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 )
6 * This file is part of FFmpeg.
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.
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.
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
25 * AAC definitions and structures
26 * @author Oded Shimon ( ods15 ods15 dyndns org )
27 * @author Maxim Gavrilov ( maxim.gavrilov gmail com )
35 #include "mpeg4audio.h"
39 #define AAC_INIT_VLC_STATIC(num, size) \
40 INIT_VLC_STATIC(&vlc_spectral[num], 6, ff_aac_spectral_sizes[num], \
41 ff_aac_spectral_bits[num], sizeof( ff_aac_spectral_bits[num][0]), sizeof( ff_aac_spectral_bits[num][0]), \
42 ff_aac_spectral_codes[num], sizeof(ff_aac_spectral_codes[num][0]), sizeof(ff_aac_spectral_codes[num][0]), \
45 #define MAX_CHANNELS 64
47 #define IVQUANT_SIZE 1024
49 enum AudioObjectType {
52 AOT_AAC_MAIN, ///< Y Main
53 AOT_AAC_LC, ///< Y Low Complexity
54 AOT_AAC_SSR, ///< N (code in SoC repo) Scalable Sample Rate
55 AOT_AAC_LTP, ///< N (code in SoC repo) Long Term Prediction
56 AOT_SBR, ///< N (in progress) Spectral Band Replication
57 AOT_AAC_SCALABLE, ///< N Scalable
58 AOT_TWINVQ, ///< N Twin Vector Quantizer
59 AOT_CELP, ///< N Code Excited Linear Prediction
60 AOT_HVXC, ///< N Harmonic Vector eXcitation Coding
61 AOT_TTSI = 12, ///< N Text-To-Speech Interface
62 AOT_MAINSYNTH, ///< N Main Synthesis
63 AOT_WAVESYNTH, ///< N Wavetable Synthesis
64 AOT_MIDI, ///< N General MIDI
65 AOT_SAFX, ///< N Algorithmic Synthesis and Audio Effects
66 AOT_ER_AAC_LC, ///< N Error Resilient Low Complexity
67 AOT_ER_AAC_LTP = 19, ///< N Error Resilient Long Term Prediction
68 AOT_ER_AAC_SCALABLE, ///< N Error Resilient Scalable
69 AOT_ER_TWINVQ, ///< N Error Resilient Twin Vector Quantizer
70 AOT_ER_BSAC, ///< N Error Resilient Bit-Sliced Arithmetic Coding
71 AOT_ER_AAC_LD, ///< N Error Resilient Low Delay
72 AOT_ER_CELP, ///< N Error Resilient Code Excited Linear Prediction
73 AOT_ER_HVXC, ///< N Error Resilient Harmonic Vector eXcitation Coding
74 AOT_ER_HILN, ///< N Error Resilient Harmonic and Individual Lines plus Noise
75 AOT_ER_PARAM, ///< N Error Resilient Parametric
76 AOT_SSC, ///< N SinuSoidal Coding
79 enum ExtensionPayloadID {
83 EXT_DYNAMIC_RANGE = 0xb,
85 EXT_SBR_DATA_CRC = 0xe,
96 ZERO_BT = 0, ///< Scalefactors and spectral data are all zero.
97 FIRST_PAIR_BT = 5, ///< This and later band types encode two values (rather than four) with one code word.
98 ESC_BT = 11, ///< Spectral data are coded with an escape sequence.
99 NOISE_BT = 13, ///< Spectral data are scaled white noise not coded in the bitstream.
100 INTENSITY_BT2 = 14, ///< Scalefactor data are intensity stereo positions.
101 INTENSITY_BT = 15, ///< Scalefactor data are intensity stereo positions.
104 #define IS_CODEBOOK_UNSIGNED(x) ((x - 1) & 10)
106 enum ChannelPosition {
107 AAC_CHANNEL_FRONT = 1,
108 AAC_CHANNEL_SIDE = 2,
109 AAC_CHANNEL_BACK = 3,
122 * coupling parameters
130 AVCodecContext * avccontext;
132 MPEG4AudioConfig m4ac;
134 int is_saved; ///< Set if elements have stored overlap from previous frame.
135 DynamicRangeControl che_drc;
137 enum ChannelPosition che_pos[4][MAX_ELEM_ID]; /**< channel element channel mapping with the
138 * first index as the first 4 raw data block types
142 * @defgroup tables Computed / set up during initialization.
146 MDCTContext mdct_small;
151 * @defgroup output Members used for output interleaving.
154 float *output_data[MAX_CHANNELS]; ///< Points to each element's 'ret' buffer (PCM output).
155 float add_bias; ///< offset for dsp.float_to_int16
156 float sf_scale; ///< Pre-scale for correct IMDCT and dsp.float_to_int16.
157 int sf_offset; ///< offset into pow2sf_tab as appropriate for dsp.float_to_int16
162 #endif /* FFMPEG_AAC_H */