78e65cd7 |
/*
* audio encoder psychoacoustic model
* Copyright (C) 2008 Konstantin Shishkov
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#ifndef AVCODEC_PSYMODEL_H
#define AVCODEC_PSYMODEL_H
#include "avcodec.h"
/** maximum possible number of bands */
#define PSY_MAX_BANDS 128 |
5371803d |
/** maximum number of channels */
#define PSY_MAX_CHANS 20 |
78e65cd7 |
|
72dabdfc |
#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))
|
78e65cd7 |
/**
* single band psychoacoustic information
*/ |
fd257dc4 |
typedef struct FFPsyBand { |
78e65cd7 |
int bits;
float energy;
float threshold;
float distortion;
float perceptual_weight; |
fd257dc4 |
} FFPsyBand; |
78e65cd7 |
/** |
0bc01cc9 |
* single channel psychoacoustic information
*/
typedef struct FFPsyChannel {
FFPsyBand psy_bands[PSY_MAX_BANDS]; ///< channel bands information
float entropy; ///< total PE for this channel
} FFPsyChannel;
/**
* psychoacoustic information for an arbitrary group of channels
*/
typedef struct FFPsyChannelGroup {
FFPsyChannel *ch[PSY_MAX_CHANS]; ///< pointers to the individual channels in the group
uint8_t num_ch; ///< number of channels in this group
uint8_t coupling[PSY_MAX_BANDS]; ///< allow coupling for this band in the group
} FFPsyChannelGroup;
/** |
78e65cd7 |
* windowing related information
*/ |
fd257dc4 |
typedef struct FFPsyWindowInfo { |
78e65cd7 |
int window_type[3]; ///< window type (short/long/transitional, etc.) - current, previous and next
int window_shape; ///< window shape (sine/KBD/whatever)
int num_windows; ///< number of windows in a frame
int grouping[8]; ///< window grouping (for e.g. AAC)
int *window_sizes; ///< sequence of window sizes inside one frame (for eg. WMA) |
fd257dc4 |
} FFPsyWindowInfo; |
78e65cd7 |
/**
* context used by psychoacoustic model
*/ |
fd257dc4 |
typedef struct FFPsyContext { |
78e65cd7 |
AVCodecContext *avctx; ///< encoder context
const struct FFPsyModel *model; ///< encoder-specific model functions
|
0bc01cc9 |
FFPsyChannel *ch; ///< single channel information
FFPsyChannelGroup *group; ///< channel group information
int num_groups; ///< number of channel groups |
78e65cd7 |
uint8_t **bands; ///< scalefactor band sizes for possible frame sizes
int *num_bands; ///< number of scalefactor bands for possible frame sizes
int num_lens; ///< number of scalefactor band sets
|
5371803d |
struct {
int size; ///< size of the bitresevoir in bits
int bits; ///< number of bits used in the bitresevoir
} bitres;
|
78e65cd7 |
void* model_priv_data; ///< psychoacoustic model implementation private data |
fd257dc4 |
} FFPsyContext; |
78e65cd7 |
/**
* codec-specific psychoacoustic model implementation
*/
typedef struct FFPsyModel {
const char *name;
int (*init) (FFPsyContext *apc); |
b58e2985 |
/**
* Suggest window sequence for channel.
*
* @param ctx model context
* @param audio samples for the current frame
* @param la lookahead samples (NULL when unavailable)
* @param channel number of channel element to analyze
* @param prev_type previous window type
*
* @return suggested window information in a structure
*/ |
025ccf1f |
FFPsyWindowInfo (*window)(FFPsyContext *ctx, const float *audio, const float *la, int channel, int prev_type); |
b58e2985 |
/** |
0bc01cc9 |
* Perform psychoacoustic analysis and set band info (threshold, energy) for a group of channels. |
b58e2985 |
* |
0bc01cc9 |
* @param ctx model context
* @param channel channel number of the first channel in the group to perform analysis on
* @param coeffs array of pointers to the transformed coefficients
* @param wi window information for the channels in the group |
b58e2985 |
*/ |
d3a6c2ab |
void (*analyze)(FFPsyContext *ctx, int channel, const float **coeffs, const FFPsyWindowInfo *wi); |
b58e2985 |
|
78e65cd7 |
void (*end) (FFPsyContext *apc); |
fd257dc4 |
} FFPsyModel; |
78e65cd7 |
/**
* Initialize psychoacoustic model.
*
* @param ctx model context
* @param avctx codec context
* @param num_lens number of possible frame lengths
* @param bands scalefactor band lengths for all frame lengths
* @param num_bands number of scalefactor bands for all frame lengths |
0bc01cc9 |
* @param num_groups number of channel groups
* @param group_map array with # of channels in group - 1, for each group |
78e65cd7 |
*
* @return zero if successful, a negative value if not
*/ |
94ee7da0 |
int ff_psy_init(FFPsyContext *ctx, AVCodecContext *avctx, int num_lens,
const uint8_t **bands, const int *num_bands,
int num_groups, const uint8_t *group_map); |
0bc01cc9 |
/**
* Determine what group a channel belongs to.
*
* @param ctx psymodel context
* @param channel channel to locate the group for
*
* @return pointer to the FFPsyChannelGroup this channel belongs to
*/
FFPsyChannelGroup *ff_psy_find_group(FFPsyContext *ctx, int channel); |
78e65cd7 |
/**
* Cleanup model context at the end.
*
* @param ctx model context
*/ |
94ee7da0 |
void ff_psy_end(FFPsyContext *ctx); |
78e65cd7 |
/**************************************************************************
* Audio preprocessing stuff. *
* This should be moved into some audio filter eventually. *
**************************************************************************/
struct FFPsyPreprocessContext;
/**
* psychoacoustic model audio preprocessing initialization
*/ |
94ee7da0 |
struct FFPsyPreprocessContext *ff_psy_preprocess_init(AVCodecContext *avctx); |
78e65cd7 |
/**
* Preprocess several channel in audio frame in order to compress it better.
*
* @param ctx preprocessing context |
9b8e2a87 |
* @param audio samples to be filtered (in place)
* @param channels number of channel to preprocess |
78e65cd7 |
*/ |
9b8e2a87 |
void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx, float **audio, int channels); |
78e65cd7 |
/**
* Cleanup audio preprocessing module.
*/ |
94ee7da0 |
void ff_psy_preprocess_end(struct FFPsyPreprocessContext *ctx); |
78e65cd7 |
#endif /* AVCODEC_PSYMODEL_H */ |