Go to the documentation of this file.
99 enum OCStatus oc_type,
int get_new_frame);
101 #define overread_err "Input buffer exhausted before END element found\n"
106 for (
i = 0;
i < tags;
i++) {
109 sum += (1 + (syn_ele ==
TYPE_CPE)) *
184 for (ch = 0; ch < avctx->
channels; ch++) {
201 uint64_t right,
int pos)
205 .av_position =
left | right,
207 .elem_id = layout_map[
offset][1],
215 .elem_id = layout_map[
offset][1],
219 .av_position = right,
221 .elem_id = layout_map[
offset + 1][1],
231 int num_pos_channels = 0;
235 for (
i = *current;
i < tags;
i++) {
236 if (layout_map[
i][2] !=
pos)
246 num_pos_channels += 2;
257 return num_pos_channels;
262 int i, n, total_non_cc_elements;
264 int num_front_channels, num_side_channels, num_back_channels;
273 if (num_front_channels < 0)
277 if (num_side_channels < 0)
281 if (num_back_channels < 0)
284 if (num_side_channels == 0 && num_back_channels >= 4) {
285 num_side_channels = 2;
286 num_back_channels -= 2;
290 if (num_front_channels & 1) {
294 .elem_id = layout_map[
i][1],
298 num_front_channels--;
300 if (num_front_channels >= 4) {
305 num_front_channels -= 2;
307 if (num_front_channels >= 2) {
312 num_front_channels -= 2;
314 while (num_front_channels >= 2) {
319 num_front_channels -= 2;
322 if (num_side_channels >= 2) {
327 num_side_channels -= 2;
329 while (num_side_channels >= 2) {
334 num_side_channels -= 2;
337 while (num_back_channels >= 4) {
342 num_back_channels -= 2;
344 if (num_back_channels >= 2) {
349 num_back_channels -= 2;
351 if (num_back_channels) {
355 .elem_id = layout_map[
i][1],
366 .elem_id = layout_map[
i][1],
375 .elem_id = layout_map[
i][1],
382 total_non_cc_elements = n =
i;
385 for (
i = 1;
i < n;
i++)
386 if (e2c_vec[
i - 1].av_position > e2c_vec[
i].av_position) {
394 for (
i = 0;
i < total_non_cc_elements;
i++) {
398 if (e2c_vec[
i].av_position != UINT64_MAX) {
413 ac->
oc[0] = ac->
oc[1];
426 ac->
oc[1] = ac->
oc[0];
442 enum OCStatus oc_type,
int get_new_frame)
451 memcpy(ac->
oc[1].
layout_map, layout_map, tags *
sizeof(layout_map[0]));
454 for (
i = 0;
i < tags;
i++) {
455 int type = layout_map[
i][0];
456 int id = layout_map[
i][1];
467 for (
i = 0;
i < tags;
i++) {
468 int type = layout_map[
i][0];
469 int id = layout_map[
i][1];
470 int iid = id_map[
type][
id];
471 int position = layout_map[
i][2];
509 for (j = 0; j <= 1; j++) {
528 if (channel_config < 1 || (channel_config > 7 && channel_config < 11) ||
529 channel_config > 12) {
531 "invalid default channel configuration (%d)\n",
537 *tags *
sizeof(*layout_map));
552 " instead of a spec-compliant 7.1(wide) layout, use -strict %d to decode"
577 &layout_map_tags, 2) < 0)
596 &layout_map_tags, 1) < 0)
632 "This stream seems to incorrectly report its last channel as %s[%d], mapping to LFE[0]\n",
654 "This stream seems to incorrectly report its last channel as %s[%d], mapping to SCE[1]\n",
715 layout_map[0][0] = syn_ele;
717 layout_map[0][2] =
type;
723 int reference_position) {
738 int num_front, num_side, num_back, num_lfe, num_assoc_data, num_cc;
748 "Sample rate index in program config element does not "
749 "match the sample rate index configured by the container.\n");
766 if (
get_bits_left(gb) < 5 * (num_front + num_side + num_back + num_cc) + 4 *(num_lfe + num_assoc_data + num_cc)) {
806 int get_bit_alignment,
810 int extension_flag,
ret, ep_config, res_flags;
838 if (channel_config == 0) {
840 tags =
decode_pce(avctx, m4ac, layout_map, gb, get_bit_alignment);
845 &tags, channel_config)))
851 }
else if (m4ac->
sbr == 1 && m4ac->
ps == -1)
857 if (extension_flag) {
870 "AAC data resilience (flags %x)",
886 "epConfig %d", ep_config);
898 int ret, ep_config, res_flags;
901 const int ELDEXT_TERM = 0;
916 "AAC data resilience (flags %x)",
927 while (
get_bits(gb, 4) != ELDEXT_TERM) {
941 &tags, channel_config)))
950 "epConfig %d", ep_config);
972 int get_bit_alignment,
986 "invalid sampling rate index %d\n",
994 "invalid low delay sampling rate index %d\n",
1020 "Audio object type %s%d",
1021 m4ac->
sbr == 1 ?
"SBR+" :
"",
1027 "AOT %d chan config %d sampling index %d (%d) SBR %d PS %d\n",
1044 if (bit_size < 0 || bit_size > INT_MAX) {
1049 ff_dlog(avctx,
"audio specific config size %d\n", (
int)bit_size >> 3);
1050 for (
i = 0; i < bit_size >> 3;
i++)
1070 union {
unsigned u;
int s; } v = { previous_val * 1664525
u + 1013904223 };
1083 if (92017 <= rate)
return 0;
1084 else if (75132 <= rate)
return 1;
1085 else if (55426 <= rate)
return 2;
1086 else if (46009 <= rate)
return 3;
1087 else if (37566 <= rate)
return 4;
1088 else if (27713 <= rate)
return 5;
1089 else if (23004 <= rate)
return 6;
1090 else if (18783 <= rate)
return 7;
1091 else if (13856 <= rate)
return 8;
1092 else if (11502 <= rate)
return 9;
1093 else if (9391 <= rate)
return 10;
1104 #define AAC_INIT_VLC_STATIC(num, size) \
1105 INIT_VLC_STATIC(&vlc_spectral[num], 8, ff_aac_spectral_sizes[num], \
1106 ff_aac_spectral_bits[num], sizeof(ff_aac_spectral_bits[num][0]), \
1107 sizeof(ff_aac_spectral_bits[num][0]), \
1108 ff_aac_spectral_codes[num], sizeof(ff_aac_spectral_codes[num][0]), \
1109 sizeof(ff_aac_spectral_codes[num][0]), \
1191 int layout_map_tags;
1282 "Invalid Predictor Reset Group.\n");
1328 "AAC LD is only defined for ONLY_LONG_SEQUENCE but "
1341 for (
i = 0;
i < 7;
i++) {
1398 "Prediction is not allowed in AAC-LC.\n");
1403 "LTP in ER AAC LD not yet implemented.\n");
1415 "Number of scalefactor bands in group (%d) "
1416 "exceeds limit (%d).\n",
1443 while (k < ics->max_sfb) {
1446 int sect_band_type =
get_bits(gb, 4);
1447 if (sect_band_type == 12) {
1453 sect_end += sect_len_incr;
1458 if (sect_end > ics->
max_sfb) {
1460 "Number of bands (%d) exceeds limit (%d).\n",
1464 }
while (sect_len_incr == (1 <<
bits) - 1);
1465 for (; k < sect_end; k++) {
1466 band_type [idx] = sect_band_type;
1467 band_type_run_end[idx++] = sect_end;
1485 unsigned int global_gain,
1488 int band_type_run_end[120])
1496 int run_end = band_type_run_end[idx];
1497 if (band_type[idx] ==
ZERO_BT) {
1498 for (;
i < run_end;
i++, idx++)
1502 for (;
i < run_end;
i++, idx++) {
1504 clipped_offset = av_clip(
offset[2], -155, 100);
1505 if (
offset[2] != clipped_offset) {
1507 "If you heard an audible artifact, there may be a bug in the decoder. "
1508 "Clipped intensity stereo position (%d -> %d)",
1509 offset[2], clipped_offset);
1512 sf[idx] = 100 - clipped_offset;
1517 }
else if (band_type[idx] ==
NOISE_BT) {
1518 for (;
i < run_end;
i++, idx++) {
1519 if (noise_flag-- > 0)
1523 clipped_offset = av_clip(
offset[1], -100, 155);
1524 if (
offset[1] != clipped_offset) {
1526 "If you heard an audible artifact, there may be a bug in the decoder. "
1527 "Clipped noise gain (%d -> %d)",
1528 offset[1], clipped_offset);
1531 sf[idx] = -(100 + clipped_offset);
1537 for (;
i < run_end;
i++, idx++) {
1541 "Scalefactor (%d) out of range.\n",
offset[0]);
1560 const uint16_t *swb_offset,
int num_swb)
1565 if (pulse_swb >= num_swb)
1567 pulse->
pos[0] = swb_offset[pulse_swb];
1569 if (pulse->
pos[0] >= swb_offset[num_swb])
1574 if (pulse->
pos[
i] >= swb_offset[num_swb])
1589 int w,
filt,
i, coef_len, coef_res, coef_compress;
1602 "TNS filter order %d is greater than maximum %d.\n",
1610 coef_len = coef_res + 3 - coef_compress;
1611 tmp2_idx = 2 * coef_compress + coef_res;
1634 if (ms_present == 1) {
1635 for (idx = 0; idx < max_idx; idx++)
1637 }
else if (ms_present == 2) {
1656 int pulse_present,
const Pulse *pulse,
1660 int i, k,
g, idx = 0;
1666 memset(coef +
g * 128 + offsets[ics->
max_sfb], 0,
1673 const unsigned cbt_m1 = band_type[idx] - 1;
1675 int off_len = offsets[
i + 1] - offsets[
i];
1679 for (group = 0; group < (
AAC_SIGNE)g_len; group++, cfo+=128) {
1680 memset(cfo, 0, off_len *
sizeof(*cfo));
1682 }
else if (cbt_m1 ==
NOISE_BT - 1) {
1683 for (group = 0; group < (
AAC_SIGNE)g_len; group++, cfo+=128) {
1686 for (k = 0; k < off_len; k++) {
1691 band_energy = ac->
fdsp->scalarproduct_fixed(cfo, cfo, off_len);
1697 for (k = 0; k < off_len; k++) {
1703 scale = sf[idx] / sqrtf(band_energy);
1715 switch (cbt_m1 >> 1) {
1717 for (group = 0; group < (
AAC_SIGNE)g_len; group++, cfo+=128) {
1727 cb_idx = cb_vector_idx[
code];
1731 cf =
VMUL4(cf, vq, cb_idx, sf + idx);
1738 for (group = 0; group < (
AAC_SIGNE)g_len; group++, cfo+=128) {
1750 cb_idx = cb_vector_idx[
code];
1751 nnz = cb_idx >> 8 & 15;
1764 for (group = 0; group < (
AAC_SIGNE)g_len; group++, cfo+=128) {
1774 cb_idx = cb_vector_idx[
code];
1778 cf =
VMUL2(cf, vq, cb_idx, sf + idx);
1786 for (group = 0; group < (
AAC_SIGNE)g_len; group++, cfo+=128) {
1798 cb_idx = cb_vector_idx[
code];
1799 nnz = cb_idx >> 8 & 15;
1800 sign = nnz ?
SHOW_UBITS(
re, gb, nnz) << (cb_idx >> 12) : 0;
1805 cf =
VMUL2S(cf, vq, cb_idx, sign, sf + idx);
1812 for (group = 0; group < (
AAC_SIGNE)g_len; group++, cfo+=128) {
1818 uint32_t *icf = (uint32_t *) cf;
1838 cb_idx = cb_vector_idx[
code];
1844 for (j = 0; j < 2; j++) {
1879 unsigned v = ((
const uint32_t*)vq)[cb_idx & 15];
1880 *icf++ = (
bits & 1
U<<31) | v;
1899 if (pulse_present) {
1903 while (offsets[idx + 1] <= pulse->
pos[
i])
1905 if (band_type[idx] !=
NOISE_BT && sf[idx]) {
1909 ico = co + (co > 0 ? -ico : ico);
1911 coef_base[ pulse->
pos[
i] ] = ico;
1915 ico = co / sqrtf(sqrtf(fabsf(co))) + (co > 0 ? -ico : ico);
1917 coef_base[ pulse->
pos[
i] ] =
cbrtf(fabsf(ico)) * ico * sf[idx];
1929 const unsigned cbt_m1 = band_type[idx] - 1;
1930 int *cfo = coef + offsets[
i];
1931 int off_len = offsets[
i + 1] - offsets[
i];
1935 for (group = 0; group < (
int)g_len; group++, cfo+=128) {
1964 k < sce->ics.swb_offset[sfb + 1];
1981 static const uint8_t gain_mode[4][3] = {
1993 for (bd = 0; bd < max_band; bd++) {
1994 for (wd = 0; wd < gain_mode[
mode][0]; wd++) {
1996 for (ad = 0; ad < adjust_num; ad++) {
1999 : gain_mode[
mode][2]));
2020 int global_gain, eld_syntax, er_syntax, pulse_present = 0;
2036 if (!common_window && !scale_flag) {
2051 if (!eld_syntax && (pulse_present =
get_bits1(gb))) {
2054 "Pulse tool not allowed in eight short sequence.\n");
2060 "Pulse data corrupt or invalid.\n");
2066 if (tns->
present && !er_syntax) {
2080 if (tns->
present && er_syntax) {
2109 int g,
i, group, idx = 0;
2117 for (group = 0; group < ics->
group_len[
g]; group++) {
2118 ac->
fdsp->butterflies_fixed(ch0 + group * 128 + offsets[
i],
2119 ch1 + group * 128 + offsets[
i],
2120 offsets[
i+1] - offsets[
i]);
2122 for (group = 0; group < ics->
group_len[
g]; group++) {
2124 ch1 + group * 128 + offsets[
i],
2125 offsets[
i+1] - offsets[
i]);
2149 int g, group,
i, idx = 0;
2157 for (;
i < bt_run_end;
i++, idx++) {
2161 scale =
c * sce1->
sf[idx];
2162 for (group = 0; group < ics->
group_len[
g]; group++)
2165 coef0 + group * 128 + offsets[
i],
2168 offsets[
i + 1] - offsets[
i] ,ac->
avctx);
2171 coef0 + group * 128 + offsets[
i],
2173 offsets[
i + 1] - offsets[
i]);
2178 idx += bt_run_end -
i;
2194 int i,
ret, common_window, ms_present = 0;
2197 common_window = eld_syntax ||
get_bits1(gb);
2198 if (common_window) {
2209 if (ms_present == 3) {
2212 }
else if (ms_present)
2220 if (common_window) {
2234 1.09050773266525765921,
2235 1.18920711500272106672,
2279 for (
c = 0;
c < num_gain;
c++) {
2287 gain_cache =
GET_GAIN(scale, gain);
2289 if ((
abs(gain_cache)-1024) >> 3 > 30)
2294 coup->
gain[
c][0] = gain_cache;
2297 for (sfb = 0; sfb < sce->
ics.
max_sfb; sfb++, idx++) {
2310 if ((
abs(gain_cache)-1024) >> 3 > 30)
2315 coup->
gain[
c][idx] = gain_cache;
2333 int num_excl_chan = 0;
2336 for (
i = 0;
i < 7;
i++)
2340 return num_excl_chan / 7;
2352 int drc_num_bands = 1;
2373 for (
i = 0;
i < drc_num_bands;
i++) {
2386 for (
i = 0;
i < drc_num_bands;
i++) {
2404 for(
i=0;
i+1<
sizeof(buf) &&
len>=8;
i++,
len-=8)
2411 if (sscanf(buf,
"libfaac %d.%d", &
major, &
minor) == 2){
2448 "SBR with 960 frame length");
2498 int bottom, top, order, start,
end,
size, inc;
2520 if ((
size =
end - start) <= 0)
2532 for (m = 0; m <
size; m++, start += inc)
2533 for (
i = 1;
i <=
FFMIN(m, order);
i++)
2537 for (m = 0; m <
size; m++, start += inc) {
2538 tmp[0] = coef[start];
2539 for (
i = 1;
i <=
FFMIN(m, order);
i++)
2541 for (
i = order;
i > 0;
i--)
2564 memset(
in, 0, 448 *
sizeof(*
in));
2571 memset(
in + 1024 + 576, 0, 448 *
sizeof(*
in));
2588 int16_t num_samples = 2048;
2590 if (ltp->
lag < 1024)
2591 num_samples = ltp->
lag + 1024;
2592 for (
i = 0;
i < num_samples;
i++)
2594 memset(&predTime[
i], 0, (2048 -
i) *
sizeof(*predTime));
2603 for (
i = offsets[sfb];
i < offsets[sfb + 1];
i++)
2621 memcpy(saved_ltp, saved, 512 *
sizeof(*saved_ltp));
2622 memset(saved_ltp + 576, 0, 448 *
sizeof(*saved_ltp));
2625 for (
i = 0;
i < 64;
i++)
2628 memcpy(saved_ltp, ac->
buf_mdct + 512, 448 *
sizeof(*saved_ltp));
2629 memset(saved_ltp + 576, 0, 448 *
sizeof(*saved_ltp));
2632 for (
i = 0;
i < 64;
i++)
2637 for (
i = 0;
i < 512;
i++)
2664 for (
i = 0;
i < 1024;
i += 128)
2669 for (
i=0;
i<1024;
i++)
2670 buf[
i] = (buf[
i] + 4LL) >> 3;
2684 memcpy(
out, saved, 448 *
sizeof(*
out));
2692 memcpy(
out + 448 + 4*128,
temp, 64 *
sizeof(*
out));
2695 memcpy(
out + 576, buf + 64, 448 *
sizeof(*
out));
2701 memcpy( saved,
temp + 64, 64 *
sizeof(*saved));
2705 memcpy( saved + 448, buf + 7*128 + 64, 64 *
sizeof(*saved));
2707 memcpy( saved, buf + 512, 448 *
sizeof(*saved));
2708 memcpy( saved + 448, buf + 7*128 + 64, 64 *
sizeof(*saved));
2710 memcpy( saved, buf + 512, 512 *
sizeof(*saved));
2733 for (
i = 0;
i < 8;
i++)
2750 memcpy(
out, saved, 420 *
sizeof(*
out));
2758 memcpy(
out + 420 + 4*120,
temp, 60 *
sizeof(*
out));
2761 memcpy(
out + 540, buf + 60, 420 *
sizeof(*
out));
2767 memcpy( saved,
temp + 60, 60 *
sizeof(*saved));
2771 memcpy( saved + 420, buf + 7*120 + 60, 60 *
sizeof(*saved));
2773 memcpy( saved, buf + 480, 420 *
sizeof(*saved));
2774 memcpy( saved + 420, buf + 7*120 + 60, 60 *
sizeof(*saved));
2776 memcpy( saved, buf + 480, 480 *
sizeof(*saved));
2795 for (
i = 0;
i < 1024;
i++)
2796 buf[
i] = (buf[
i] + 2) >> 2;
2802 memcpy(
out, saved, 192 *
sizeof(*
out));
2804 memcpy(
out + 320, buf + 64, 192 *
sizeof(*
out));
2810 memcpy(saved, buf + 256, 256 *
sizeof(*saved));
2821 const int n2 = n >> 1;
2822 const int n4 = n >> 2;
2831 for (
i = 0;
i < n2;
i+=2) {
2844 for (
i = 0;
i < 1024;
i++)
2845 buf[
i] = (buf[
i] + 1) >> 1;
2848 for (
i = 0;
i < n;
i+=2) {
2858 for (
i = n4;
i < n2;
i ++) {
2864 for (
i = 0;
i < n2;
i ++) {
2870 for (
i = 0;
i < n4;
i ++) {
2877 memmove(saved + n, saved, 2 * n *
sizeof(*saved));
2878 memcpy( saved, buf, n *
sizeof(*saved));
2903 apply_coupling_method(ac, &cc->
ch[0], cce,
index);
2908 apply_coupling_method(ac, &cc->
ch[1], cce,
index++);
2977 che->
ch[0].
ret[j] = (
int32_t)av_clip64((int64_t)che->
ch[0].
ret[j]*128, INT32_MIN, INT32_MAX-0x8000)+0x8000;
2979 che->
ch[1].
ret[j] = (
int32_t)av_clip64((int64_t)che->
ch[1].
ret[j]*128, INT32_MIN, INT32_MAX-0x8000)+0x8000;
2996 int layout_map_tags,
ret;
3004 "More than one AAC RDB per ADTS frame");
3027 layout_map_tags = 2;
3028 layout_map[0][0] = layout_map[1][0] =
TYPE_SCE;
3030 layout_map[0][1] = 0;
3031 layout_map[1][1] = 1;
3078 if (chan_config < 0 || (chan_config >= 8 && chan_config < 11) || chan_config >= 13) {
3086 if (!(che=
get_che(ac, elem_type, elem_id))) {
3088 "channel element %d.%d is not allocated\n",
3089 elem_type, elem_id);
3095 switch (elem_type) {
3132 int samples = 0, multiplier, audio_found = 0, pce_found = 0;
3133 int is_dmono, sce_count = 0;
3134 int payload_alignment;
3173 if (che_presence[elem_type][elem_id]) {
3174 int error = che_presence[elem_type][elem_id] > 1;
3176 elem_type, elem_id);
3182 che_presence[elem_type][elem_id]++;
3184 if (!(che=
get_che(ac, elem_type, elem_id))) {
3186 elem_type, elem_id);
3194 switch (elem_type) {
3225 if (pce_found && !pushed) {
3238 "Not evaluating a further program_config_element as this construct is dubious at best.\n");
3258 while (elem_id > 0) {
3275 che_prev_type = elem_type;
3298 if (ac->
oc[1].
status && audio_found) {
3321 is_dmono = ac->
dmono_mode && sce_count == 2 &&
3337 int *got_frame_ptr,
AVPacket *avpkt)
3341 int buf_size = avpkt->
size;
3346 int new_extradata_size;
3349 &new_extradata_size);
3350 int jp_dualmono_size;
3355 if (new_extradata) {
3360 new_extradata_size * 8LL, 1);
3367 if (jp_dualmono && jp_dualmono_size > 0)
3372 if (INT_MAX / 8 <= buf_size)
3392 for (buf_offset = buf_consumed; buf_offset < buf_size; buf_offset++)
3393 if (buf[buf_offset])
3396 return buf_size > buf_offset ? buf_consumed : buf_size;
3445 #define AACDEC_FLAGS AV_OPT_FLAG_DECODING_PARAM | AV_OPT_FLAG_AUDIO_PARAM
3447 {
"dual_mono_mode",
"Select the channel to decode for dual mono",
static void error(const char *err)
enum RawDataBlockType type[8]
Type of channel element to be coupled - SCE or CPE.
static void vector_pow43(int *coefs, int len)
int frame_size
Number of samples per channel in an audio frame.
CouplingPoint
The point during decoding at which channel coupling is applied.
@ AV_SAMPLE_FMT_FLTP
float, planar
static void skip_bits_long(GetBitContext *s, int n)
Skips the specified number of bits.
#define AV_LOG_WARNING
Something somehow does not look correct.
static av_always_inline int lcg_random(unsigned previous_val)
linear congruential pseudorandom number generator
const uint8_t ff_tns_max_bands_128[]
static void apply_mid_side_stereo(AACContext *ac, ChannelElement *cpe)
Mid/Side stereo decoding; reference: 4.6.8.1.3.
static int decode_eld_specific_config(AACContext *ac, AVCodecContext *avctx, GetBitContext *gb, MPEG4AudioConfig *m4ac, int channel_config)
static void update_ltp(AACContext *ac, SingleChannelElement *sce)
Update the LTP buffer for next frame.
static int get_bits_left(GetBitContext *gb)
void AAC_RENAME() ff_init_ff_sine_windows(int index)
initialize the specified entry of ff_sine_windows
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel sample they are references to shared objects When the negotiation mechanism computes the intersection of the formats supported at each end of a all references to both lists are replaced with a reference to the intersection And when a single format is eventually chosen for a link amongst the remaining all references to the list are updated That means that if a filter requires that its input and output have the same format amongst a supported all it has to do is use a reference to the same list of formats query_formats can leave some formats unset and return AVERROR(EAGAIN) to cause the negotiation mechanism toagain later. That can be used by filters with complex requirements to use the format negotiated on one link to set the formats supported on another. Frame references ownership and permissions
uint64_t channel_layout
Audio channel layout.
static void imdct_and_windowing(AACContext *ac, SingleChannelElement *sce)
Conduct IMDCT and windowing.
int sample_rate
samples per second
#define FFSWAP(type, a, b)
#define u(width, name, range_min, range_max)
static int aac_decode_frame(AVCodecContext *avctx, void *data, int *got_frame_ptr, AVPacket *avpkt)
const float *const ff_aac_codebook_vector_vals[]
static int decode_fill(AACContext *ac, GetBitContext *gb, int len)
static av_cold int aac_decode_init(AVCodecContext *avctx)
#define INIT_VLC_STATIC(vlc, bits, a, b, c, d, e, f, g, static_size)
int skip_samples
Number of audio samples to skip at the start of the next decoded frame.
int err_recognition
Error recognition; may misdetect some more or less valid parts as errors.
#define GET_VLC(code, name, gb, table, bits, max_depth)
If the vlc code is invalid and max_depth=1, then no bits will be removed.
static int decode_prediction(AACContext *ac, IndividualChannelStream *ics, GetBitContext *gb)
void ff_cbrt_tableinit(void)
void(* vector_fmul_reverse)(float *dst, const float *src0, const float *src1, int len)
Calculate the entry wise product of two vectors of floats, and store the result in a vector of floats...
static int get_bits_count(const GetBitContext *s)
void(* subband_scale)(int *dst, int *src, int scale, int offset, int len, void *log_context)
const uint16_t *const ff_aac_codebook_vector_idx[]
static av_cold int end(AVCodecContext *avctx)
void(* mdct_calc)(struct FFTContext *s, FFTSample *output, const FFTSample *input)
This structure describes decoded (raw) audio or video data.
static int skip_data_stream_element(AACContext *ac, GetBitContext *gb)
Skip data_stream_element; reference: table 4.10.
static void apply_dependent_coupling(AACContext *ac, SingleChannelElement *target, ChannelElement *cce, int index)
Apply dependent channel coupling (applied before IMDCT).
static void ff_aac_tableinit(void)
static int AAC_RENAME() compute_lpc_coefs(const LPC_TYPE *autoc, int max_order, LPC_TYPE *lpc, int lpc_stride, int fail, int normalize)
Levinson-Durbin recursion.
const uint8_t ff_aac_num_swb_960[]
static void decode_mid_side_stereo(ChannelElement *cpe, GetBitContext *gb, int ms_present)
Decode Mid/Side data; reference: table 4.54.
static int count_paired_channels(uint8_t(*layout_map)[3], int tags, int pos, int *current)
@ AOT_ER_AAC_LTP
N Error Resilient Long Term Prediction.
@ AV_SAMPLE_FMT_S32P
signed 32 bits, planar
ChannelElement * tag_che_map[4][MAX_ELEM_ID]
const uint8_t ff_aac_num_swb_120[]
static av_always_inline int get_vlc2(GetBitContext *s, VLC_TYPE(*table)[2], int bits, int max_depth)
Parse a vlc code.
#define AV_LOG_VERBOSE
Detailed information.
av_cold int ff_mdct15_init(MDCT15Context **ps, int inverse, int N, double scale)
int8_t used[MAX_LTP_LONG_SFB]
static int decode_band_types(AACContext *ac, enum BandType band_type[120], int band_type_run_end[120], GetBitContext *gb, IndividualChannelStream *ics)
Decode band types (section_data payload); reference: table 4.46.
static int * DEC_SQUAD(int *dst, unsigned idx)
static AVOnce aac_table_init
static void apply_prediction(AACContext *ac, SingleChannelElement *sce)
Apply AAC-Main style frequency domain prediction.
#define UPDATE_CACHE(name, gb)
const uint8_t ff_aac_num_swb_480[]
static void pop_output_configuration(AACContext *ac)
Restore the previous output configuration if and only if the current configuration is unlocked.
INTFLOAT * ret
PCM output.
#define AVERROR_UNKNOWN
Unknown error, typically from an external library.
static int decode_spectrum_and_dequant(AACContext *ac, INTFLOAT coef[1024], GetBitContext *gb, const INTFLOAT sf[120], int pulse_present, const Pulse *pulse, const IndividualChannelStream *ics, enum BandType band_type[120])
Decode spectral data; reference: table 4.50.
uint64_t request_channel_layout
Request decoder to use this channel layout if it can (0 for default)
const uint16_t *const ff_swb_offset_128[]
static int init_get_bits(GetBitContext *s, const uint8_t *buffer, int bit_size)
Initialize GetBitContext.
static int decode_pce(AVCodecContext *avctx, MPEG4AudioConfig *m4ac, uint8_t(*layout_map)[3], GetBitContext *gb, int byte_align_ref)
Decode program configuration element; reference: table 4.2.
#define FF_DEBUG_PICT_INFO
uint8_t * data[AV_NUM_DATA_POINTERS]
pointer to the picture/channel planes.
const uint8_t ff_tns_max_bands_1024[]
void(* butterflies_float)(float *av_restrict v1, float *av_restrict v2, int len)
Calculate the sum and difference of two vectors of floats.
static void reset_all_predictors(PredictorState *ps)
#define GET_CACHE(name, gb)
static int set_default_channel_config(AACContext *ac, AVCodecContext *avctx, uint8_t(*layout_map)[3], int *tags, int channel_config)
Set up channel positions based on a default channel configuration as specified in table 1....
const uint8_t ff_mpeg4audio_channels[8]
static void skip_bits(GetBitContext *s, int n)
Dynamic Range Control - decoded from the bitstream but not processed further.
int num_swb
number of scalefactor window bands
static unsigned int get_bits(GetBitContext *s, int n)
Read 1-25 bits.
enum CouplingPoint coupling_point
The point during decoding at which coupling is applied.
static SDL_Window * window
const uint8_t ff_aac_num_swb_512[]
@ OC_LOCKED
Output configuration locked in place.
void(* apply_ltp)(AACContext *ac, SingleChannelElement *sce)
INTFLOAT saved[1536]
overlap
static const INTFLOAT ltp_coef[8]
INTFLOAT ret_buf[2048]
PCM output buffer.
int id_select[8]
element id
static int decode_drc_channel_exclusions(DynamicRangeControl *che_drc, GetBitContext *gb)
Parse whether channels are to be excluded from Dynamic Range Compression; reference: table 4....
int flags
AV_CODEC_FLAG_*.
#define POW_SF2_ZERO
ff_aac_pow2sf_tab index corresponding to pow(2, 0);
static void decode_gain_control(SingleChannelElement *sce, GetBitContext *gb)
it s the only field you need to keep assuming you have a context There is some magic you don t need to care about around this just let it vf type
static float * VMUL2(float *dst, const float *v, unsigned idx, const float *scale)
static void decode_ltp(LongTermPrediction *ltp, GetBitContext *gb, uint8_t max_sfb)
Decode Long Term Prediction data; reference: table 4.xx.
AVFixedDSPContext * avpriv_alloc_fixed_dsp(int bit_exact)
Allocate and initialize a fixed DSP context.
uint8_t prediction_used[41]
IndividualChannelStream ics
static void spectral_to_sample(AACContext *ac, int samples)
Convert spectral data to samples, applying all supported tools as appropriate.
#define AV_EF_BITSTREAM
detect bitstream specification deviations
@ AOT_ER_AAC_LC
N Error Resilient Low Complexity.
static int ff_thread_once(char *control, void(*routine)(void))
#define AV_LOG_ERROR
Something went wrong and cannot losslessly be recovered.
@ ZERO_BT
Scalefactors and spectral data are all zero.
#define FF_PROFILE_AAC_HE_V2
static av_cold int che_configure(AACContext *ac, enum ChannelPosition che_pos, int type, int id, int *channels)
Check for the channel element in the current channel position configuration.
static int decode_cpe(AACContext *ac, GetBitContext *gb, ChannelElement *cpe)
Decode a channel_pair_element; reference: table 4.4.
static int init_get_bits8(GetBitContext *s, const uint8_t *buffer, int byte_size)
Initialize GetBitContext.
int exclude_mask[MAX_CHANNELS]
Channels to be excluded from DRC processing.
void(* vector_pow43)(int *coefs, int len)
#define AV_CH_LOW_FREQUENCY
#define CLOSE_READER(name, gb)
static void decode(AVCodecContext *dec_ctx, AVPacket *pkt, AVFrame *frame, FILE *outfile)
@ NOISE_BT
Spectral data are scaled white noise not coded in the bitstream.
float(* scalarproduct_float)(const float *v1, const float *v2, int len)
Calculate the scalar product of two vectors of floats.
@ AOT_ER_AAC_LD
N Error Resilient Low Delay.
static const AVClass aac_decoder_class
@ OC_TRIAL_FRAME
Output configuration under trial specified by a frame header.
INTFLOAT coeffs[1024]
coefficients for IMDCT, maybe processed
static void windowing_and_mdct_ltp(AACContext *ac, INTFLOAT *out, INTFLOAT *in, IndividualChannelStream *ics)
Apply windowing and MDCT to obtain the spectral coefficient from the predicted sample by LTP.
const uint16_t *const ff_swb_offset_960[]
static int sample_rate_idx(int rate)
static av_always_inline void reset_predict_state(PredictorState *ps)
int num_coupled
number of target elements
static int decode_dynamic_range(DynamicRangeControl *che_drc, GetBitContext *gb)
Decode dynamic range information; reference: table 4.52.
@ OC_NONE
Output unconfigured.
@ INTENSITY_BT2
Scalefactor data are intensity stereo positions (out of phase).
static void apply_intensity_stereo(AACContext *ac, ChannelElement *cpe, int ms_present)
intensity stereo decoding; reference: 4.6.8.2.3
#define av_assert0(cond)
assert() equivalent, that is always enabled.
static int aac_decode_frame_int(AVCodecContext *avctx, void *data, int *got_frame_ptr, GetBitContext *gb, AVPacket *avpkt)
static void imdct_and_windowing_eld(AACContext *ac, SingleChannelElement *sce)
#define AV_LOG_DEBUG
Stuff which is only useful for libav* developers.
#define SKIP_BITS(name, gb, num)
float ff_aac_kbd_short_120[120]
static int aac_decode_er_frame(AVCodecContext *avctx, void *data, int *got_frame_ptr, GetBitContext *gb)
static int decode_scalefactors(AACContext *ac, INTFLOAT sf[120], GetBitContext *gb, unsigned int global_gain, IndividualChannelStream *ics, enum BandType band_type[120], int band_type_run_end[120])
Decode scalefactors; reference: table 4.47.
int force_dmono_mode
0->not dmono, 1->use first channel, 2->use second channel
static int parse_adts_frame_header(AACContext *ac, GetBitContext *gb)
Individual Channel Stream.
#define SCALE_DIFF_ZERO
codebook index corresponding to zero scalefactor indices difference
INTFLOAT coef[8][4][TNS_MAX_ORDER]
#define NOISE_PRE
preamble for NOISE_BT, put in bitstream with the first noise band
const uint16_t * swb_offset
table of offsets to the lowest spectral coefficient of a scalefactor band, sfb, for a particular wind...
uint8_t * av_packet_get_side_data(const AVPacket *pkt, enum AVPacketSideDataType type, int *size)
Get side information from packet.
static int decode_ga_specific_config(AACContext *ac, AVCodecContext *avctx, GetBitContext *gb, int get_bit_alignment, MPEG4AudioConfig *m4ac, int channel_config)
Decode GA "General Audio" specific configuration; reference: table 4.1.
int warned_num_aac_frames
@ INTENSITY_BT
Scalefactor data are intensity stereo positions (in phase).
#define LIBAVUTIL_VERSION_INT
Describe the class of an AVClass context structure.
#define AAC_INIT_VLC_STATIC(num, size)
static int decode_pulses(Pulse *pulse, GetBitContext *gb, const uint16_t *swb_offset, int num_swb)
Decode pulse data; reference: table 4.7.
static void flush(AVCodecContext *avctx)
#define AVERROR_PATCHWELCOME
Not yet implemented in FFmpeg, patches welcome.
void(* vector_fmul_scalar)(float *dst, const float *src, float mul, int len)
Multiply a vector of floats by a scalar float.
const float ff_aac_eld_window_480[1800]
static void imdct_and_windowing_960(AACContext *ac, SingleChannelElement *sce)
Conduct IMDCT and windowing.
const uint8_t ff_aac_num_swb_128[]
static void decode_channel_map(uint8_t layout_map[][3], enum ChannelPosition type, GetBitContext *gb, int n)
Decode an array of 4 bit element IDs, optionally interleaved with a stereo/mono switching bit.
struct AVCodecInternal * internal
Private context used for internal data.
const char * av_default_item_name(void *ptr)
Return the context name.
static unsigned int get_bits1(GetBitContext *s)
static av_cold int aac_decode_close(AVCodecContext *avctx)
#define LAST_SKIP_BITS(name, gb, num)
int band_top[17]
Indicates the top of the i-th DRC band in units of 4 spectral lines.
float ff_aac_kbd_long_960[960]
ChannelElement * che[4][MAX_ELEM_ID]
static void apply_ltp(AACContext *ac, SingleChannelElement *sce)
Apply the long term prediction.
int skip_samples_multiplier
const uint16_t *const ff_swb_offset_480[]
#define AV_CH_FRONT_CENTER
#define AV_EF_EXPLODE
abort decoding on minor error detection
PredictorState predictor_state[MAX_PREDICTORS]
#define AV_CH_FRONT_LEFT_OF_CENTER
static int decode_audio_specific_config(AACContext *ac, AVCodecContext *avctx, MPEG4AudioConfig *m4ac, const uint8_t *data, int64_t bit_size, int sync_extension)
static int decode_cce(AACContext *ac, GetBitContext *gb, ChannelElement *che)
Decode coupling_channel_element; reference: table 4.8.
static void apply_channel_coupling(AACContext *ac, ChannelElement *cc, enum RawDataBlockType type, int elem_id, enum CouplingPoint coupling_point, void(*apply_coupling_method)(AACContext *ac, SingleChannelElement *target, ChannelElement *cce, int index))
channel coupling transformation interface
Undefined Behavior In the C some operations are like signed integer dereferencing freed accessing outside allocated Undefined Behavior must not occur in a C it is not safe even if the output of undefined operations is unused The unsafety may seem nit picking but Optimizing compilers have in fact optimized code on the assumption that no undefined Behavior occurs Optimizing code based on wrong assumptions can and has in some cases lead to effects beyond the output of computations The signed integer overflow problem in speed critical code Code which is highly optimized and works with signed integers sometimes has the problem that often the output of the computation does not c
int band_type_run_end[120]
band type run end points
const uint8_t ff_tns_max_bands_512[]
static float * VMUL2S(float *dst, const float *v, unsigned idx, unsigned sign, const float *scale)
void(* imdct_half)(struct FFTContext *s, FFTSample *output, const FFTSample *input)
uint8_t layout_map[MAX_ELEM_ID *4][3]
void(* apply_tns)(INTFLOAT coef[1024], TemporalNoiseShaping *tns, IndividualChannelStream *ics, int decode)
const uint8_t ff_aac_scalefactor_bits[121]
static float * VMUL4(float *dst, const float *v, unsigned idx, const float *scale)
static float * VMUL4S(float *dst, const float *v, unsigned idx, unsigned sign, const float *scale)
const uint8_t ff_aac_pred_sfb_max[]
static int decode_audio_specific_config_gb(AACContext *ac, AVCodecContext *avctx, MPEG4AudioConfig *m4ac, GetBitContext *gb, int get_bit_alignment, int sync_extension)
Decode audio specific configuration; reference: table 1.13.
int ff_get_buffer(AVCodecContext *avctx, AVFrame *frame, int flags)
Get a buffer for a frame.
@ AOT_ER_AAC_SCALABLE
N Error Resilient Scalable.
SingleChannelElement ch[2]
const uint16_t *const ff_swb_offset_1024[]
static void relative_align_get_bits(GetBitContext *gb, int reference_position)
@ AOT_AAC_SCALABLE
N Scalable.
void(* vector_fmul)(float *dst, const float *src0, const float *src1, int len)
Calculate the entry wise product of two vectors of floats and store the result in a vector of floats.
int warned_remapping_once
static int decode_ics(AACContext *ac, SingleChannelElement *sce, GetBitContext *gb, int common_window, int scale_flag)
Decode an individual_channel_stream payload; reference: table 4.44.
int sample_rate
Sample rate of the audio data.
static const int8_t tags_per_config[16]
static void noise_scale(int *coefs, int scale, int band_energy, int len)
#define FF_COMPLIANCE_STRICT
Strictly conform to all the things in the spec no matter what consequences.
enum AVSampleFormat sample_fmt
audio sample format
uint32_t ff_cbrt_tab[1<< 13]
int prog_ref_level
A reference level for the long-term program audio level for all channels combined.
void avpriv_report_missing_feature(void *avc, const char *msg,...) av_printf_format(2
Log a generic warning message about a missing feature.
OCStatus
Output configuration status.
static const int8_t filt[NUMTAPS]
int ff_mpeg4audio_get_config_gb(MPEG4AudioConfig *c, GetBitContext *gb, int sync_extension, void *logctx)
Parse MPEG-4 systems extradata from a potentially unaligned GetBitContext to retrieve audio configura...
static int push_output_configuration(AACContext *ac)
Save current output configuration if and only if it has been locked.
const uint8_t ff_tns_max_bands_480[]
#define OPEN_READER(name, gb)
const uint16_t *const ff_swb_offset_512[]
void AAC_RENAME() ff_sbr_apply(AACContext *ac, SpectralBandReplication *sbr, int id_aac, INTFLOAT *L, INTFLOAT *R)
Apply one SBR element to one AAC element.
it s the only field you need to keep assuming you have a context There is some magic you don t need to care about around this just let it vf offset
static void skip_bits1(GetBitContext *s)
#define AV_CH_FRONT_RIGHT_OF_CENTER
static int output_configure(AACContext *ac, uint8_t layout_map[MAX_ELEM_ID *4][3], int tags, enum OCStatus oc_type, int get_new_frame)
Configure output channel order based on the current program configuration element.
uint8_t ms_mask[128]
Set if mid/side stereo is used for each scalefactor window band.
int dyn_rng_ctl[17]
DRC magnitude information.
#define AV_LOG_INFO
Standard information.
@ OC_GLOBAL_HDR
Output configuration set in a global header but not yet locked.
@ AOT_AAC_SSR
N (code in SoC repo) Scalable Sample Rate.
int channels
number of audio channels
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel layout
uint8_t pi<< 24) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi - 0x80) *(1.0f/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8, uint8_t,(*(const uint8_t *) pi - 0x80) *(1.0/(1<< 7))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16, int16_t,(*(const int16_t *) pi >> 8)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16, int16_t, *(const int16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16, int16_t, *(const int16_t *) pi *(1.0/(1<< 15))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32, int32_t,(*(const int32_t *) pi >> 24)+0x80) CONV_FUNC_GROUP(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32, int32_t, *(const int32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32, int32_t, *(const int32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, float, av_clip_uint8(lrintf(*(const float *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, float, av_clip_int16(lrintf(*(const float *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, float, av_clipl_int32(llrintf(*(const float *) pi *(1U<< 31)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, double, av_clip_uint8(lrint(*(const double *) pi *(1<< 7))+0x80)) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, double, av_clip_int16(lrint(*(const double *) pi *(1<< 15)))) CONV_FUNC_GROUP(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, double, av_clipl_int32(llrint(*(const double *) pi *(1U<< 31)))) #define SET_CONV_FUNC_GROUP(ofmt, ifmt) static void set_generic_function(AudioConvert *ac) { } void ff_audio_convert_free(AudioConvert **ac) { if(! *ac) return;ff_dither_free(&(*ac) ->dc);av_freep(ac);} AudioConvert *ff_audio_convert_alloc(AVAudioResampleContext *avr, enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels, int sample_rate, int apply_map) { AudioConvert *ac;int in_planar, out_planar;ac=av_mallocz(sizeof(*ac));if(!ac) return NULL;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);return NULL;} return ac;} 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;} else if(in_planar) ac->func_type=CONV_FUNC_TYPE_INTERLEAVE;else ac->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);return ac;} int ff_audio_convert(AudioConvert *ac, AudioData *out, AudioData *in) { int use_generic=1;int len=in->nb_samples;int p;if(ac->dc) { av_log(ac->avr, AV_LOG_TRACE, "%d samples - audio_convert: %s to %s (dithered)\n", len, av_get_sample_fmt_name(ac->in_fmt), av_get_sample_fmt_name(ac->out_fmt));return ff_convert_dither(ac-> in
@ AV_PKT_DATA_JP_DUALMONO
An AV_PKT_DATA_JP_DUALMONO side data packet indicates that the packet may contain "dual mono" audio s...
static av_cold void aac_static_table_init(void)
int nb_samples
number of audio samples (per channel) described by this frame
static void aacdec_init(AACContext *ac)
Single Channel Element - used for both SCE and LFE elements.
static const uint8_t aac_channel_layout_map[16][5][3]
#define i(width, name, range_min, range_max)
and forward the test the status of outputs and forward it to the corresponding return FFERROR_NOT_READY If the filters stores internally one or a few frame for some it can consider them to be part of the FIFO and delay acknowledging a status change accordingly Example code
static const AVOption options[]
SpectralBandReplication sbr
uint8_t * extradata
some codecs need / can use extradata like Huffman tables.
static unsigned int show_bits(GetBitContext *s, int n)
Show 1-25 bits.
void AAC_RENAME() ff_sine_window_init(INTFLOAT *window, int n)
Generate a sine window.
const float ff_aac_eld_window_512[1920]
uint8_t ** extended_data
pointers to the data planes/channels.
channel element - generic struct for SCE/CPE/CCE/LFE
@ AOT_ER_AAC_ELD
N Error Resilient Enhanced Low Delay.
static void apply_independent_coupling(AACContext *ac, SingleChannelElement *target, ChannelElement *cce, int index)
Apply independent channel coupling (applied after IMDCT).
static av_always_inline void predict(PredictorState *ps, float *coef, int output_enable)
#define AV_CH_LAYOUT_NATIVE
Channel mask value used for AVCodecContext.request_channel_layout to indicate that the user requests ...
#define NOISE_PRE_BITS
length of preamble
#define AV_CH_BACK_CENTER
#define FF_DEBUG_STARTCODE
static VLC vlc_spectral[11]
static av_always_inline float cbrtf(float x)
static int decode_ics_info(AACContext *ac, IndividualChannelStream *ics, GetBitContext *gb)
Decode Individual Channel Stream info; reference: table 4.6.
void av_frame_unref(AVFrame *frame)
Unreference all the buffers referenced by frame and reset the frame fields.
static int assign_pair(struct elem_to_channel e2c_vec[MAX_ELEM_ID], uint8_t(*layout_map)[3], int offset, uint64_t left, uint64_t right, int pos)
void * av_mallocz(size_t size)
Allocate a memory block with alignment suitable for all memory accesses (including vectors if availab...
av_cold void ff_mdct15_uninit(MDCT15Context **ps)
OutputConfiguration oc[2]
static void apply_tns(INTFLOAT coef_param[1024], TemporalNoiseShaping *tns, IndividualChannelStream *ics, int decode)
Decode Temporal Noise Shaping filter coefficients and apply all-pole filters; reference: 4....
static void reset_predictor_group(PredictorState *ps, int group_num)
@ OC_TRIAL_PCE
Output configuration under trial specified by an inband PCE.
static void subband_scale(int *dst, int *src, int scale, int offset, int len, void *log_context)
DynamicRangeControl che_drc
const uint16_t *const ff_swb_offset_120[]
#define FF_PROFILE_AAC_HE
@ AOT_ER_BSAC
N Error Resilient Bit-Sliced Arithmetic Coding.
int pce_instance_tag
Indicates with which program the DRC info is associated.
const uint8_t ff_aac_num_swb_1024[]
const char * class_name
The name of the class; usually it is the same name as the context structure type to which the AVClass...
INTFLOAT sf[120]
scalefactors
float ff_aac_kbd_long_1024[1024]
int strict_std_compliance
strictly follow the standard (MPEG-4, ...).
SingleChannelElement * output_element[MAX_CHANNELS]
Points to each SingleChannelElement.
#define AACDEC_FLAGS
AVOptions for Japanese DTV specific extensions (ADTS only)
static const uint8_t * align_get_bits(GetBitContext *s)
void(* update_ltp)(AACContext *ac, SingleChannelElement *sce)
int ch_select[8]
[0] shared list of gains; [1] list of gains for right channel; [2] list of gains for left channel; [3...
Tag MUST be and< 10hcoeff half pel interpolation filter coefficients, hcoeff[0] are the 2 middle coefficients[1] are the next outer ones and so on, resulting in a filter like:...eff[2], hcoeff[1], hcoeff[0], hcoeff[0], hcoeff[1], hcoeff[2] ... the sign of the coefficients is not explicitly stored but alternates after each coeff and coeff[0] is positive, so ...,+,-,+,-,+,+,-,+,-,+,... hcoeff[0] is not explicitly stored but found by subtracting the sum of all stored coefficients with signs from 32 hcoeff[0]=32 - hcoeff[1] - hcoeff[2] - ... a good choice for hcoeff and htaps is htaps=6 hcoeff={40,-10, 2} an alternative which requires more computations at both encoder and decoder side and may or may not be better is htaps=8 hcoeff={42,-14, 6,-2}ref_frames minimum of the number of available reference frames and max_ref_frames for example the first frame after a key frame always has ref_frames=1spatial_decomposition_type wavelet type 0 is a 9/7 symmetric compact integer wavelet 1 is a 5/3 symmetric compact integer wavelet others are reserved stored as delta from last, last is reset to 0 if always_reset||keyframeqlog quality(logarithmic quantizer scale) stored as delta from last, last is reset to 0 if always_reset||keyframemv_scale stored as delta from last, last is reset to 0 if always_reset||keyframe FIXME check that everything works fine if this changes between framesqbias dequantization bias stored as delta from last, last is reset to 0 if always_reset||keyframeblock_max_depth maximum depth of the block tree stored as delta from last, last is reset to 0 if always_reset||keyframequant_table quantization tableHighlevel bitstream structure:==============================--------------------------------------------|Header|--------------------------------------------|------------------------------------|||Block0||||split?||||yes no||||......... intra?||||:Block01 :yes no||||:Block02 :....... ..........||||:Block03 ::y DC ::ref index:||||:Block04 ::cb DC ::motion x :||||......... :cr DC ::motion y :||||....... ..........|||------------------------------------||------------------------------------|||Block1|||...|--------------------------------------------|------------ ------------ ------------|||Y subbands||Cb subbands||Cr subbands||||--- ---||--- ---||--- ---|||||LL0||HL0||||LL0||HL0||||LL0||HL0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||LH0||HH0||||LH0||HH0||||LH0||HH0|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HL1||LH1||||HL1||LH1||||HL1||LH1|||||--- ---||--- ---||--- ---||||--- ---||--- ---||--- ---|||||HH1||HL2||||HH1||HL2||||HH1||HL2|||||...||...||...|||------------ ------------ ------------|--------------------------------------------Decoding process:=================------------|||Subbands|------------||||------------|Intra DC||||LL0 subband prediction ------------|\ Dequantization ------------------- \||Reference frames|\ IDWT|------- -------|Motion \|||Frame 0||Frame 1||Compensation . OBMC v -------|------- -------|--------------. \------> Frame n output Frame Frame<----------------------------------/|...|------------------- Range Coder:============Binary Range Coder:------------------- The implemented range coder is an adapted version based upon "Range encoding: an algorithm for removing redundancy from a digitised message." by G. N. N. Martin. The symbols encoded by the Snow range coder are bits(0|1). The associated probabilities are not fix but change depending on the symbol mix seen so far. bit seen|new state ---------+----------------------------------------------- 0|256 - state_transition_table[256 - old_state];1|state_transition_table[old_state];state_transition_table={ 0, 0, 0, 0, 0, 0, 0, 0, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 56, 57, 58, 59, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 94, 95, 96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111, 112, 113, 114, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149, 150, 151, 152, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 190, 191, 192, 194, 194, 195, 196, 197, 198, 199, 200, 201, 202, 202, 204, 205, 206, 207, 208, 209, 209, 210, 211, 212, 213, 215, 215, 216, 217, 218, 219, 220, 220, 222, 223, 224, 225, 226, 227, 227, 229, 229, 230, 231, 232, 234, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245, 246, 247, 248, 248, 0, 0, 0, 0, 0, 0, 0};FIXME Range Coding of integers:------------------------- FIXME Neighboring Blocks:===================left and top are set to the respective blocks unless they are outside of the image in which case they are set to the Null block top-left is set to the top left block unless it is outside of the image in which case it is set to the left block if this block has no larger parent block or it is at the left side of its parent block and the top right block is not outside of the image then the top right block is used for top-right else the top-left block is used Null block y, cb, cr are 128 level, ref, mx and my are 0 Motion Vector Prediction:=========================1. the motion vectors of all the neighboring blocks are scaled to compensate for the difference of reference frames scaled_mv=(mv *(256 *(current_reference+1)/(mv.reference+1))+128)> the median of the scaled left
#define FF_ARRAY_ELEMS(a)
static ChannelElement * get_che(AACContext *ac, int type, int elem_id)
static void imdct_and_window(TwinVQContext *tctx, enum TwinVQFrameType ftype, int wtype, float *in, float *prev, int ch)
void(* imdct_half)(struct MDCT15Context *s, float *dst, const float *src, ptrdiff_t stride)
main external API structure.
int AAC_RENAME() ff_decode_sbr_extension(AACContext *ac, SpectralBandReplication *sbr, GetBitContext *gb, int crc, int cnt, int id_aac)
Decode one SBR element.
static VLC vlc_scalefactors
#define SHOW_UBITS(name, gb, num)
int ps
-1 implicit, 1 presence
float ff_aac_pow2sf_tab[428]
void ff_aacdec_init_mips(AACContext *c)
#define NOISE_OFFSET
subtracted from global gain, used as offset for the preamble
@ AV_PKT_DATA_NEW_EXTRADATA
The AV_PKT_DATA_NEW_EXTRADATA is used to notify the codec or the format that the extradata buffer was...
static int decode_tns(AACContext *ac, TemporalNoiseShaping *tns, GetBitContext *gb, const IndividualChannelStream *ics)
Decode Temporal Noise Shaping data; reference: table 4.48.
enum WindowSequence window_sequence[2]
av_cold void ff_kbd_window_init(float *window, float alpha, int n)
Generate a Kaiser-Bessel Derived Window.
void AAC_RENAME() ff_aac_sbr_ctx_close(SpectralBandReplication *sbr)
Close one SBR context.
int sbr
-1 implicit, 1 presence
Filter the word “frame” indicates either a video frame or a group of audio samples
int band_incr
Number of DRC bands greater than 1 having DRC info.
#define AV_CH_FRONT_RIGHT
static int * DEC_UQUAD(int *dst, unsigned idx, unsigned sign)
void(* windowing_and_mdct_ltp)(AACContext *ac, INTFLOAT *out, INTFLOAT *in, IndividualChannelStream *ics)
#define AV_CODEC_FLAG_BITEXACT
Use only bitexact stuff (except (I)DCT).
static int frame_configure_elements(AVCodecContext *avctx)
static int decode_extension_payload(AACContext *ac, GetBitContext *gb, int cnt, ChannelElement *che, enum RawDataBlockType elem_type)
Decode extension data (incomplete); reference: table 4.51.
#define avpriv_request_sample(...)
void(* vector_fmul_window)(float *dst, const float *src0, const float *src1, const float *win, int len)
Overlap/add with window function.
static int count_channels(uint8_t(*layout)[3], int tags)
int dyn_rng_sgn[17]
DRC sign information; 0 - positive, 1 - negative.
This structure stores compressed data.
static void imdct_and_windowing_ld(AACContext *ac, SingleChannelElement *sce)
av_cold AVFloatDSPContext * avpriv_float_dsp_alloc(int bit_exact)
Allocate a float DSP context.
float ff_aac_kbd_short_128[128]
#define AVERROR_BUG
Internal bug, also see AVERROR_BUG2.
uint8_t max_sfb
number of scalefactor bands per group
INTFLOAT ltp_state[3072]
time signal for LTP
#define AVERROR_INVALIDDATA
Invalid data found when processing input.
int interpolation_scheme
Indicates the interpolation scheme used in the SBR QMF domain.
static av_always_inline int fixed_sqrt(int x, int bits)
Calculate the square root.
void AAC_RENAME() ff_aac_sbr_init(void)
Initialize SBR.
void AAC_RENAME() ff_aac_sbr_ctx_init(AACContext *ac, SpectralBandReplication *sbr, int id_aac)
Initialize one SBR context.
static int * DEC_UPAIR(int *dst, unsigned idx, unsigned sign)
static int * DEC_SPAIR(int *dst, unsigned idx)
static const INTFLOAT *const tns_tmp2_map[4]
void(* imdct_and_windowing)(AACContext *ac, SingleChannelElement *sce)
enum BandType band_type[128]
band types
uint8_t use_kb_window[2]
If set, use Kaiser-Bessel window, otherwise use a sine window.
VLC_TYPE(* table)[2]
code, bits
@ AOT_AAC_LC
Y Low Complexity.
@ AOT_AAC_LTP
Y Long Term Prediction.
static const float cce_scale[]
int dmono_mode
0->not dmono, 1->use first channel, 2->use second channel
int predictor_reset_group
const uint32_t ff_aac_scalefactor_code[121]
static uint64_t sniff_channel_order(uint8_t(*layout_map)[3], int tags)
int predictor_initialized