FFmpeg  4.0
aac.h
Go to the documentation of this file.
1 /*
2  * AAC definitions and structures
3  * Copyright (c) 2005-2006 Oded Shimon ( ods15 ods15 dyndns org )
4  * Copyright (c) 2006-2007 Maxim Gavrilov ( maxim.gavrilov gmail com )
5  *
6  * This file is part of FFmpeg.
7  *
8  * FFmpeg is free software; you can redistribute it and/or
9  * modify it under the terms of the GNU Lesser General Public
10  * License as published by the Free Software Foundation; either
11  * version 2.1 of the License, or (at your option) any later version.
12  *
13  * FFmpeg is distributed in the hope that it will be useful,
14  * but WITHOUT ANY WARRANTY; without even the implied warranty of
15  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
16  * Lesser General Public License for more details.
17  *
18  * You should have received a copy of the GNU Lesser General Public
19  * License along with FFmpeg; if not, write to the Free Software
20  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
21  */
22 
23 /**
24  * @file
25  * AAC definitions and structures
26  * @author Oded Shimon ( ods15 ods15 dyndns org )
27  * @author Maxim Gavrilov ( maxim.gavrilov gmail com )
28  */
29 
30 #ifndef AVCODEC_AAC_H
31 #define AVCODEC_AAC_H
32 
33 
34 #include "aac_defines.h"
35 #include "libavutil/float_dsp.h"
36 #include "libavutil/fixed_dsp.h"
37 #include "avcodec.h"
38 #if !USE_FIXED
39 #include "mdct15.h"
40 #endif
41 #include "fft.h"
42 #include "mpeg4audio.h"
43 #include "sbr.h"
44 
45 #include <stdint.h>
46 
47 #define MAX_CHANNELS 64
48 #define MAX_ELEM_ID 16
49 
50 #define TNS_MAX_ORDER 20
51 #define MAX_LTP_LONG_SFB 40
52 
53 #define CLIP_AVOIDANCE_FACTOR 0.95f
54 
64 };
65 
71  EXT_SBR_DATA = 0xd,
73 };
74 
80 };
81 
82 enum BandType {
83  ZERO_BT = 0, ///< Scalefactors and spectral data are all zero.
84  FIRST_PAIR_BT = 5, ///< This and later band types encode two values (rather than four) with one code word.
85  ESC_BT = 11, ///< Spectral data are coded with an escape sequence.
86  RESERVED_BT = 12, ///< Band types following are encoded differently from others.
87  NOISE_BT = 13, ///< Spectral data are scaled white noise not coded in the bitstream.
88  INTENSITY_BT2 = 14, ///< Scalefactor data are intensity stereo positions (out of phase).
89  INTENSITY_BT = 15, ///< Scalefactor data are intensity stereo positions (in phase).
90 };
91 
92 #define IS_CODEBOOK_UNSIGNED(x) (((x) - 1) & 10)
93 
101 };
102 
103 /**
104  * The point during decoding at which channel coupling is applied.
105  */
110 };
111 
112 /**
113  * Output configuration status
114  */
115 enum OCStatus {
116  OC_NONE, ///< Output unconfigured
117  OC_TRIAL_PCE, ///< Output configuration under trial specified by an inband PCE
118  OC_TRIAL_FRAME, ///< Output configuration under trial specified by a frame header
119  OC_GLOBAL_HDR, ///< Output configuration set in a global header but not yet locked
120  OC_LOCKED, ///< Output configuration locked in place
121 };
122 
123 typedef struct OutputConfiguration {
127  int channels;
128  uint64_t channel_layout;
131 
132 /**
133  * Predictor State
134  */
135 typedef struct PredictorState {
145 
146 #define MAX_PREDICTORS 672
147 
148 #define SCALE_DIV_512 36 ///< scalefactor difference that corresponds to scale difference in 512 times
149 #define SCALE_ONE_POS 140 ///< scalefactor index that corresponds to scale=1.0
150 #define SCALE_MAX_POS 255 ///< scalefactor index maximum value
151 #define SCALE_MAX_DIFF 60 ///< maximum scalefactor difference allowed by standard
152 #define SCALE_DIFF_ZERO 60 ///< codebook index corresponding to zero scalefactor indices difference
153 
154 #define POW_SF2_ZERO 200 ///< ff_aac_pow2sf_tab index corresponding to pow(2, 0);
155 
156 #define NOISE_PRE 256 ///< preamble for NOISE_BT, put in bitstream with the first noise band
157 #define NOISE_PRE_BITS 9 ///< length of preamble
158 #define NOISE_OFFSET 90 ///< subtracted from global gain, used as offset for the preamble
159 
160 /**
161  * Long Term Prediction
162  */
163 typedef struct LongTermPrediction {
164  int8_t present;
165  int16_t lag;
166  int coef_idx;
168  int8_t used[MAX_LTP_LONG_SFB];
170 
171 /**
172  * Individual Channel Stream
173  */
174 typedef struct IndividualChannelStream {
175  uint8_t max_sfb; ///< number of scalefactor bands per group
176  enum WindowSequence window_sequence[2];
177  uint8_t use_kb_window[2]; ///< If set, use Kaiser-Bessel window, otherwise use a sine window.
179  uint8_t group_len[8];
181  const uint16_t *swb_offset; ///< table of offsets to the lowest spectral coefficient of a scalefactor band, sfb, for a particular window
182  const uint8_t *swb_sizes; ///< table of scalefactor band sizes for a particular window
183  int num_swb; ///< number of scalefactor window bands
189  int predictor_reset_count[31]; ///< used by encoder to count prediction resets
190  uint8_t prediction_used[41];
191  uint8_t window_clipping[8]; ///< set if a certain window is near clipping
192  float clip_avoidance_factor; ///< set if any window is near clipping to the necessary atennuation factor to avoid it
194 
195 /**
196  * Temporal Noise Shaping
197  */
198 typedef struct TemporalNoiseShaping {
199  int present;
200  int n_filt[8];
201  int length[8][4];
202  int direction[8][4];
203  int order[8][4];
204  int coef_idx[8][4][TNS_MAX_ORDER];
205  INTFLOAT coef[8][4][TNS_MAX_ORDER];
207 
208 /**
209  * Dynamic Range Control - decoded from the bitstream but not processed further.
210  */
211 typedef struct DynamicRangeControl {
212  int pce_instance_tag; ///< Indicates with which program the DRC info is associated.
213  int dyn_rng_sgn[17]; ///< DRC sign information; 0 - positive, 1 - negative
214  int dyn_rng_ctl[17]; ///< DRC magnitude information
215  int exclude_mask[MAX_CHANNELS]; ///< Channels to be excluded from DRC processing.
216  int band_incr; ///< Number of DRC bands greater than 1 having DRC info.
217  int interpolation_scheme; ///< Indicates the interpolation scheme used in the SBR QMF domain.
218  int band_top[17]; ///< Indicates the top of the i-th DRC band in units of 4 spectral lines.
219  int prog_ref_level; /**< A reference level for the long-term program audio level for all
220  * channels combined.
221  */
223 
224 typedef struct Pulse {
226  int start;
227  int pos[4];
228  int amp[4];
229 } Pulse;
230 
231 /**
232  * coupling parameters
233  */
234 typedef struct ChannelCoupling {
235  enum CouplingPoint coupling_point; ///< The point during decoding at which coupling is applied.
236  int num_coupled; ///< number of target elements
237  enum RawDataBlockType type[8]; ///< Type of channel element to be coupled - SCE or CPE.
238  int id_select[8]; ///< element id
239  int ch_select[8]; /**< [0] shared list of gains; [1] list of gains for right channel;
240  * [2] list of gains for left channel; [3] lists of gains for both channels
241  */
242  INTFLOAT gain[16][120];
244 
245 /**
246  * Single Channel Element - used for both SCE and LFE elements.
247  */
248 typedef struct SingleChannelElement {
252  enum BandType band_type[128]; ///< band types
253  enum BandType band_alt[128]; ///< alternative band type (used by encoder)
254  int band_type_run_end[120]; ///< band type run end points
255  INTFLOAT sf[120]; ///< scalefactors
256  int sf_idx[128]; ///< scalefactor indices (used by encoder)
257  uint8_t zeroes[128]; ///< band is not coded (used by encoder)
258  uint8_t can_pns[128]; ///< band is allowed to PNS (informative)
259  float is_ener[128]; ///< Intensity stereo pos (used by encoder)
260  float pns_ener[128]; ///< Noise energy values (used by encoder)
261  DECLARE_ALIGNED(32, INTFLOAT, pcoeffs)[1024]; ///< coefficients for IMDCT, pristine
262  DECLARE_ALIGNED(32, INTFLOAT, coeffs)[1024]; ///< coefficients for IMDCT, maybe processed
263  DECLARE_ALIGNED(32, INTFLOAT, saved)[1536]; ///< overlap
264  DECLARE_ALIGNED(32, INTFLOAT, ret_buf)[2048]; ///< PCM output buffer
265  DECLARE_ALIGNED(16, INTFLOAT, ltp_state)[3072]; ///< time signal for LTP
266  DECLARE_ALIGNED(32, AAC_FLOAT, lcoeffs)[1024]; ///< MDCT of LTP coefficients (used by encoder)
267  DECLARE_ALIGNED(32, AAC_FLOAT, prcoeffs)[1024]; ///< Main prediction coefs (used by encoder)
268  PredictorState predictor_state[MAX_PREDICTORS];
269  INTFLOAT *ret; ///< PCM output
271 
272 /**
273  * channel element - generic struct for SCE/CPE/CCE/LFE
274  */
275 typedef struct ChannelElement {
276  int present;
277  // CPE specific
278  int common_window; ///< Set if channels share a common 'IndividualChannelStream' in bitstream.
279  int ms_mode; ///< Signals mid/side stereo flags coding mode (used by encoder)
280  uint8_t is_mode; ///< Set if any bands have been encoded using intensity stereo (used by encoder)
281  uint8_t ms_mask[128]; ///< Set if mid/side stereo is used for each scalefactor window band
282  uint8_t is_mask[128]; ///< Set if intensity stereo is used (used by encoder)
283  // shared
285  // CCE specific
289 
290 /**
291  * main AAC context
292  */
293 struct AACContext {
294  AVClass *class;
297 
298  int is_saved; ///< Set if elements have stored overlap from previous frame.
300 
301  /**
302  * @name Channel element related data
303  * @{
304  */
306  ChannelElement *tag_che_map[4][MAX_ELEM_ID];
309  /** @} */
310 
311  /**
312  * @name temporary aligned temporary buffers
313  * (We do not want to have these on the stack.)
314  * @{
315  */
316  DECLARE_ALIGNED(32, INTFLOAT, buf_mdct)[1024];
317  /** @} */
318 
319  /**
320  * @name Computed / set up during initialization
321  * @{
322  */
327 #if USE_FIXED
328  AVFixedDSPContext *fdsp;
329 #else
334 #endif /* USE_FIXED */
336  /** @} */
337 
338  /**
339  * @name Members used for output
340  * @{
341  */
342  SingleChannelElement *output_element[MAX_CHANNELS]; ///< Points to each SingleChannelElement
343  /** @} */
344 
345 
346  /**
347  * @name Japanese DTV specific extension
348  * @{
349  */
350  int force_dmono_mode;///< 0->not dmono, 1->use first channel, 2->use second channel
351  int dmono_mode; ///< 0->not dmono, 1->use first channel, 2->use second channel
352  /** @} */
353 
355 
359 
361 
362  /* aacdec functions pointers */
366  IndividualChannelStream *ics, int decode);
370  void (*vector_pow43)(int *coefs, int len);
371  void (*subband_scale)(int *dst, int *src, int scale, int offset, int len);
372 
373 };
374 
376 
377 #endif /* AVCODEC_AAC_H */
int predictor_initialized
Definition: aac.h:187
AVFloatDSPContext * fdsp
Definition: aac.h:333
static void imdct_and_windowing(AACContext *ac, SingleChannelElement *sce)
Conduct IMDCT and windowing.
static void apply_ltp(AACContext *ac, SingleChannelElement *sce)
Apply the long term prediction.
Band types following are encoded differently from others.
Definition: aac.h:86
Definition: aac.h:60
This structure describes decoded (raw) audio or video data.
Definition: frame.h:218
AVCodecContext * avctx
Definition: aac.h:295
Definition: aac.h:224
else temp
Definition: vf_mcdeint.c:256
Definition: aac.h:63
Definition: aac.h:56
Definition: aac.h:57
uint8_t pi<< 24) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_U8,(uint64_t)((*(const uint8_t *) pi - 0x80U))<< 56) CONV_FUNC(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8,(*(const uint8_t *) pi - 0x80) *(1.0f/(1<< 7))) CONV_FUNC(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8,(*(const uint8_t *) pi - 0x80) *(1.0/(1<< 7))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16,(*(const int16_t *) pi >>8)+0x80) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_S16,(uint64_t)(*(const int16_t *) pi)<< 48) CONV_FUNC(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16, *(const int16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16, *(const int16_t *) pi *(1.0/(1<< 15))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32,(*(const int32_t *) pi >>24)+0x80) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_S32,(uint64_t)(*(const int32_t *) pi)<< 32) CONV_FUNC(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32, *(const int32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32, *(const int32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S64,(*(const int64_t *) pi >>56)+0x80) CONV_FUNC(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S64, *(const int64_t *) pi *(1.0f/(INT64_C(1)<< 63))) CONV_FUNC(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S64, *(const int64_t *) pi *(1.0/(INT64_C(1)<< 63))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, av_clip_uint8(lrintf(*(const float *) pi *(1<< 7))+0x80)) CONV_FUNC(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, av_clip_int16(lrintf(*(const float *) pi *(1<< 15)))) CONV_FUNC(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, av_clipl_int32(llrintf(*(const float *) pi *(1U<< 31)))) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_FLT, llrintf(*(const float *) pi *(INT64_C(1)<< 63))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, av_clip_uint8(lrint(*(const double *) pi *(1<< 7))+0x80)) CONV_FUNC(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, av_clip_int16(lrint(*(const double *) pi *(1<< 15)))) CONV_FUNC(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, av_clipl_int32(llrint(*(const double *) pi *(1U<< 31)))) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_DBL, llrint(*(const double *) pi *(INT64_C(1)<< 63))) #define FMT_PAIR_FUNC(out, in) static conv_func_type *const fmt_pair_to_conv_functions[AV_SAMPLE_FMT_NB *AV_SAMPLE_FMT_NB]={ FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_S64), };static void cpy1(uint8_t **dst, const uint8_t **src, int len){ memcpy(*dst, *src, len);} static void cpy2(uint8_t **dst, const uint8_t **src, int len){ memcpy(*dst, *src, 2 *len);} static void cpy4(uint8_t **dst, const uint8_t **src, int len){ memcpy(*dst, *src, 4 *len);} static void cpy8(uint8_t **dst, const uint8_t **src, int len){ memcpy(*dst, *src, 8 *len);} AudioConvert *swri_audio_convert_alloc(enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels, const int *ch_map, int flags) { AudioConvert *ctx;conv_func_type *f=fmt_pair_to_conv_functions[av_get_packed_sample_fmt(out_fmt)+AV_SAMPLE_FMT_NB *av_get_packed_sample_fmt(in_fmt)];if(!f) return NULL;ctx=av_mallocz(sizeof(*ctx));if(!ctx) return NULL;if(channels==1){ in_fmt=av_get_planar_sample_fmt(in_fmt);out_fmt=av_get_planar_sample_fmt(out_fmt);} ctx->channels=channels;ctx->conv_f=f;ctx->ch_map=ch_map;if(in_fmt==AV_SAMPLE_FMT_U8||in_fmt==AV_SAMPLE_FMT_U8P) memset(ctx->silence, 0x80, sizeof(ctx->silence));if(out_fmt==in_fmt &&!ch_map) { switch(av_get_bytes_per_sample(in_fmt)){ case 1:ctx->simd_f=cpy1;break;case 2:ctx->simd_f=cpy2;break;case 4:ctx->simd_f=cpy4;break;case 8:ctx->simd_f=cpy8;break;} } if(HAVE_X86ASM &&HAVE_MMX) swri_audio_convert_init_x86(ctx, out_fmt, in_fmt, channels);if(ARCH_ARM) swri_audio_convert_init_arm(ctx, out_fmt, in_fmt, channels);if(ARCH_AARCH64) swri_audio_convert_init_aarch64(ctx, out_fmt, in_fmt, channels);return ctx;} void swri_audio_convert_free(AudioConvert **ctx) { av_freep(ctx);} int swri_audio_convert(AudioConvert *ctx, AudioData *out, AudioData *in, int len) { int ch;int off=0;const int os=(out->planar ? 1 :out->ch_count) *out->bps;unsigned misaligned=0;av_assert0(ctx->channels==out->ch_count);if(ctx->in_simd_align_mask) { int planes=in->planar ? in->ch_count :1;unsigned m=0;for(ch=0;ch< planes;ch++) m|=(intptr_t) in->ch[ch];misaligned|=m &ctx->in_simd_align_mask;} if(ctx->out_simd_align_mask) { int planes=out->planar ? out->ch_count :1;unsigned m=0;for(ch=0;ch< planes;ch++) m|=(intptr_t) out->ch[ch];misaligned|=m &ctx->out_simd_align_mask;} if(ctx->simd_f &&!ctx->ch_map &&!misaligned){ off=len &~15;av_assert1(off >=0);av_assert1(off<=len);av_assert2(ctx->channels==SWR_CH_MAX||!in->ch[ctx->channels]);if(off >0){ if(out->planar==in->planar){ int planes=out->planar ? out->ch_count :1;for(ch=0;ch< planes;ch++){ ctx->simd_f(out-> ch ch
Definition: audioconvert.c:56
INTFLOAT * ret
PCM output.
Definition: aac.h:269
int present
Definition: aac.h:276
int common_window
Set if channels share a common &#39;IndividualChannelStream&#39; in bitstream.
Definition: aac.h:278
static void update_ltp(AACContext *ac, SingleChannelElement *sce)
Update the LTP buffer for next frame.
static void vector_pow43(int *coefs, int len)
Definition: aacdec_fixed.c:151
uint64_t channel_layout
Definition: aac.h:128
static void subband_scale(int *dst, int *src, int scale, int offset, int len)
Definition: aacdec_fixed.c:165
#define MAX_LTP_LONG_SFB
Definition: aac.h:51
Dynamic Range Control - decoded from the bitstream but not processed further.
Definition: aac.h:211
#define src
Definition: vp8dsp.c:254
ChannelPosition
Definition: aac.h:94
static void decode(AVCodecContext *dec_ctx, AVPacket *pkt, AVFrame *frame, FILE *outfile)
Definition: decode_audio.c:42
Spectral data are scaled white noise not coded in the bitstream.
Definition: aac.h:87
Definition: aac.h:58
int band_incr
Number of DRC bands greater than 1 having DRC info.
Definition: aac.h:216
int dmono_mode
0->not dmono, 1->use first channel, 2->use second channel
Definition: aac.h:351
const uint16_t * swb_offset
table of offsets to the lowest spectral coefficient of a scalefactor band, sfb, for a particular wind...
Definition: aac.h:181
float INTFLOAT
Definition: aac_defines.h:86
Definition: aac.h:67
AAC_FLOAT cor0
Definition: aac.h:136
BandType
Definition: aac.h:82
uint8_t
uint8_t layout_map[MAX_ELEM_ID *4][3]
Definition: aac.h:125
AAC_FLOAT var1
Definition: aac.h:139
Output configuration under trial specified by an inband PCE.
Definition: aac.h:117
int warned_960_sbr
Definition: aac.h:358
Definition: aac.h:59
TemporalNoiseShaping tns
Definition: aac.h:250
CouplingPoint
The point during decoding at which channel coupling is applied.
Definition: aac.h:106
int num_coupled
number of target elements
Definition: aac.h:236
FFTContext mdct_ltp
Definition: aac.h:326
#define DECLARE_ALIGNED(n, t, v)
Declare a variable that is aligned in memory.
Definition: mem.h:112
AAC_FLOAT cor1
Definition: aac.h:137
Scalefactor data are intensity stereo positions (in phase).
Definition: aac.h:89
Output configuration set in a global header but not yet locked.
Definition: aac.h:119
int random_state
Definition: aac.h:335
MDCT15Context * mdct480
Definition: aac.h:331
MPEG4AudioConfig m4ac
Definition: aac.h:124
AAC_FLOAT r1
Definition: aac.h:141
SpectralBandReplication sbr
Definition: aac.h:287
FFTContext mdct_small
Definition: aac.h:324
ExtensionPayloadID
Definition: aac.h:66
AAC_FLOAT r0
Definition: aac.h:140
Spectral Band Replication definitions and structures.
uint8_t max_sfb
number of scalefactor bands per group
Definition: aac.h:175
Definition: aac.h:62
static const uint8_t offset[127][2]
Definition: vf_spp.c:92
WindowSequence
Definition: aac.h:75
int num_swb
number of scalefactor window bands
Definition: aac.h:183
int prog_ref_level
A reference level for the long-term program audio level for all channels combined.
Definition: aac.h:219
Output configuration locked in place.
Definition: aac.h:120
Predictor State.
Definition: aac.h:135
int warned_remapping_once
Definition: aac.h:308
AAC_FLOAT x_est
Definition: aac.h:143
Definition: fft.h:88
int predictor_reset_group
Definition: aac.h:188
MDCT15Context * mdct120
Definition: aac.h:330
float AAC_FLOAT
Definition: aac_defines.h:90
FFTContext mdct_ld
Definition: aac.h:325
void ff_aacdec_init_mips(AACContext *c)
Definition: aacdec_mips.c:433
int pce_instance_tag
Indicates with which program the DRC info is associated.
Definition: aac.h:212
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...
int interpolation_scheme
Indicates the interpolation scheme used in the SBR QMF domain.
Definition: aac.h:217
coupling parameters
Definition: aac.h:234
int tags_mapped
Definition: aac.h:307
MDCT15Context * mdct960
Definition: aac.h:332
int force_dmono_mode
0->not dmono, 1->use first channel, 2->use second channel
Definition: aac.h:350
int is_saved
Set if elements have stored overlap from previous frame.
Definition: aac.h:298
int warned_num_aac_frames
Definition: aac.h:357
Libavcodec external API header.
typedef void(RENAME(mix_any_func_type))
Temporal Noise Shaping.
Definition: aac.h:198
Long Term Prediction.
Definition: aac.h:163
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...
main external API structure.
Definition: avcodec.h:1518
IndividualChannelStream ics
Definition: aac.h:249
#define MAX_PREDICTORS
Definition: aac.h:146
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)\", len, av_get_sample_fmt_name(ac->in_fmt), av_get_sample_fmt_name(ac->out_fmt));return ff_convert_dither(ac-> in
#define MAX_ELEM_ID
Definition: aac.h:48
Describe the class of an AVClass context structure.
Definition: log.h:67
Spectral data are coded with an escape sequence.
Definition: aac.h:85
cl_device_type type
const uint8_t * swb_sizes
table of scalefactor band sizes for a particular window
Definition: aac.h:182
OCStatus
Output configuration status.
Definition: aac.h:115
#define MAX_CHANNELS
Definition: aac.h:47
#define TNS_MAX_ORDER
Definition: aac.h:50
main AAC context
Definition: aac.h:293
LongTermPrediction ltp
Definition: aac.h:180
AAC_FLOAT k1
Definition: aac.h:142
ChannelCoupling coup
Definition: aac.h:286
int ms_mode
Signals mid/side stereo flags coding mode (used by encoder)
Definition: aac.h:279
Output configuration under trial specified by a frame header.
Definition: aac.h:118
uint8_t is_mode
Set if any bands have been encoded using intensity stereo (used by encoder)
Definition: aac.h:280
enum OCStatus status
Definition: aac.h:129
Scalefactor data are intensity stereo positions (out of phase).
Definition: aac.h:88
int16_t lag
Definition: aac.h:165
DynamicRangeControl che_drc
Definition: aac.h:299
AVFrame * frame
Definition: aac.h:296
Single Channel Element - used for both SCE and LFE elements.
Definition: aac.h:248
static double c[64]
Definition: aac.h:61
Individual Channel Stream.
Definition: aac.h:174
float clip_avoidance_factor
set if any window is near clipping to the necessary atennuation factor to avoid it ...
Definition: aac.h:192
INTFLOAT coef
Definition: aac.h:167
channel element - generic struct for SCE/CPE/CCE/LFE
Definition: aac.h:275
int start
Definition: aac.h:226
int warned_gain_control
Definition: aac.h:360
static const int16_t coeffs[]
int len
Scalefactors and spectral data are all zero.
Definition: aac.h:83
int num_pulse
Definition: aac.h:225
FILE * out
Definition: movenc.c:54
FFTContext mdct
Definition: aac.h:323
const char int length
Definition: avisynth_c.h:768
int8_t present
Definition: aac.h:164
Spectral Band Replication.
Definition: sbr.h:139
int layout_map_tags
Definition: aac.h:126
AAC_FLOAT var0
Definition: aac.h:138
Output unconfigured.
Definition: aac.h:116
This and later band types encode two values (rather than four) with one code word.
Definition: aac.h:84
RawDataBlockType
Definition: aac.h:55