previous impulse response filter "impNr": 0 - strong, 1 - medium, 2 - none
Definition: amrnbdec.c:131
AV_LOG_ERROR
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
Definition: log.h:176
decode_pitch_vector
static void decode_pitch_vector(AMRContext *p, const AMRNBSubframe *amr_subframe, const int subframe)
Definition: amrnbdec.c:391
update_state
static void update_state(AMRContext *p)
Update buffers and history at the end of decoding a subframe.
Definition: amrnbdec.c:847
positions
static const uint16_t positions[][14][3]
Definition: vf_vectorscope.c:796
update
static av_always_inline void update(SilenceDetectContext *s, AVFrame *insamples, int is_silence, int current_sample, int64_t nb_samples_notify, AVRational time_base)
Definition: af_silencedetect.c:76
AMRContext::fixed_vector
float fixed_vector[AMR_SUBFRAME_SIZE]
algebraic codebook (fixed) vector (must be kept zero between frames)
Definition: amrnbdec.c:120
NULL_IF_CONFIG_SMALL
#define NULL_IF_CONFIG_SMALL(x)
Return NULL if CONFIG_SMALL is true, otherwise the argument without modification. ...
Definition: internal.h:186
AMRNBFrame::subframe
AMRNBSubframe subframe[4]
unpacked data for each subframe
Definition: amrnbdata.h:70
ff_pow_0_7
const float ff_pow_0_7[10]
Table of pow(0.7,n)
Definition: acelp_vectors.c:99
AVMEDIA_TYPE_AUDIO
Definition: avutil.h:202
avassert.h
simple assert() macros that are a bit more flexible than ISO C assert().
length
GLsizei GLsizei * length
Definition: opengl_enc.c:115
AVCodec::name
const char * name
Name of the codec implementation.
Definition: avcodec.h:3415
AMRContext::prev_lsf_r
int16_t prev_lsf_r[LP_FILTER_ORDER]
residual LSF vector from previous subframe
Definition: amrnbdec.c:105
frame_sizes_nb
static const uint8_t frame_sizes_nb[N_MODES]
number of bytes for each mode
Definition: amrnbdata.h:357
ff_scale_vector_to_given_sum_of_squares
void ff_scale_vector_to_given_sum_of_squares(float *out, const float *in, float sum_of_squares, const int n)
Set the sum of squares of a signal by scaling.
Definition: acelp_vectors.c:224
ff_pow_0_75
const float ff_pow_0_75[10]
Table of pow(0.75,n)
Definition: acelp_vectors.c:104
AMRContext::pitch_gain
float pitch_gain[5]
quantified pitch gains for the current and previous four subframes
Definition: amrnbdec.c:123
LP_FILTER_ORDER
#define LP_FILTER_ORDER
linear predictive coding filter order
Definition: amrnbdata.h:53
count
GLsizei count
Definition: opengl_enc.c:109
ACELPVContext::weighted_vector_sumf
void(* weighted_vector_sumf)(float *out, const float *in_a, const float *in_b, float weight_coeff_a, float weight_coeff_b, int length)
float implementation of weighted sum of two vectors.
Definition: acelp_vectors.h:40
lsf_3_3_MODE_5k15
static const int16_t lsf_3_3_MODE_5k15[128][4]
Definition: amrnbdata.h:413
AMRContext::excitation
float * excitation
pointer to the current excitation vector in excitation_buf
Definition: amrnbdec.c:117
AVCodecContext::channel_layout
uint64_t channel_layout
Audio channel layout.
Definition: avcodec.h:2224
AMR_SAMPLE_BOUND
#define AMR_SAMPLE_BOUND
threshold for synthesis overflow
Definition: amrnbdec.c:63
AMRContext::ir_filter_onset
uint8_t ir_filter_onset
flag for impulse response filter strength
Definition: amrnbdec.c:132
interpolate_lsf
static void interpolate_lsf(ACELPVContext *ctx, float lsf_q[4][LP_FILTER_ORDER], float *lsf_new)
Interpolate the LSF vector (used for fixed gain smoothing).
Definition: amrnbdec.c:239
AMR_SUBFRAME_SIZE
#define AMR_SUBFRAME_SIZE
samples per subframe
Definition: amrnbdata.h:36
ir_filters_lookup_MODE_7k95
static const float *const ir_filters_lookup_MODE_7k95[2]
Definition: amrnbdata.h:1661
AMRNBSubframe
AMRNB unpacked data subframe.
Definition: amrnbdata.h:58
channel_layout.h
audio channel layout utility functions
MIN_ENERGY
#define MIN_ENERGY
Initial energy in dB.
Definition: amrnbdec.c:84
av_assert1
#define av_assert1(cond)
assert() equivalent, that does not lie in speed critical code.
Definition: avassert.h:53
highpass_poles
static const float highpass_poles[2]
Definition: amrnbdata.h:1668
acelp_filters.h
FFMIN
#define FFMIN(a, b)
Definition: common.h:96
ff_amrnb_decoder
AVCodec ff_amrnb_decoder
Definition: amrnbdec.c:1083
N_MODES
number of modes
Definition: amrnbdata.h:49
AMRContext::samples_in
float samples_in[LP_FILTER_ORDER+AMR_SUBFRAME_SIZE]
floating point samples
Definition: amrnbdec.c:139
MODE_12k2
12.2 kbit/s
Definition: amrnbdata.h:47
lsf_3_1_MODE_7k95
static const int16_t lsf_3_1_MODE_7k95[512][3]
Definition: amrnbdata.h:459
AMRFixed::y
float y[10]
Definition: acelp_vectors.h:56
ctx
AVFormatContext * ctx
Definition: movenc.c:48
lsf_5_5
static const int16_t lsf_5_5[64][4]
Definition: amrnbdata.h:1384
AMRNBSubframe::p_lag
uint16_t p_lag
index to decode the pitch lag
Definition: amrnbdata.h:59
truncf
static av_always_inline av_const float truncf(float x)
Definition: libm.h:465
highpass_zeros
static const float highpass_zeros[2]
Definition: amrnbdata.h:1667
gains_MODE_4k75
static const uint16_t gains_MODE_4k75[512][2]
gain table for 4.75 kbps mode
Definition: amrnbdata.h:1469
AMRContext::pitch_vector
float pitch_vector[AMR_SUBFRAME_SIZE]
adaptive code book (pitch) vector
Definition: amrnbdec.c:119
ff_tilt_compensation
void ff_tilt_compensation(float *mem, float tilt, float *samples, int size)
Apply tilt compensation filter, 1 - tilt * z-1.
Definition: acelp_filters.c:136
MIN_LSF_SPACING
#define MIN_LSF_SPACING
Ensures stability of LPC filter.
Definition: amrnbdec.c:80
lsf_3_mean
static const float lsf_3_mean[LP_FILTER_ORDER]
Definition: amrnbdata.h:1409
ff_acelp_lspd2lpc
void ff_acelp_lspd2lpc(const double *lsp, float *lpc, int lp_half_order)
Reconstruct LPC coefficients from the line spectral pair frequencies.
Definition: lsp.c:209
AVERROR_PATCHWELCOME
#define AVERROR_PATCHWELCOME
Not yet implemented in FFmpeg, patches welcome.
Definition: error.h:62
anti_sparseness
static const float * anti_sparseness(AMRContext *p, AMRFixed *fixed_sparse, const float *fixed_vector, float fixed_gain, float *out)
Reduce fixed vector sparseness by smoothing with one of three IR filters.
Definition: amrnbdec.c:719
AMRContext::pitch_lag_int
uint8_t pitch_lag_int
integer part of pitch lag from current subframe
Definition: amrnbdec.c:114
AV_LOG_INFO
#define AV_LOG_INFO
Standard information.
Definition: log.h:187
AMRContext::tilt_mem
float tilt_mem
previous input to tilt compensation filter
Definition: amrnbdec.c:135
acelp_vectors.h
AMRContext::lsf_q
float lsf_q[4][LP_FILTER_ORDER]
Interpolated LSF vector for fixed gain smoothing.
Definition: amrnbdec.c:109
avcodec.h
Libavcodec external API header.
PRED_FAC_MODE_12k2
#define PRED_FAC_MODE_12k2
Prediction factor for 12.2kbit/s mode.
Definition: amrnbdec.c:77
AVSampleFormat
AVSampleFormat
Audio sample formats.
Definition: samplefmt.h:58
ff_celp_circ_addf
void ff_celp_circ_addf(float *out, const float *in, const float *lagged, int lag, float fac, int n)
Add an array to a rotated array.
Definition: celp_filters.c:50
AVCodecContext::sample_rate
int sample_rate
samples per second
Definition: avcodec.h:2173
MODE_7k95
7.95 kbit/s
Definition: amrnbdata.h:45
AMRContext::high_pass_mem
float high_pass_mem[2]
previous intermediate values in the high-pass filter
Definition: amrnbdec.c:137
AVCodecContext
main external API structure.
Definition: avcodec.h:1518
lsf_5_mean
static const float lsf_5_mean[LP_FILTER_ORDER]
Definition: amrnbdata.h:1414
MODE_10k2
10.2 kbit/s
Definition: amrnbdata.h:46
AMRNBSubframe::p_gain
uint16_t p_gain
index to decode the pitch gain
Definition: amrnbdata.h:60
ff_get_buffer
int ff_get_buffer(AVCodecContext *avctx, AVFrame *frame, int flags)
Get a buffer for a frame.
Definition: decode.c:1891
in
uint8_t pi<< 24) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8, uint8_t,(*(constuint8_t *) pi-0x80)*(1.0f/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8, uint8_t,(*(constuint8_t *) pi-0x80)*(1.0/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16, int16_t,(*(constint16_t *) pi >>8)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16, int16_t,*(constint16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16, int16_t,*(constint16_t *) pi *(1.0/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32, int32_t,(*(constint32_t *) pi >>24)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32, int32_t,*(constint32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32, int32_t,*(constint32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, float, av_clip_uint8(lrintf(*(constfloat *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, float, av_clip_int16(lrintf(*(constfloat *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, float, av_clipl_int32(llrintf(*(constfloat *) pi *(1U<< 31)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, double, av_clip_uint8(lrint(*(constdouble *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, double, av_clip_int16(lrint(*(constdouble *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, double, av_clipl_int32(llrint(*(constdouble *) pi *(1U<< 31))))#defineSET_CONV_FUNC_GROUP(ofmt, ifmt) staticvoidset_generic_function(AudioConvert *ac){}voidff_audio_convert_free(AudioConvert **ac){if(!*ac) return;ff_dither_free(&(*ac) ->dc);av_freep(ac);}AudioConvert *ff_audio_convert_alloc(AVAudioResampleContext *avr, enumAVSampleFormatout_fmt, enumAVSampleFormatin_fmt, intchannels, intsample_rate, intapply_map){AudioConvert *ac;intin_planar, out_planar;ac=av_mallocz(sizeof(*ac));if(!ac) returnNULL;ac->avr=avr;ac->out_fmt=out_fmt;ac->in_fmt=in_fmt;ac->channels=channels;ac->apply_map=apply_map;if(avr->dither_method!=AV_RESAMPLE_DITHER_NONE &&av_get_packed_sample_fmt(out_fmt)==AV_SAMPLE_FMT_S16 &&av_get_bytes_per_sample(in_fmt)>2){ac->dc=ff_dither_alloc(avr, out_fmt, in_fmt, channels, sample_rate, apply_map);if(!ac->dc){av_free(ac);returnNULL;}returnac;}in_planar=ff_sample_fmt_is_planar(in_fmt, channels);out_planar=ff_sample_fmt_is_planar(out_fmt, channels);if(in_planar==out_planar){ac->func_type=CONV_FUNC_TYPE_FLAT;ac->planes=in_planar?ac->channels:1;}elseif(in_planar) ac->func_type=CONV_FUNC_TYPE_INTERLEAVE;elseac->func_type=CONV_FUNC_TYPE_DEINTERLEAVE;set_generic_function(ac);if(ARCH_AARCH64) ff_audio_convert_init_aarch64(ac);if(ARCH_ARM) ff_audio_convert_init_arm(ac);if(ARCH_X86) ff_audio_convert_init_x86(ac);returnac;}intff_audio_convert(AudioConvert *ac, AudioData *out, AudioData *in){intuse_generic=1;intlen=in->nb_samples;intp;if(ac->dc){av_log(ac->avr, AV_LOG_TRACE,"%dsamples-audio_convert:%sto%s(dithered)\n", len, av_get_sample_fmt_name(ac->in_fmt), av_get_sample_fmt_name(ac->out_fmt));returnff_convert_dither(ac-> in
Definition: audio_convert.c:194
ff_celp_math_init
void ff_celp_math_init(CELPMContext *c)
Initialize CELPMContext.
Definition: celp_math.c:120
buf
void * buf
Definition: avisynth_c.h:690
AMRContext::diff_count
uint8_t diff_count
the number of subframes for which diff has been above 0.65
Definition: amrnbdec.c:127
amr_unpacking_bitmaps_per_mode
static const uint8_t *const amr_unpacking_bitmaps_per_mode[N_MODES]
position of the bitmapping data for each packet type in the AMRNBFrame
Definition: amrnbdata.h:345
AMRContext::prediction_error
float prediction_error[4]
quantified prediction errors {20log10(^gamma_gc)} for previous four subframes
Definition: amrnbdec.c:122
ff_celp_filter_init
void ff_celp_filter_init(CELPFContext *c)
Initialize CELPFContext.
Definition: celp_filters.c:212
highpass_gain
static const float highpass_gain
Definition: amrnbdata.h:1669
tilt_factor
static float tilt_factor(AMRContext *p, float *lpc_n, float *lpc_d)
Get the tilt factor of a formant filter from its transfer function.
Definition: amrnbdec.c:874
ff_acelp_lsf2lspd
void ff_acelp_lsf2lspd(double *lsp, const float *lsf, int lp_order)
Floating point version of ff_acelp_lsf2lsp()
Definition: lsp.c:93
AMRContext::cur_frame_mode
enum Mode cur_frame_mode
Definition: amrnbdec.c:103
AMRContext::fixed_gain
float fixed_gain[5]
quantified fixed gains for the current and previous four subframes
Definition: amrnbdec.c:124
AMRContext::lpc
float lpc[4][LP_FILTER_ORDER]
lpc coefficient vectors for 4 subframes
Definition: amrnbdec.c:112
AMRContext::beta
float beta
previous pitch_gain, bounded by [0.0,SHARP_MAX]
Definition: amrnbdec.c:126
SHARP_MAX
#define SHARP_MAX
Maximum sharpening factor.
Definition: amrnbdec.c:91
AMR_TILT_RESPONSE
#define AMR_TILT_RESPONSE
Number of impulse response coefficients used for tilt factor.
Definition: amrnbdec.c:94
ir_filters_lookup
static const float *const ir_filters_lookup[2]
Definition: amrnbdata.h:1658
AMRContext::celpf_ctx
CELPFContext celpf_ctx
context for filters for CELP-based codecs
Definition: amrnbdec.c:143
ff_acelp_vectors_init
void ff_acelp_vectors_init(ACELPVContext *c)
Initialize ACELPVContext.
Definition: acelp_vectors.c:268
decode_8_pulses_31bits
static void decode_8_pulses_31bits(const int16_t *fixed_index, AMRFixed *fixed_sparse)
Decode the algebraic codebook index to pulse positions and signs and construct the algebraic codebook...
Definition: amrnbdec.c:453
decode_pitch_lag_1_6
static void decode_pitch_lag_1_6(int *lag_int, int *lag_frac, int pitch_index, const int prev_lag_int, const int subframe)
Like ff_decode_pitch_lag(), but with 1/6 resolution.
Definition: amrnbdec.c:372
lsf_5_4
static const int16_t lsf_5_4[256][4]
Definition: amrnbdata.h:1295
avpriv_report_missing_feature
void avpriv_report_missing_feature(void *avc, const char *msg,...) av_printf_format(2
Log a generic warning message about a missing feature.
decode_10bit_pulse
static void decode_10bit_pulse(int code, int pulse_position[8], int i1, int i2, int i3)
Decode a 10-bit algebraic codebook index from a 10.2 kbit/s frame.
Definition: amrnbdec.c:435
lsf_3_3
static const int16_t lsf_3_3[512][4]
Definition: amrnbdata.h:897
AVFrame::data
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
Definition: frame.h:232
lsf_5_2
static const int16_t lsf_5_2[256][4]
Definition: amrnbdata.h:1117
gray_decode
static const uint8_t gray_decode[8]
3-bit Gray code to binary lookup table
Definition: amrnbdata.h:1438
pred_fac
static const float pred_fac[LP_FILTER_ORDER]
Prediction factor table for modes other than 12.2kbit/s.
Definition: amrnbdata.h:1420
CELPFContext::celp_lp_zero_synthesis_filterf
void(* celp_lp_zero_synthesis_filterf)(float *out, const float *filter_coeffs, const float *in, int buffer_length, int filter_length)
LP zero synthesis filter.
Definition: celp_filters.h:65
AMRContext::prev_sparse_fixed_gain
float prev_sparse_fixed_gain
previous fixed gain; used by anti-sparseness processing to determine "onset"
Definition: amrnbdec.c:130
AMRContext::postfilter_mem
float postfilter_mem[10]
previous intermediate values in the formant filter
Definition: amrnbdec.c:134
AMR_AGC_ALPHA
#define AMR_AGC_ALPHA
Adaptive gain control factor used in post-filter.
Definition: amrnbdec.c:98
internal.h
common internal api header.
common.h
common internal and external API header
lsf2lsp_5
static void lsf2lsp_5(AMRContext *p)
Decode a set of 5 split-matrix quantized lsf indexes into 2 lsp vectors.
Definition: amrnbdec.c:298
lsf2lsp_for_mode12k2
static void lsf2lsp_for_mode12k2(AMRContext *p, double lsp[LP_FILTER_ORDER], const float lsf_no_r[LP_FILTER_ORDER], const int16_t *lsf_quantizer[5], const int quantizer_offset, const int sign, const int update)
Decode a set of 5 split-matrix quantized lsf indexes into an lsp vector.
Definition: amrnbdec.c:260
AMRFixed::pitch_lag
int pitch_lag
Definition: acelp_vectors.h:58
gains_low
static const uint16_t gains_low[64][2]
gain table for 5.15 and 5.90 kbps modes
Definition: amrnbdata.h:1610
MODE_6k7
6.70 kbit/s
Definition: amrnbdata.h:43
decode_gains
static void decode_gains(AMRContext *p, const AMRNBSubframe *amr_subframe, const enum Mode mode, const int subframe, float *fixed_gain_factor)
Decode pitch gain and fixed gain factor (part of section 6.1.3).
Definition: amrnbdec.c:630
ff_set_min_dist_lsf
void ff_set_min_dist_lsf(float *lsf, double min_spacing, int size)
Adjust the quantized LSFs so they are increasing and not too close.
Definition: lsp.c:51
ff_acelp_filter_init
void ff_acelp_filter_init(ACELPFContext *c)
Initialize ACELPFContext.
Definition: acelp_filters.c:148
acelp_pitch_delay.h
LSF_R_FAC
#define LSF_R_FAC
LSF residual tables to Hertz.
Definition: amrnbdec.c:79
AVCodecContext::priv_data
void * priv_data
Definition: avcodec.h:1545
ff_b60_sinc
const float ff_b60_sinc[61]
b60 hamming windowed sinc function coefficients
Definition: acelp_vectors.c:114
diff
static av_always_inline int diff(const uint32_t a, const uint32_t b)
Definition: vf_palettegen.c:136
MODE_4k75
4.75 kbit/s
Definition: amrnbdata.h:40
gains_high
static const uint16_t gains_high[128][2]
gain table for 6.70, 7.40 and 10.2 kbps modes
Definition: amrnbdata.h:1578
AMRContext::hang_count
uint8_t hang_count
the number of subframes since a hangover period started
Definition: amrnbdec.c:128
AVCodecContext::channels
int channels
number of audio channels
Definition: avcodec.h:2174
amrnbdata.h
AMR narrowband data and definitions.
energy_mean
static const float energy_mean[8]
desired mean innovation energy, indexed by active mode
Definition: amrnbdata.h:1458
MODE_7k4
7.40 kbit/s
Definition: amrnbdata.h:44
sample_fmts
static enum AVSampleFormat sample_fmts[]
Definition: adpcmenc.c:701
PITCH_LAG_MIN_MODE_12k2
#define PITCH_LAG_MIN_MODE_12k2
Lower bound on decoded lag search in 12.2kbit/s mode.
Definition: amrnbdec.c:81
AMRContext::celpm_ctx
CELPMContext celpm_ctx
context for fixed point math operations
Definition: amrnbdec.c:144
out
FILE * out
Definition: movenc.c:54
AMRNBSubframe::pulses
uint16_t pulses[10]
pulses: 10 for MODE_12k2, 7 for MODE_10k2, and index and sign for others
Definition: amrnbdata.h:62
AMRContext::excitation_buf
float excitation_buf[PITCH_DELAY_MAX+LP_FILTER_ORDER+1+AMR_SUBFRAME_SIZE]
current excitation and all necessary excitation history
Definition: amrnbdec.c:116
celp_math.h
unpack_bitstream
static enum Mode unpack_bitstream(AMRContext *p, const uint8_t *buf, int buf_size)
Unpack an RFC4867 speech frame into the AMR frame mode and parameters.
Definition: amrnbdec.c:207
AV_CH_LAYOUT_MONO
#define AV_CH_LAYOUT_MONO
Definition: channel_layout.h:85
MODE_5k15
5.15 kbit/s
Definition: amrnbdata.h:41
AVPacket
This structure stores compressed data.
Definition: avcodec.h:1407
ff_pow_0_55
const float ff_pow_0_55[10]
Table of pow(0.55,n)
Definition: acelp_vectors.c:109
AMRContext::acelpf_ctx
ACELPFContext acelpf_ctx
context for filters for ACELP-based codecs
Definition: amrnbdec.c:141
lsf_5_3
static const int16_t lsf_5_3[256][4]
Definition: amrnbdata.h:1206
AMR_TILT_GAMMA_T
#define AMR_TILT_GAMMA_T
Tilt factor = 1st reflection coefficient * gamma_t.
Definition: amrnbdec.c:96
mode
mode
Use these values in ebur128_init (or'ed).
Definition: ebur128.h:83
AVFrame::nb_samples
int nb_samples
number of audio samples (per channel) described by this frame
Definition: frame.h:284
AV_CODEC_CAP_DR1
#define AV_CODEC_CAP_DR1
Codec uses get_buffer() for allocating buffers and supports custom allocators.
Definition: avcodec.h:959
ACELPFContext::acelp_interpolatef
void(* acelp_interpolatef)(float *out, const float *in, const float *filter_coeffs, int precision, int frac_pos, int filter_length, int length)
Floating point version of ff_acelp_interpolate()
Definition: acelp_filters.h:32
ff_amr_set_fixed_gain
float ff_amr_set_fixed_gain(float fixed_gain_factor, float fixed_mean_energy, float *prediction_error, float energy_mean, const float *pred_table)
Calculate fixed gain (part of section 6.1.3 of AMR spec)
Definition: acelp_pitch_delay.c:127
AMRContext::acelpv_ctx
ACELPVContext acelpv_ctx
context for vector operations for ACELP-based codecs
Definition: amrnbdec.c:142
lsp_avg_init
static const int16_t lsp_avg_init[LP_FILTER_ORDER]
Mean lsp values.
Definition: amrnbdata.h:404
Generated on Sun May 13 2018 02:03:42 for FFmpeg by   doxygen 1.8.6

AltStyle によって変換されたページ (->オリジナル) /