summaryrefslogtreecommitdiff
path: root/libavcodec/psymodel.c
diff options
context:
space:
mode:
authorAlex Converse <alex.converse@gmail.com>2009-07-08 20:01:31 +0000
committerAlex Converse <alex.converse@gmail.com>2009-07-08 20:01:31 +0000
commit78e65cd7726942a1615ead039abe0bfa79341212 (patch)
tree7003e32f0234d3fb6d7959e9f193e2ec733df5c6 /libavcodec/psymodel.c
parent5e039e1b4c0fe25c76faa7ea107db60264edb757 (diff)
downloadffmpeg-78e65cd7726942a1615ead039abe0bfa79341212.tar.gz
Merge the AAC encoder from SoC svn. It is still considered experimental.
Originally committed as revision 19375 to svn://svn.ffmpeg.org/ffmpeg/trunk
Diffstat (limited to 'libavcodec/psymodel.c')
-rw-r--r--libavcodec/psymodel.c130
1 files changed, 130 insertions, 0 deletions
diff --git a/libavcodec/psymodel.c b/libavcodec/psymodel.c
new file mode 100644
index 0000000000..623254e531
--- /dev/null
+++ b/libavcodec/psymodel.c
@@ -0,0 +1,130 @@
+/*
+ * 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
+ */
+
+#include "avcodec.h"
+#include "psymodel.h"
+#include "iirfilter.h"
+
+extern const FFPsyModel ff_aac_psy_model;
+
+av_cold int ff_psy_init(FFPsyContext *ctx, AVCodecContext *avctx,
+ int num_lens,
+ const uint8_t **bands, const int* num_bands)
+{
+ ctx->avctx = avctx;
+ ctx->psy_bands = av_mallocz(sizeof(FFPsyBand) * PSY_MAX_BANDS * avctx->channels);
+ ctx->bands = av_malloc (sizeof(ctx->bands[0]) * num_lens);
+ ctx->num_bands = av_malloc (sizeof(ctx->num_bands[0]) * num_lens);
+ memcpy(ctx->bands, bands, sizeof(ctx->bands[0]) * num_lens);
+ memcpy(ctx->num_bands, num_bands, sizeof(ctx->num_bands[0]) * num_lens);
+ switch(ctx->avctx->codec_id){
+ case CODEC_ID_AAC:
+ ctx->model = &ff_aac_psy_model;
+ break;
+ }
+ if(ctx->model->init)
+ return ctx->model->init(ctx);
+ return 0;
+}
+
+FFPsyWindowInfo ff_psy_suggest_window(FFPsyContext *ctx,
+ const int16_t *audio, const int16_t *la,
+ int channel, int prev_type)
+{
+ return ctx->model->window(ctx, audio, la, channel, prev_type);
+}
+
+void ff_psy_set_band_info(FFPsyContext *ctx, int channel,
+ const float *coeffs, FFPsyWindowInfo *wi)
+{
+ ctx->model->analyze(ctx, channel, coeffs, wi);
+}
+
+av_cold void ff_psy_end(FFPsyContext *ctx)
+{
+ if(ctx->model->end)
+ ctx->model->end(ctx);
+ av_freep(&ctx->bands);
+ av_freep(&ctx->num_bands);
+ av_freep(&ctx->psy_bands);
+}
+
+typedef struct FFPsyPreprocessContext{
+ AVCodecContext *avctx;
+ float stereo_att;
+ struct FFIIRFilterCoeffs *fcoeffs;
+ struct FFIIRFilterState **fstate;
+}FFPsyPreprocessContext;
+
+#define FILT_ORDER 4
+
+av_cold struct FFPsyPreprocessContext* ff_psy_preprocess_init(AVCodecContext *avctx)
+{
+ FFPsyPreprocessContext *ctx;
+ int i;
+ float cutoff_coeff;
+ ctx = av_mallocz(sizeof(FFPsyPreprocessContext));
+ ctx->avctx = avctx;
+
+ if(avctx->flags & CODEC_FLAG_QSCALE)
+ cutoff_coeff = 1.0f / av_clip(1 + avctx->global_quality / FF_QUALITY_SCALE, 1, 8);
+ else
+ cutoff_coeff = avctx->bit_rate / (4.0f * avctx->sample_rate * avctx->channels);
+
+ ctx->fcoeffs = ff_iir_filter_init_coeffs(FF_FILTER_TYPE_BUTTERWORTH, FF_FILTER_MODE_LOWPASS,
+ FILT_ORDER, cutoff_coeff, 0.0, 0.0);
+ if(ctx->fcoeffs){
+ ctx->fstate = av_mallocz(sizeof(ctx->fstate[0]) * avctx->channels);
+ for(i = 0; i < avctx->channels; i++)
+ ctx->fstate[i] = ff_iir_filter_init_state(FILT_ORDER);
+ }
+ return ctx;
+}
+
+void ff_psy_preprocess(struct FFPsyPreprocessContext *ctx,
+ const int16_t *audio, int16_t *dest,
+ int tag, int channels)
+{
+ int ch, i;
+ if(ctx->fstate){
+ for(ch = 0; ch < channels; ch++){
+ ff_iir_filter(ctx->fcoeffs, ctx->fstate[tag+ch], ctx->avctx->frame_size,
+ audio + ch, ctx->avctx->channels,
+ dest + ch, ctx->avctx->channels);
+ }
+ }else{
+ for(ch = 0; ch < channels; ch++){
+ for(i = 0; i < ctx->avctx->frame_size; i++)
+ dest[i*ctx->avctx->channels + ch] = audio[i*ctx->avctx->channels + ch];
+ }
+ }
+}
+
+av_cold void ff_psy_preprocess_end(struct FFPsyPreprocessContext *ctx)
+{
+ int i;
+ ff_iir_filter_free_coeffs(ctx->fcoeffs);
+ if (ctx->fstate)
+ for (i = 0; i < ctx->avctx->channels; i++)
+ ff_iir_filter_free_state(ctx->fstate[i]);
+ av_freep(&ctx->fstate);
+}
+