Add new variance update option and unittests for intelligibility

webrtc/modules/audio_processing/intelligibility/intelligibility_utils.cc

 /*
  *  Copyright (c) 2014 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.
  */
 
 //
 //  Implements helper functions and classes for intelligibility enhancement.
 //
 
 #include "webrtc/modules/audio_processing/intelligibility/intelligibility_utils.h"
 
+#include <math.h>
+#include <string.h>
 #include <algorithm>
-#include <cmath>
-#include <cstring>
 
 using std::complex;
+using std::min;
 
-namespace {
+namespace webrtc {
 
-// Return |current| changed towards |target|, with the change being at most
-// |limit|.
-inline float UpdateFactor(float target, float current, float limit) {
+namespace intelligibility {
+
+float UpdateFactor(float target, float current, float limit) {
   float delta = fabsf(target - current);
   float sign = copysign(1.0f, target - current);
   return current + sign * fminf(delta, limit);
 }
 
-// std::isfinite for complex numbers.
-inline bool cplxfinite(complex<float> c) {
+bool cplxfinite(complex<float> c) {
   return std::isfinite(c.real()) && std::isfinite(c.imag());
 }
 
-// std::isnormal for complex numbers.
-inline bool cplxnormal(complex<float> c) {
+bool cplxnormal(complex<float> c) {
   return std::isnormal(c.real()) && std::isnormal(c.imag());
 }
 
-// Apply a small fudge to degenerate complex values. The numbers in the array
-// were chosen randomly, so that even a series of all zeroes has some small
-// variability.
-inline complex<float> zerofudge(complex<float> c) {
+complex<float> zerofudge(complex<float> c) {
   const static complex<float> fudge[7] = {{0.001f, 0.002f},
                                           {0.008f, 0.001f},
                                           {0.003f, 0.008f},
                                           {0.0006f, 0.0009f},
                                           {0.001f, 0.004f},
                                           {0.003f, 0.004f},
                                           {0.002f, 0.009f}};
   static int fudge_index = 0;
   if (cplxfinite(c) && !cplxnormal(c)) {
     fudge_index = (fudge_index + 1) % 7;
     return c + fudge[fudge_index];
   }
   return c;
 }
 
-// Incremental mean computation. Return the mean of the series with the
-// mean |mean| with added |data|.
-inline complex<float> NewMean(complex<float> mean,
-                              complex<float> data,
-                              int count) {
+complex<float> NewMean(complex<float> mean, complex<float> data, int count) {
   return mean + (data - mean) / static_cast<float>(count);
 }
 
-inline void AddToMean(complex<float> data, int count, complex<float>* mean) {
+void AddToMean(complex<float> data, int count, complex<float>* mean) {
   (*mean) = NewMean(*mean, data, count);
 }
 
-}  // namespace
-
-using std::min;
-
-namespace webrtc {
-
-namespace intelligibility {
 
 static const int kWindowBlockSize = 10;
 
 VarianceArray::VarianceArray(int freqs,
                              StepType type,
                              int window_size,
                              float decay)
     : running_mean_(new complex<float>[freqs]()),
       running_mean_sq_(new complex<float>[freqs]()),
       sub_running_mean_(new complex<float>[freqs]()),
       sub_running_mean_sq_(new complex<float>[freqs]()),
       variance_(new float[freqs]()),
       conj_sum_(new float[freqs]()),
       freqs_(freqs),
       window_size_(window_size),
       decay_(decay),
       history_cursor_(0),
       count_(0),
-      array_mean_(0.0f) {
+      array_mean_(0.0f),
+      buffer_full_(false) {
   history_.reset(new rtc::scoped_ptr<complex<float>[]>[freqs_]());
   for (int i = 0; i < freqs_; ++i) {
     history_[i].reset(new complex<float>[window_size_]());
   }
   subhistory_.reset(new rtc::scoped_ptr<complex<float>[]>[freqs_]());
   for (int i = 0; i < freqs_; ++i) {
     subhistory_[i].reset(new complex<float>[window_size_]());
   }
   subhistory_sq_.reset(new rtc::scoped_ptr<complex<float>[]>[freqs_]());
   for (int i = 0; i < freqs_; ++i) {
     subhistory_sq_[i].reset(new complex<float>[window_size_]());
   }
   switch (type) {
     case kStepInfinite:
       step_func_ = &VarianceArray::InfiniteStep;
       break;
     case kStepDecaying:
       step_func_ = &VarianceArray::DecayStep;
       break;
     case kStepWindowed:
       step_func_ = &VarianceArray::WindowedStep;
       break;
     case kStepBlocked:
       step_func_ = &VarianceArray::BlockedStep;
       break;
+    case kStepBlockBasedMovingAverage:
+      step_func_ = &VarianceArray::BlockBasedMovingAverage;
+      break;
   }
 }
 
 // Compute the variance with Welford's algorithm, adding some fudge to
 // the input in case of all-zeroes.
 void VarianceArray::InfiniteStep(const complex<float>* data, bool skip_fudge) {
   array_mean_ = 0.0f;
   ++count_;
   for (int i = 0; i < freqs_; ++i) {
     complex<float> sample = data[i];
@@ skipping 81 matching lines @@
   history_cursor_ = (history_cursor_ + 1) % window_size_;
   ++count_;
 }
 
 // Variance with a window of blocks. Within each block, the variances are
 // recomputed from scratch at every stp, using |Var(X) = E(X^2) - E^2(X)|.
 // Once a block is filled with kWindowBlockSize samples, it is added to the
 // history window and a new block is started. The variances for the window
 // are recomputed from scratch at each of these transitions.
 void VarianceArray::BlockedStep(const complex<float>* data, bool /*dummy*/) {
-  int blocks = min(window_size_, history_cursor_);
+  int blocks = min(window_size_, history_cursor_ + 1);
   for (int i = 0; i < freqs_; ++i) {
     AddToMean(data[i], count_ + 1, &sub_running_mean_[i]);
     AddToMean(data[i] * std::conj(data[i]), count_ + 1,
               &sub_running_mean_sq_[i]);
     subhistory_[i][history_cursor_ % window_size_] = sub_running_mean_[i];
     subhistory_sq_[i][history_cursor_ % window_size_] = sub_running_mean_sq_[i];
 
     variance_[i] =
         (NewMean(running_mean_sq_[i], sub_running_mean_sq_[i], blocks) -
          NewMean(running_mean_[i], sub_running_mean_[i], blocks) *
              std::conj(NewMean(running_mean_[i], sub_running_mean_[i], blocks)))
             .real();
     if (count_ == kWindowBlockSize - 1) {
       sub_running_mean_[i] = complex<float>(0.0f, 0.0f);
       sub_running_mean_sq_[i] = complex<float>(0.0f, 0.0f);
       running_mean_[i] = complex<float>(0.0f, 0.0f);
       running_mean_sq_[i] = complex<float>(0.0f, 0.0f);
       for (int j = 0; j < min(window_size_, history_cursor_); ++j) {
-        AddToMean(subhistory_[i][j], j, &running_mean_[i]);
-        AddToMean(subhistory_sq_[i][j], j, &running_mean_sq_[i]);
+        AddToMean(subhistory_[i][j], j + 1, &running_mean_[i]);
+        AddToMean(subhistory_sq_[i][j], j + 1, &running_mean_sq_[i]);
       }
       ++history_cursor_;
     }
   }
   ++count_;
   if (count_ == kWindowBlockSize) {
     count_ = 0;
   }
 }
 
+// Recomputes variances for each window from scratch based on previous window.
+void VarianceArray::BlockBasedMovingAverage(const std::complex<float>* data,
+                                            bool /*dummy*/) {
+  // TODO(ekmeyerson) To mitigate potential divergence, add counter so that
+  // after every so often sums are computed scratch by summing over all
+  // elements instead of subtracting oldest and adding newest.
+  for (int i = 0; i < freqs_; ++i) {
+    sub_running_mean_[i] += data[i];
+    sub_running_mean_sq_[i] += data[i] * std::conj(data[i]);
+  }
+  ++count_;
+
+  // TODO(ekmeyerson) Make kWindowBlockSize nonconstant to allow
+  // experimentation with different block size,window size pairs.
+  if (count_ >= kWindowBlockSize) {
+    count_ = 0;
+
+    for (int i = 0; i < freqs_; ++i) {
+      running_mean_[i] -= subhistory_[i][history_cursor_];
+      running_mean_sq_[i] -= subhistory_sq_[i][history_cursor_];
+
+      float scale = 1.f / kWindowBlockSize;
+      subhistory_[i][history_cursor_] = sub_running_mean_[i] * scale;
+      subhistory_sq_[i][history_cursor_] = sub_running_mean_sq_[i] * scale;
+
+      sub_running_mean_[i] = std::complex<float>(0.0f, 0.0f);
+      sub_running_mean_sq_[i] = std::complex<float>(0.0f, 0.0f);
+
+      running_mean_[i] += subhistory_[i][history_cursor_];
+      running_mean_sq_[i] += subhistory_sq_[i][history_cursor_];
+
+      scale = 1.f / (buffer_full_ ? window_size_ : history_cursor_ + 1);
+      variance_[i] = std::real(running_mean_sq_[i] * scale -
+                               running_mean_[i] * scale *
+                                   std::conj(running_mean_[i]) * scale);
+    }
+
+    ++history_cursor_;
+    if (history_cursor_ >= window_size_) {
+      buffer_full_ = true;
+      history_cursor_ = 0;
+    }
+  }
+}
+
 void VarianceArray::Clear() {
   memset(running_mean_.get(), 0, sizeof(*running_mean_.get()) * freqs_);
   memset(running_mean_sq_.get(), 0, sizeof(*running_mean_sq_.get()) * freqs_);
   memset(variance_.get(), 0, sizeof(*variance_.get()) * freqs_);
   memset(conj_sum_.get(), 0, sizeof(*conj_sum_.get()) * freqs_);
   history_cursor_ = 0;
   count_ = 0;
   array_mean_ = 0.0f;
 }
 
@@ skipping 24 matching lines @@
       factor = 1.0f;
     }
     out_block[i] = factor * in_block[i];
     current_[i] = UpdateFactor(target_[i], current_[i], change_limit_);
   }
 }
 
 }  // namespace intelligibility
 
 }  // namespace webrtc