1 /*
2 * audio encoder psychoacoustic model
3 * Copyright (C) 2008 Konstantin Shishkov
4 *
5 * This file is part of FFmpeg.
6 *
7 * FFmpeg is free software; you can redistribute it and/or
8 * modify it under the terms of the GNU Lesser General Public
9 * License as published by the Free Software Foundation; either
10 * version 2.1 of the License, or (at your option) any later version.
11 *
12 * FFmpeg is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
15 * Lesser General Public License for more details.
16 *
17 * You should have received a copy of the GNU Lesser General Public
18 * License along with FFmpeg; if not, write to the Free Software
19 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20 */
21
22 #ifndef AVCODEC_PSYMODEL_H
23 #define AVCODEC_PSYMODEL_H
24
26
27 /** maximum possible number of bands */
28 #define PSY_MAX_BANDS 128
29 /** maximum number of channels */
30 #define PSY_MAX_CHANS 20
31
32 #define AAC_CUTOFF(s) (s->bit_rate ? FFMIN3(4000 + s->bit_rate/8, 12000 + s->bit_rate/32, s->sample_rate / 2) : (s->sample_rate / 2))
33
34 /**
35 * single band psychoacoustic information
36 */
44
45 /**
46 * single channel psychoacoustic information
47 */
50 float entropy;
///< total PE for this channel
52
53 /**
54 * psychoacoustic information for an arbitrary group of channels
55 */
61
62 /**
63 * windowing related information
64 */
66 int window_type[3];
///< window type (short/long/transitional, etc.) - current, previous and next
69 int grouping[8];
///< window grouping (for e.g. AAC)
70 int *
window_sizes;
///< sequence of window sizes inside one frame (for eg. WMA)
72
73 /**
74 * context used by psychoacoustic model
75 */
79
83
84 uint8_t **
bands;
///< scalefactor band sizes for possible frame sizes
85 int *
num_bands;
///< number of scalefactor bands for possible frame sizes
86 int num_lens;
///< number of scalefactor band sets
87
88 struct {
89 int size;
///< size of the bitresevoir in bits
90 int bits;
///< number of bits used in the bitresevoir
92
95
96 /**
97 * codec-specific psychoacoustic model implementation
98 */
102
103 /**
104 * Suggest window sequence for channel.
105 *
106 * @param ctx model context
107 * @param audio samples for the current frame
108 * @param la lookahead samples (NULL when unavailable)
109 * @param channel number of channel element to analyze
110 * @param prev_type previous window type
111 *
112 * @return suggested window information in a structure
113 */
115
116 /**
117 * Perform psychoacoustic analysis and set band info (threshold, energy) for a group of channels.
118 *
119 * @param ctx model context
120 * @param channel channel number of the first channel in the group to perform analysis on
121 * @param coeffs array of pointers to the transformed coefficients
122 * @param wi window information for the channels in the group
123 */
125
128
129 /**
130 * Initialize psychoacoustic model.
131 *
132 * @param ctx model context
133 * @param avctx codec context
134 * @param num_lens number of possible frame lengths
135 * @param bands scalefactor band lengths for all frame lengths
136 * @param num_bands number of scalefactor bands for all frame lengths
137 * @param num_groups number of channel groups
138 * @param group_map array with # of channels in group - 1, for each group
139 *
140 * @return zero if successful, a negative value if not
141 */
143 const uint8_t **bands,
const int *num_bands,
144 int num_groups,
const uint8_t *group_map);
145
146 /**
147 * Determine what group a channel belongs to.
148 *
149 * @param ctx psymodel context
150 * @param channel channel to locate the group for
151 *
152 * @return pointer to the FFPsyChannelGroup this channel belongs to
153 */
155
156 /**
157 * Cleanup model context at the end.
158 *
159 * @param ctx model context
160 */
162
163
164 /**************************************************************************
165 * Audio preprocessing stuff. *
166 * This should be moved into some audio filter eventually. *
167 **************************************************************************/
169
170 /**
171 * psychoacoustic model audio preprocessing initialization
172 */
174
175 /**
176 * Preprocess several channel in audio frame in order to compress it better.
177 *
178 * @param ctx preprocessing context
179 * @param audio samples to be filtered (in place)
180 * @param channels number of channel to preprocess
181 */
183
184 /**
185 * Cleanup audio preprocessing module.
186 */
188
189 #endif /* AVCODEC_PSYMODEL_H */