Go to the documentation of this file.
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
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  */
22 #include <string.h>
24 #include "avcodec.h"
25 #include "psymodel.h"
26 #include "iirfilter.h"
27 #include "libavutil/mem.h"
29 extern const FFPsyModel ff_aac_psy_model;
31 av_cold int ff_psy_init(FFPsyContext *ctx, AVCodecContext *avctx, int num_lens,
32  const uint8_t **bands, const int* num_bands,
33  int num_groups, const uint8_t *group_map)
34 {
35  int i, j, k = 0;
37  ctx->avctx = avctx;
38  ctx->ch = av_mallocz_array(sizeof(ctx->ch[0]), avctx->channels * 2);
39  ctx->group = av_mallocz_array(sizeof(ctx->group[0]), num_groups);
40  ctx->bands = av_malloc_array (sizeof(ctx->bands[0]), num_lens);
41  ctx->num_bands = av_malloc_array (sizeof(ctx->num_bands[0]), num_lens);
42  ctx->cutoff = avctx->cutoff;
44  if (!ctx->ch || !ctx->group || !ctx->bands || !ctx->num_bands) {
45  ff_psy_end(ctx);
46  return AVERROR(ENOMEM);
47  }
49  memcpy(ctx->bands, bands, sizeof(ctx->bands[0]) * num_lens);
50  memcpy(ctx->num_bands, num_bands, sizeof(ctx->num_bands[0]) * num_lens);
52  /* assign channels to groups (with virtual channels for coupling) */
53  for (i = 0; i < num_groups; i++) {
54  /* NOTE: Add 1 to handle the AAC chan_config without modification.
55  * This has the side effect of allowing an array of 0s to map
56  * to one channel per group.
57  */
58  ctx->group[i].num_ch = group_map[i] + 1;
59  for (j = 0; j < ctx->group[i].num_ch * 2; j++)
60  ctx->group[i].ch[j] = &ctx->ch[k++];
61  }
63  switch (ctx->avctx->codec_id) {
64  case AV_CODEC_ID_AAC:
65  ctx->model = &ff_aac_psy_model;
66  break;
67  }
68  if (ctx->model->init)
69  return ctx->model->init(ctx);
70  return 0;
71 }
74 {
75  int i = 0, ch = 0;
77  while (ch <= channel)
78  ch += ctx->group[i++].num_ch;
80  return &ctx->group[i-1];
81 }
84 {
85  if (ctx->model && ctx->model->end)
86  ctx->model->end(ctx);
87  av_freep(&ctx->bands);
88  av_freep(&ctx->num_bands);
89  av_freep(&ctx->group);
90  av_freep(&ctx->ch);
91 }
93 typedef struct FFPsyPreprocessContext{
95  float stereo_att;
101 #define FILT_ORDER 4
104 {
106  int i;
107  float cutoff_coeff = 0;
108  ctx = av_mallocz(sizeof(FFPsyPreprocessContext));
109  if (!ctx)
110  return NULL;
111  ctx->avctx = avctx;
113  /* AAC has its own LP method */
114  if (avctx->codec_id != AV_CODEC_ID_AAC) {
115  if (avctx->cutoff > 0)
116  cutoff_coeff = 2.0 * avctx->cutoff / avctx->sample_rate;
118  if (cutoff_coeff && cutoff_coeff < 0.98)
121  cutoff_coeff, 0.0, 0.0);
122  if (ctx->fcoeffs) {
123  ctx->fstate = av_mallocz_array(sizeof(ctx->fstate[0]), avctx->channels);
124  if (!ctx->fstate) {
125  av_free(ctx->fcoeffs);
126  av_free(ctx);
127  return NULL;
128  }
129  for (i = 0; i < avctx->channels; i++)
131  }
132  }
134  ff_iir_filter_init(&ctx->fiir);
136  return ctx;
137 }
139 void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx, float **audio, int channels)
140 {
141  int ch;
142  int frame_size = ctx->avctx->frame_size;
143  FFIIRFilterContext *iir = &ctx->fiir;
145  if (ctx->fstate) {
146  for (ch = 0; ch < channels; ch++)
147  iir->filter_flt(ctx->fcoeffs, ctx->fstate[ch], frame_size,
148  &audio[ch][frame_size], 1, &audio[ch][frame_size], 1);
149  }
150 }
153 {
154  int i;
156  if (ctx->fstate)
157  for (i = 0; i < ctx->avctx->channels; i++)
159  av_freep(&ctx->fstate);
160  av_free(ctx);
161 }
#define NULL
Definition: coverity.c:32
void(* end)(FFPsyContext *apc)
Definition: psymodel.h:141
uint8_t ** bands
scalefactor band sizes for possible frame sizes
Definition: psymodel.h:98
FFPsyChannelGroup * group
channel group information
Definition: psymodel.h:94
Memory handling functions.
av_cold void ff_psy_preprocess_end(struct FFPsyPreprocessContext *ctx)
Cleanup audio preprocessing module.
Definition: psymodel.c:152
psychoacoustic information for an arbitrary group of channels
Definition: psymodel.h:68
av_cold 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)
Initialize psychoacoustic model.
Definition: psymodel.c:31
void * av_mallocz(size_t size)
Allocate a memory block with alignment suitable for all memory accesses (including vectors if availab...
Definition: mem.c:237
int * num_bands
number of scalefactor bands for possible frame sizes
Definition: psymodel.h:99
av_cold struct FFIIRFilterState * ff_iir_filter_init_state(int order)
Create new filter state.
Definition: iirfilter.c:201
av_cold struct FFIIRFilterCoeffs * ff_iir_filter_init_coeffs(void *avc, enum IIRFilterType filt_type, enum IIRFilterMode filt_mode, int order, float cutoff_ratio, float stopband, float ripple)
Initialize filter coefficients.
Definition: iirfilter.c:162
#define av_cold
Definition: attributes.h:88
void(* filter_flt)(const struct FFIIRFilterCoeffs *coeffs, struct FFIIRFilterState *state, int size, const float *src, ptrdiff_t sstep, float *dst, ptrdiff_t dstep)
Perform IIR filtering on floating-point input samples.
Definition: iirfilter.h:63
struct FFIIRFilterCoeffs * fcoeffs
Definition: psymodel.c:96
context used by psychoacoustic model
Definition: psymodel.h:89
const FFPsyModel ff_aac_psy_model
Definition: aacpsy.c:1018
Definition: aptx.h:33
AVCodecContext * avctx
Definition: psymodel.c:94
FFPsyChannel * ch[PSY_MAX_CHANS]
pointers to the individual channels in the group
Definition: psymodel.h:69
av_cold void ff_iir_filter_free_statep(struct FFIIRFilterState **state)
Free and zero filter state.
Definition: iirfilter.c:304
codec-specific psychoacoustic model implementation
Definition: psymodel.h:114
IIR filter state.
Definition: iirfilter.c:47
int(* init)(FFPsyContext *apc)
Definition: psymodel.h:116
uint8_t num_ch
number of channels in this group
Definition: psymodel.h:70
AVFormatContext * ctx
Definition: movenc.c:48
int frame_size
Number of samples per channel in an audio frame.
Definition: avcodec.h:1206
int frame_size
Definition: mxfenc.c:2139
Libavcodec external API header.
enum AVCodecID codec_id
Definition: avcodec.h:536
int sample_rate
samples per second
Definition: avcodec.h:1186
FFPsyChannelGroup * ff_psy_find_group(FFPsyContext *ctx, int channel)
Determine what group a channel belongs to.
Definition: psymodel.c:73
main external API structure.
Definition: avcodec.h:526
static const float bands[]
int cutoff
lowpass frequency cutoff for analysis
Definition: psymodel.h:96
const struct FFPsyModel * model
encoder-specific model functions
Definition: psymodel.h:91
uint8_t pi<< 24) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_U8,(uint64_t)((*(const uint8_t *) pi-0x80U))<< 56) CONV_FUNC(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_U8,(*(const uint8_t *) pi-0x80)*(1.0f/(1<< 7))) CONV_FUNC(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_U8,(*(const uint8_t *) pi-0x80)*(1.0/(1<< 7))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S16,(*(const int16_t *) pi >>8)+0x80) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_S16,(uint64_t)(*(const int16_t *) pi)<< 48) CONV_FUNC(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S16,*(const int16_t *) pi *(1.0f/(1<< 15))) CONV_FUNC(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S16,*(const int16_t *) pi *(1.0/(1<< 15))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S32,(*(const int32_t *) pi >>24)+0x80) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_S32,(uint64_t)(*(const int32_t *) pi)<< 32) CONV_FUNC(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S32,*(const int32_t *) pi *(1.0f/(1U<< 31))) CONV_FUNC(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S32,*(const int32_t *) pi *(1.0/(1U<< 31))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_S64,(*(const int64_t *) pi >>56)+0x80) CONV_FUNC(AV_SAMPLE_FMT_FLT, float, AV_SAMPLE_FMT_S64,*(const int64_t *) pi *(1.0f/(UINT64_C(1)<< 63))) CONV_FUNC(AV_SAMPLE_FMT_DBL, double, AV_SAMPLE_FMT_S64,*(const int64_t *) pi *(1.0/(UINT64_C(1)<< 63))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_FLT, av_clip_uint8(lrintf(*(const float *) pi *(1<< 7))+0x80)) CONV_FUNC(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_FLT, av_clip_int16(lrintf(*(const float *) pi *(1<< 15)))) CONV_FUNC(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_FLT, av_clipl_int32(llrintf(*(const float *) pi *(1U<< 31)))) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_FLT, llrintf(*(const float *) pi *(UINT64_C(1)<< 63))) CONV_FUNC(AV_SAMPLE_FMT_U8, uint8_t, AV_SAMPLE_FMT_DBL, av_clip_uint8(lrint(*(const double *) pi *(1<< 7))+0x80)) CONV_FUNC(AV_SAMPLE_FMT_S16, int16_t, AV_SAMPLE_FMT_DBL, av_clip_int16(lrint(*(const double *) pi *(1<< 15)))) CONV_FUNC(AV_SAMPLE_FMT_S32, int32_t, AV_SAMPLE_FMT_DBL, av_clipl_int32(llrint(*(const double *) pi *(1U<< 31)))) CONV_FUNC(AV_SAMPLE_FMT_S64, int64_t, AV_SAMPLE_FMT_DBL, llrint(*(const double *) pi *(UINT64_C(1)<< 63)))#define FMT_PAIR_FUNC(out, in) static conv_func_type *const fmt_pair_to_conv_functions[AV_SAMPLE_FMT_NB *AV_SAMPLE_FMT_NB]={FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_U8), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_S16), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_S32), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_FLT), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_DBL), FMT_PAIR_FUNC(AV_SAMPLE_FMT_U8, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S16, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S32, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_FLT, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_DBL, AV_SAMPLE_FMT_S64), FMT_PAIR_FUNC(AV_SAMPLE_FMT_S64, AV_SAMPLE_FMT_S64),};static void cpy1(uint8_t **dst, const uint8_t **src, int len){memcpy(*dst,*src, len);}static void cpy2(uint8_t **dst, const uint8_t **src, int len){memcpy(*dst,*src, 2 *len);}static void cpy4(uint8_t **dst, const uint8_t **src, int len){memcpy(*dst,*src, 4 *len);}static void cpy8(uint8_t **dst, const uint8_t **src, int len){memcpy(*dst,*src, 8 *len);}AudioConvert *swri_audio_convert_alloc(enum AVSampleFormat out_fmt, enum AVSampleFormat in_fmt, int channels, const int *ch_map, int flags){AudioConvert *ctx;conv_func_type *f=fmt_pair_to_conv_functions[av_get_packed_sample_fmt(out_fmt)+AV_SAMPLE_FMT_NB *av_get_packed_sample_fmt(in_fmt)];if(!f) return NULL;ctx=av_mallocz(sizeof(*ctx));if(!ctx) return NULL;if(channels==1){in_fmt=av_get_planar_sample_fmt(in_fmt);out_fmt=av_get_planar_sample_fmt(out_fmt);}ctx->channels=channels;ctx->conv_f=f;ctx->ch_map=ch_map;if(in_fmt==AV_SAMPLE_FMT_U8||in_fmt==AV_SAMPLE_FMT_U8P) memset(ctx->silence, 0x80, sizeof(ctx->silence));if(out_fmt==in_fmt &&!ch_map){switch(av_get_bytes_per_sample(in_fmt)){case 1:ctx->simd_f=cpy1;break;case 2:ctx->simd_f=cpy2;break;case 4:ctx->simd_f=cpy4;break;case 8:ctx->simd_f=cpy8;break;}}if(HAVE_X86ASM &&1) swri_audio_convert_init_x86(ctx, out_fmt, in_fmt, channels);if(ARCH_ARM) swri_audio_convert_init_arm(ctx, out_fmt, in_fmt, channels);if(ARCH_AARCH64) swri_audio_convert_init_aarch64(ctx, out_fmt, in_fmt, channels);return ctx;}void swri_audio_convert_free(AudioConvert **ctx){av_freep(ctx);}int swri_audio_convert(AudioConvert *ctx, AudioData *out, AudioData *in, int len){int ch;int off=0;const int os=(out->planar?1:out->ch_count)*out->bps;unsigned misaligned=0;av_assert0(ctx->channels==out->ch_count);if(ctx->in_simd_align_mask){int planes=in->planar?in->ch_count:1;unsigned m=0;for(ch=0;ch< planes;ch++) m|=(intptr_t) in->ch[ch];misaligned|=m &ctx->in_simd_align_mask;}if(ctx->out_simd_align_mask){int planes=out->planar?out->ch_count:1;unsigned m=0;for(ch=0;ch< planes;ch++) m|=(intptr_t) out->ch[ch];misaligned|=m &ctx->out_simd_align_mask;}if(ctx->simd_f &&!ctx->ch_map &&!misaligned){off=len &~15;av_assert1(off >=0);av_assert1(off<=len);av_assert2(ctx->channels==SWR_CH_MAX||!in->ch[ctx->channels]);if(off >0){if(out->planar==in->planar){int planes=out->planar?out->ch_count:1;for(ch=0;ch< planes;ch++){ctx->simd_f(out-> ch ch
Definition: audioconvert.c:56
IIR filter global parameters.
Definition: iirfilter.c:37
void ff_iir_filter_init(FFIIRFilterContext *f)
Initialize FFIIRFilterContext.
Definition: iirfilter.c:319
struct FFIIRFilterState ** fstate
Definition: psymodel.c:97
av_cold struct FFPsyPreprocessContext * ff_psy_preprocess_init(AVCodecContext *avctx)
psychoacoustic model audio preprocessing initialization
Definition: psymodel.c:103
Use these values when setting the channel map with ebur128_set_channel().
Definition: ebur128.h:39
void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx, float **audio, int channels)
Preprocess several channel in audio frame in order to compress it better.
Definition: psymodel.c:139
#define FILT_ORDER
Definition: psymodel.c:101
struct FFIIRFilterContext fiir
Definition: psymodel.c:98
int cutoff
Audio cutoff bandwidth (0 means "automatic")
Definition: avcodec.h:1230
#define av_free(p)
IIR filter interface.
int channels
number of audio channels
Definition: avcodec.h:1187
FFPsyChannel * ch
single channel information
Definition: psymodel.h:93
#define av_freep(p)
av_cold void ff_iir_filter_free_coeffsp(struct FFIIRFilterCoeffs **coeffsp)
Free filter coefficients.
Definition: iirfilter.c:309
#define av_malloc_array(a, b)
AVCodecContext * avctx
encoder context
Definition: psymodel.h:90
Filter the word “frame” indicates either a video frame or a group of audio as stored in an AVFrame structure Format for each input and each output the list of supported formats For video that means pixel format For audio that means channel sample they are references to shared objects When the negotiation mechanism computes the intersection of the formats supported at each end of a all references to both lists are replaced with a reference to the intersection And when a single format is eventually chosen for a link amongst the remaining all references to the list are updated That means that if a filter requires that its input and output have the same format amongst a supported all it has to do is use a reference to the same list of formats query_formats can leave some formats unset and return AVERROR(EAGAIN) to cause the negotiation mechanism toagain later.That can be used by filters with complex requirements to use the format negotiated on one link to set the formats supported on another.Frame references ownership and permissions
av_cold void ff_psy_end(FFPsyContext *ctx)
Cleanup model context at the end.
Definition: psymodel.c:83
int i
Definition: input.c:407
void * av_mallocz_array(size_t nmemb, size_t size)
Definition: mem.c:190