Adding BlockMeanCalculator for AEC.

webrtc/modules/audio_processing/aec/aec_core.cc

 /*
  *  Copyright (c) 2012 The WebRTC project authors. All Rights Reserved.
  *
  *  Use of this source code is governed by a BSD-style license
  *  that can be found in the LICENSE file in the root of the source
  *  tree. An additional intellectual property rights grant can be found
  *  in the file PATENTS.  All contributing project authors may
  *  be found in the AUTHORS file in the root of the source tree.
  */
 
@@ skipping 28 matching lines @@
 }
 #include "webrtc/system_wrappers/include/cpu_features_wrapper.h"
 #include "webrtc/typedefs.h"
 
 namespace webrtc {
 
 // Buffer size (samples)
 static const size_t kBufSizePartitions = 250;  // 1 second of audio in 16 kHz.
 
 // Metrics
-static const int subCountLen = 4;
-static const int countLen = 50;
+static const size_t kSubCountLen = 4;
+static const size_t kCountLen = 50;
 static const int kDelayMetricsAggregationWindow = 1250;  // 5 seconds at 16 kHz.
 
 // Quantities to control H band scaling for SWB input
 static const float cnScaleHband = 0.4f;  // scale for comfort noise in H band.
 // Initial bin for averaging nlp gain in low band
 static const int freqAvgIc = PART_LEN / 2;
 
 // Matlab code to produce table:
 // win = sqrt(hanning(63)); win = [0 ; win(1:32)];
 // fprintf(1, '\t%.14f, %.14f, %.14f,\n', win);
@@ skipping 82 matching lines @@
 WebRtcAecWindowData WebRtcAec_WindowData;
 
 __inline static float MulRe(float aRe, float aIm, float bRe, float bIm) {
   return aRe * bRe - aIm * bIm;
 }
 
 __inline static float MulIm(float aRe, float aIm, float bRe, float bIm) {
   return aRe * bIm + aIm * bRe;
 }
 
+PowerLevel::PowerLevel()
+// TODO(minyue): Due to a legacy bug, |framelevel| and |averagelevel| use a
+// window, of which the length is 1 unit longer than indicated. Remove "+1"
+// when the code is refactored.
+: framelevel(kSubCountLen + 1),
+  averagelevel(kCountLen + 1) {
+}
+
+// TODO(minyue): Moving some initialization from WebRtcAec_CreateAec() to ctor.
+AecCore::AecCore() = default;
+
 static int CmpFloat(const void* a, const void* b) {
   const float* da = (const float*)a;
   const float* db = (const float*)b;
 
   return (*da > *db) - (*da < *db);
 }
 
 static void FilterFar(int num_partitions,
                       int x_fft_buf_block_pos,
                       float x_fft_buf[2][kExtendedNumPartitions * PART_LEN1],
@@ skipping 353 matching lines @@
       comfortNoiseHband[1][i] = tmpAvg * u[1][i];
     }
   } else {
     memset(comfortNoiseHband, 0,
            2 * PART_LEN1 * sizeof(comfortNoiseHband[0][0]));
   }
 }
 
 static void InitLevel(PowerLevel* level) {
   const float kBigFloat = 1E17f;
-
-  level->averagelevel = 0;
-  level->framelevel = 0;
+  level->averagelevel.Reset();
+  level->framelevel.Reset();
   level->minlevel = kBigFloat;
-  level->frsum = 0;
-  level->sfrsum = 0;
-  level->frcounter = 0;
-  level->sfrcounter = 0;
 }
 
 static void InitStats(Stats* stats) {
   stats->instant = kOffsetLevel;
   stats->average = kOffsetLevel;
   stats->max = kOffsetLevel;
   stats->min = kOffsetLevel * (-1);
   stats->sum = 0;
   stats->hisum = 0;
   stats->himean = kOffsetLevel;
@@ skipping 17 matching lines @@
 static float CalculatePower(const float* in, size_t num_samples) {
   size_t k;
   float energy = 0.0f;
 
   for (k = 0; k < num_samples; ++k) {
     energy += in[k] * in[k];
   }
   return energy / num_samples;
 }
 
-static void UpdateLevel(PowerLevel* level, float energy) {
-  level->sfrsum += energy;
-  level->sfrcounter++;
-
-  if (level->sfrcounter > subCountLen) {
-    level->framelevel = level->sfrsum / (subCountLen * PART_LEN);
-    level->sfrsum = 0;
-    level->sfrcounter = 0;
-    if (level->framelevel > 0) {
-      if (level->framelevel < level->minlevel) {
-        level->minlevel = level->framelevel;  // New minimum.
+static void UpdateLevel(PowerLevel* level, float power) {
+  level->framelevel.AddSample(power);
+  if (level->framelevel.SamplesSinceLastUpdate() == 0) {
+    const float new_frame_level = level->framelevel.GetLatestMean();
+    if (new_frame_level > 0) {
+      if (new_frame_level < level->minlevel) {
+        level->minlevel = new_frame_level;  // New minimum.
       } else {
         level->minlevel *= (1 + 0.001f);  // Small increase.
       }
     }
-    level->frcounter++;
-    level->frsum += level->framelevel;
-    if (level->frcounter > countLen) {
-      level->averagelevel = level->frsum / countLen;
-      level->frsum = 0;
-      level->frcounter = 0;
-    }
+    level->averagelevel.AddSample(new_frame_level);
   }
 }
 
 static void UpdateMetrics(AecCore* aec) {
   float dtmp, dtmp2;
 
   const float actThresholdNoisy = 8.0f;
   const float actThresholdClean = 40.0f;
   const float safety = 0.99995f;
 
-  // To make noisePower consistent with the legacy code, a factor of
-  // 2.0f / PART_LEN2 is applied to noisyPower, since the legacy code uses
-  // the energy of a frame as the audio levels, while the new code uses a
-  // a per-sample energy (i.e., power).
-  const float noisyPower = 300000.0f * 2.0f / PART_LEN2;
+  const float noisyPower = 300000.0f;
 
   float actThreshold;
   float echo, suppressedEcho;
 
   if (aec->echoState) {  // Check if echo is likely present
     aec->stateCounter++;
   }
 
-  if (aec->farlevel.frcounter == 0) {
+  if (aec->farlevel.averagelevel.SamplesSinceLastUpdate() == 0) {
+    const float far_average_level = aec->farlevel.averagelevel.GetLatestMean();
+
     if (aec->farlevel.minlevel < noisyPower) {
       actThreshold = actThresholdClean;
     } else {
       actThreshold = actThresholdNoisy;
     }
 
-    if ((aec->stateCounter > (0.5f * countLen * subCountLen)) &&
-        (aec->farlevel.sfrcounter == 0)
+    if ((aec->stateCounter > (0.5f * kCountLen * kSubCountLen)) &&
+        (aec->farlevel.framelevel.SamplesSinceLastUpdate() == 0)
+        // Estimate in active far-end segments only
+        && (far_average_level > (actThreshold * aec->farlevel.minlevel))) {
 
-        // Estimate in active far-end segments only
-        && (aec->farlevel.averagelevel >
-            (actThreshold * aec->farlevel.minlevel))) {
+      const float near_average_level =
+          aec->nearlevel.averagelevel.GetLatestMean();
+      const float linout_average_level =

[peah-webrtc, 2016/03/24 07:18:41]

Please move this closer to where it is used.

[minyue-webrtc, 2016/03/24 09:13:57]

Done.

+          aec->linoutlevel.averagelevel.GetLatestMean();
+      const float nlpout_average_level =

[peah-webrtc, 2016/03/24 07:18:41]

Please move this closer to where it is used.

[minyue-webrtc, 2016/03/24 09:13:57]

Done.

+          aec->nlpoutlevel.averagelevel.GetLatestMean();
+
       // Subtract noise power
-      echo = aec->nearlevel.averagelevel - safety * aec->nearlevel.minlevel;
+      echo = near_average_level - safety * aec->nearlevel.minlevel;
 
       // ERL
-      dtmp = 10 * static_cast<float>(log10(aec->farlevel.averagelevel /
-                                           aec->nearlevel.averagelevel +
-                                           1e-10f));
-      dtmp2 = 10 * static_cast<float>(log10(aec->farlevel.averagelevel /
-                                            echo +
-                                            1e-10f));
+      dtmp = 10 * static_cast<float>(log10(far_average_level /
+                                           near_average_level + 1e-10f));
+      dtmp2 = 10 * static_cast<float>(log10(far_average_level / echo + 1e-10f));
 
       aec->erl.instant = dtmp;
       if (dtmp > aec->erl.max) {
         aec->erl.max = dtmp;
       }
 
       if (dtmp < aec->erl.min) {
         aec->erl.min = dtmp;
       }
 
       aec->erl.counter++;
       aec->erl.sum += dtmp;
       aec->erl.average = aec->erl.sum / aec->erl.counter;
 
       // Upper mean
       if (dtmp > aec->erl.average) {
         aec->erl.hicounter++;
         aec->erl.hisum += dtmp;
         aec->erl.himean = aec->erl.hisum / aec->erl.hicounter;
       }
 
       // A_NLP
-      dtmp = 10 * static_cast<float>(log10(aec->nearlevel.averagelevel /
-                                           aec->linoutlevel.averagelevel +
-                                           1e-10f));
+      dtmp = 10 * static_cast<float>(log10(near_average_level /
+                                           linout_average_level + 1e-10f));
 
       // subtract noise power
-      suppressedEcho = aec->linoutlevel.averagelevel -
-          safety * aec->linoutlevel.minlevel;
+      suppressedEcho =
+          linout_average_level - safety * aec->linoutlevel.minlevel;
 
       dtmp2 = 10 * static_cast<float>(log10(echo / suppressedEcho + 1e-10f));
 
       aec->aNlp.instant = dtmp2;
       if (dtmp > aec->aNlp.max) {
         aec->aNlp.max = dtmp;
       }
 
       if (dtmp < aec->aNlp.min) {
         aec->aNlp.min = dtmp;
       }
 
       aec->aNlp.counter++;
       aec->aNlp.sum += dtmp;
       aec->aNlp.average = aec->aNlp.sum / aec->aNlp.counter;
 
       // Upper mean
       if (dtmp > aec->aNlp.average) {
         aec->aNlp.hicounter++;
         aec->aNlp.hisum += dtmp;
         aec->aNlp.himean = aec->aNlp.hisum / aec->aNlp.hicounter;
       }
 
       // ERLE
 
       // subtract noise power
-      suppressedEcho = aec->nlpoutlevel.averagelevel -
-          safety * aec->nlpoutlevel.minlevel;
+      suppressedEcho =
+          nlpout_average_level - safety * aec->nlpoutlevel.minlevel;
 
-      dtmp = 10 * static_cast<float>(log10(aec->nearlevel.averagelevel /
-          aec->nlpoutlevel.averagelevel + 1e-10f));
+      dtmp = 10 * static_cast<float>(log10(near_average_level /
+                                           nlpout_average_level + 1e-10f));
       dtmp2 = 10 * static_cast<float>(log10(echo / suppressedEcho + 1e-10f));
 
       dtmp = dtmp2;
       aec->erle.instant = dtmp;
       if (dtmp > aec->erle.max) {
         aec->erle.max = dtmp;
       }
 
       if (dtmp < aec->erle.min) {
         aec->erle.min = dtmp;
@@ skipping 649 matching lines @@
   // For high bands
   for (i = 0; i < aec->num_bands - 1; ++i) {
     WebRtc_WriteBuffer(aec->outFrBufH[i], outputH[i], PART_LEN);
   }
 
   RTC_AEC_DEBUG_WAV_WRITE(aec->outFile, output, PART_LEN);
 }
 
 AecCore* WebRtcAec_CreateAec() {
   int i;
-  AecCore* aec = reinterpret_cast<AecCore*>(malloc(sizeof(AecCore)));
+  AecCore* aec = new AecCore;
   if (!aec) {
     return NULL;
   }
 
   aec->nearFrBuf = WebRtc_CreateBuffer(FRAME_LEN + PART_LEN, sizeof(float));
   if (!aec->nearFrBuf) {
     WebRtcAec_FreeAec(aec);
     return NULL;
   }
 
@@ skipping 517 matching lines @@
 
 int WebRtcAec_system_delay(AecCore* self) {
   return self->system_delay;
 }
 
 void WebRtcAec_SetSystemDelay(AecCore* self, int delay) {
   assert(delay >= 0);
   self->system_delay = delay;
 }
 }  // namespace webrtc