libavcodec/psymodel.h

Go to the documentation of this file.

/*
 * 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"

#define PSY_MAX_BANDS 128

typedef struct FFPsyBand {
    int   bits;
    float energy;
    float threshold;
    float distortion;
    float perceptual_weight;
} FFPsyBand;

typedef struct FFPsyWindowInfo {
    int window_type[3];               
    int window_shape;                 
    int num_windows;                  
    int grouping[8];                  
    int *window_sizes;                
} FFPsyWindowInfo;

typedef struct FFPsyContext {
    AVCodecContext *avctx;            
    const struct FFPsyModel *model;   

    FFPsyBand *psy_bands;             

    uint8_t **bands;                  
    int     *num_bands;               
    int num_lens;                     

    void* model_priv_data;            
} FFPsyContext;

typedef struct FFPsyModel {
    const char *name;
    int  (*init)   (FFPsyContext *apc);
    FFPsyWindowInfo (*window)(FFPsyContext *ctx, const int16_t *audio, const int16_t *la, int channel, int prev_type);
    void (*analyze)(FFPsyContext *ctx, int channel, const float *coeffs, FFPsyWindowInfo *wi);
    void (*end)    (FFPsyContext *apc);
} FFPsyModel;

av_cold int ff_psy_init(FFPsyContext *ctx, AVCodecContext *avctx,
                        int num_lens,
                        const uint8_t **bands, const int* num_bands);

FFPsyWindowInfo ff_psy_suggest_window(FFPsyContext *ctx,
                                      const int16_t *audio, const int16_t *la,
                                      int channel, int prev_type);


void ff_psy_set_band_info(FFPsyContext *ctx, int channel, const float *coeffs,
                          FFPsyWindowInfo *wi);

av_cold void ff_psy_end(FFPsyContext *ctx);


/**************************************************************************
 *                       Audio preprocessing stuff.                       *
 *       This should be moved into some audio filter eventually.          *
 **************************************************************************/
struct FFPsyPreprocessContext;

av_cold struct FFPsyPreprocessContext* ff_psy_preprocess_init(AVCodecContext *avctx);

void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx,
                       const int16_t *audio, int16_t *dest,
                       int tag, int channels);

av_cold void ff_psy_preprocess_end(struct FFPsyPreprocessContext *ctx);

#endif /* AVCODEC_PSYMODEL_H */

---