Revision bf689db0

View differences:

libavcodec/aacpsy.c
1
/*
2
 * AAC 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
/**
23
 * @file aacpsy.c
24
 * AAC encoder psychoacoustic model
25
 */
26

  
27
#include "avcodec.h"
28
#include "aacpsy.h"
29
#include "aactab.h"
30

  
31
/***********************************
32
 *              TODOs:
33
 * General:
34
 * better audio preprocessing (add DC highpass filter?)
35
 * more psy models
36
 * maybe improve coefficient quantization function in some way
37
 *
38
 * 3GPP-based psy model:
39
 * thresholds linearization after their modifications for attaining given bitrate
40
 * try other bitrate controlling mechanism (maybe use ratecontrol.c?)
41
 * control quality for quality-based output
42
 **********************************/
43

  
44
/**
45
 * Quantize one coefficient.
46
 * @return absolute value of the quantized coefficient
47
 * @see 3GPP TS26.403 5.6.2 "Scalefactor determination"
48
 */
49
static av_always_inline int quant(float coef, const float Q)
50
{
51
    return av_clip((int)(pow(fabsf(coef) * Q, 0.75) + 0.4054), 0, 8191);
52
}
53

  
54
static inline float get_approximate_quant_error(float *c, int size, int scale_idx)
55
{
56
    int i;
57
    int q;
58
    float coef, unquant, sum = 0.0f;
59
    const float Q  = ff_aac_pow2sf_tab[200 - scale_idx + SCALE_ONE_POS - SCALE_DIV_512];
60
    const float IQ = ff_aac_pow2sf_tab[200 + scale_idx - SCALE_ONE_POS + SCALE_DIV_512];
61
    for(i = 0; i < size; i++){
62
        coef = fabs(c[i]);
63
        q = quant(c[i], Q);
64
        unquant = (q * cbrt(q)) * IQ;
65
        sum += (coef - unquant) * (coef - unquant);
66
    }
67
    return sum;
68
}
69

  
70
/**
71
 * constants for 3GPP AAC psychoacoustic model
72
 * @{
73
 */
74
#define PSY_3GPP_SPREAD_LOW  1.5f // spreading factor for ascending threshold spreading  (15 dB/Bark)
75
#define PSY_3GPP_SPREAD_HI   3.0f // spreading factor for descending threshold spreading (30 dB/Bark)
76
/**
77
 * @}
78
 */
79

  
80
/**
81
 * information for single band used by 3GPP TS26.403-inspired psychoacoustic model
82
 */
83
typedef struct Psy3gppBand{
84
    float energy;    ///< band energy
85
    float ffac;      ///< form factor
86
}Psy3gppBand;
87

  
88
/**
89
 * psychoacoustic model frame type-dependent coefficients
90
 */
91
typedef struct Psy3gppCoeffs{
92
    float ath       [64]; ///< absolute threshold of hearing per bands
93
    float barks     [64]; ///< Bark value for each spectral band in long frame
94
    float spread_low[64]; ///< spreading factor for low-to-high threshold spreading in long frame
95
    float spread_hi [64]; ///< spreading factor for high-to-low threshold spreading in long frame
96
}Psy3gppCoeffs;
97

  
98
/**
99
 * Calculate Bark value for given line.
100
 */
101
static inline float calc_bark(float f)
102
{
103
    return 13.3f * atanf(0.00076f * f) + 3.5f * atanf((f / 7500.0f) * (f / 7500.0f));
104
}
libavcodec/aacpsy.h
1
/*
2
 * AAC 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 FFMPEG_AACPSY_H
23
#define FFMPEG_AACPSY_H
24

  
25
#include "avcodec.h"
26
#include "aac.h"
27
#include "lowpass.h"
28

  
29
enum AACPsyModelType{
30
    AAC_PSY_TEST,              ///< a sample model to exercise encoder
31
    AAC_PSY_3GPP,              ///< model following recommendations from 3GPP TS 26.403
32

  
33
    AAC_NB_PSY_MODELS          ///< total number of psychoacoustic models, since it's not a part of the ABI new models can be added freely
34
};
35

  
36
/**
37
 * context used by psychoacoustic model
38
 */
39
typedef struct AACPsyContext {
40
    AVCodecContext *avctx;            ///< encoder context
41
}AACPsyContext;
42

  
43
/**
44
 * Cleanup model context at the end.
45
 *
46
 * @param ctx model context
47
 */
48
void ff_aac_psy_end(AACPsyContext *ctx);
49

  
50
#endif /* FFMPEG_AACPSY_H */

Also available in: Unified diff