aaccoder: add a new perceptual noise substitution implementation

This commit finalizes the PNS implementation previously added to the encoder
by moving it to a seperate function search_for_pns() and thus making it
coder-generic. This new implementation makes use of the spread field of
the psy bands and the lambda quality feedback paremeter. The spread of the
spectrum in a band prevents PNS from being used excessively and thus preserve
more phase information in high frequencies.  The lambda parameter allows
the number of PNS-marked bands to vary based on the lambda parameter and the
amount of bits available, making better choices on which bands are to be marked
as noise. Comparisons with the previous PNS implementation can be found
here: https://trac.ffmpeg.org/attachment/wiki/Encode/AAC/

This is V2 of the patch, the changes from the previous version being that this
version uses the new band->spread metric from aacpsy and normalizes the
energy using the group size. These changes were suggested by Claudio Freire
on the mailing list. Another change is the use of lambda to alter the
frequency threshold. This change makes the actual threshold frequencies
vary between +-2Khz of what's specified, depending on frame encoding performance.

Reviewed-by: Claudio Freire <klaussfreire@gmail.com>
Signed-off-by: Michael Niedermayer <michaelni@gmx.at>

3 files changed, 58 insertions, 1 deletions

diff --git a/libavcodec/aaccoder.c b/libavcodec/aaccoder.c
index 8695a885c1..95782fc49e 100644
--- a/libavcodec/aaccoder.c
+++ b/libavcodec/aaccoder.c
@@ -41,7 +41,16 @@
 #include "aactab.h"
 
 /** Frequency in Hz for lower limit of noise substitution **/
-#define NOISE_LOW_LIMIT 4000
+#define NOISE_LOW_LIMIT 4500
+
+/* Energy spread threshold value below which no PNS is used, this corresponds to
+ * typically around 17Khz, after which PNS usage decays ending at 19Khz */
+#define NOISE_SPREAD_THRESHOLD 0.5f
+
+/* This constant gets divided by lambda to return ~1.65 which when multiplied
+ * by the band->threshold and compared to band->energy is the boundary between
+ * excessive PNS and little PNS usage. */
+#define NOISE_LAMBDA_NUMERATOR 252.1f
 
 /** Total number of usable codebooks **/
 #define CB_TOT 12
@@ -1132,6 +1141,43 @@ static void search_for_quantizers_fast(AVCodecContext *avctx, AACEncContext *s,
                 sce->sf_idx[(w+w2)*16+g] = sce->sf_idx[w*16+g];
 }
 
+static void search_for_pns(AACEncContext *s, AVCodecContext *avctx, SingleChannelElement *sce,
+                           const float lambda)
+{
+    int start = 0, w, w2, g;
+    const float freq_mult = avctx->sample_rate/(1024.0f/sce->ics.num_windows)/2.0f;
+    const float spread_threshold = NOISE_SPREAD_THRESHOLD*(lambda/120.f);
+    const float thr_mult = NOISE_LAMBDA_NUMERATOR/lambda;
+
+    /* Coders !twoloop don't reset the band_types */
+    for (w = 0; w < 128; w++)
+        if (sce->band_type[w] == NOISE_BT)
+            sce->band_type[w] = 0;
+
+    for (w = 0; w < sce->ics.num_windows; w += sce->ics.group_len[w]) {
+        start = 0;
+        for (g = 0;  g < sce->ics.num_swb; g++) {
+            if (start*freq_mult > NOISE_LOW_LIMIT*(lambda/170.0f)) {
+                float energy = 0.0f, threshold = 0.0f, spread = 0.0f;
+                for (w2 = 0; w2 < sce->ics.group_len[w]; w2++) {
+                    FFPsyBand *band = &s->psy.ch[s->cur_channel+0].psy_bands[(w+w2)*16+g];
+                    energy += band->energy;
+                    threshold += band->threshold;
+                    spread += band->spread;
+                }
+                if (spread > spread_threshold*sce->ics.group_len[w] &&
+                    ((sce->zeroes[w*16+g] && energy >= threshold) ||
+                    energy < threshold*thr_mult*sce->ics.group_len[w])) {
+                    sce->band_type[w*16+g] = NOISE_BT;
+                    sce->pns_ener[w*16+g] = energy / sce->ics.group_len[w];
+                    sce->zeroes[w*16+g] = 0;
+                }
+            }
+            start += sce->ics.swb_sizes[g];
+        }
+    }
+}
+
 static void search_for_ms(AACEncContext *s, ChannelElement *cpe,
                           const float lambda)
 {
@@ -1200,6 +1246,7 @@ AACCoefficientsEncoder ff_aac_coders[AAC_CODER_NB] = {
         encode_window_bands_info,
         quantize_and_encode_band,
         set_special_band_scalefactors,
+        search_for_pns,
         search_for_ms,
     },
     [AAC_CODER_ANMR] = {
@@ -1207,6 +1254,7 @@ AACCoefficientsEncoder ff_aac_coders[AAC_CODER_NB] = {
         encode_window_bands_info,
         quantize_and_encode_band,
         set_special_band_scalefactors,
+        search_for_pns,
         search_for_ms,
     },
     [AAC_CODER_TWOLOOP] = {
@@ -1214,6 +1262,7 @@ AACCoefficientsEncoder ff_aac_coders[AAC_CODER_NB] = {
         codebook_trellis_rate,
         quantize_and_encode_band,
         set_special_band_scalefactors,
+        search_for_pns,
         search_for_ms,
     },
     [AAC_CODER_FAST] = {
@@ -1221,6 +1270,7 @@ AACCoefficientsEncoder ff_aac_coders[AAC_CODER_NB] = {
         encode_window_bands_info,
         quantize_and_encode_band,
         set_special_band_scalefactors,
+        search_for_pns,
         search_for_ms,
     },
 };
diff --git a/libavcodec/aacenc.c b/libavcodec/aacenc.c
index 3854066fc1..f7325d49c1 100644
--- a/libavcodec/aacenc.c
+++ b/libavcodec/aacenc.c
@@ -641,6 +641,12 @@ static int aac_encode_frame(AVCodecContext *avctx, AVPacket *avpkt,
                     }
                 }
             }
+            if (s->options.pns && s->coder->search_for_pns) {
+                for (ch = 0; ch < chans; ch++) {
+                    s->cur_channel = start_ch + ch;
+                    s->coder->search_for_pns(s, avctx, &cpe->ch[ch], s->lambda);
+                }
+            }
             s->cur_channel = start_ch;
             if (s->options.stereo_mode && cpe->common_window) {
                 if (s->options.stereo_mode > 0) {
diff --git a/libavcodec/aacenc.h b/libavcodec/aacenc.h
index cc1b06afac..8ba58174a4 100644
--- a/libavcodec/aacenc.h
+++ b/libavcodec/aacenc.h
@@ -55,6 +55,7 @@ typedef struct AACCoefficientsEncoder {
     void (*quantize_and_encode_band)(struct AACEncContext *s, PutBitContext *pb, const float *in, int size,
                                      int scale_idx, int cb, const float lambda);
     void (*set_special_band_scalefactors)(struct AACEncContext *s, SingleChannelElement *sce);
+    void (*search_for_pns)(struct AACEncContext *s, AVCodecContext *avctx, SingleChannelElement *sce, const float lambda);
     void (*search_for_ms)(struct AACEncContext *s, ChannelElement *cpe, const float lambda);
 } AACCoefficientsEncoder;