Fix and simplify the power estimation in the IntelligibilityEnhancer

webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer.cc

Index: webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer.cc
diff --git a/webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer.cc b/webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer.cc
index 877e437fe7a298cb1cb0242af239b1b12691df17..f0050a2ae12f155d41642116d2b6e0e64e18c058 100644
--- a/webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer.cc
+++ b/webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer.cc
@@ -8,13 +8,6 @@
  *  be found in the AUTHORS file in the root of the source tree.
  */
 
-//
-//  Implements core class for intelligibility enhancer.
-//
-//  Details of the model and algorithm can be found in the original paper:
-//  http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6882788
-//
-
 #include "webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer.h"
 
 #include <math.h>
@@ -32,7 +25,7 @@ namespace webrtc {
 namespace {
 
 const size_t kErbResolution = 2;
-const int kWindowSizeMs = 2;
+const int kWindowSizeMs = 16;
 const int kChunkSizeMs = 10;  // Size provided by APM.
 const float kClipFreq = 200.0f;
 const float kConfigRho = 0.02f;  // Default production and interpretation SNR.
@@ -49,35 +42,30 @@ float DotProduct(const float* a, const float* b, size_t length) {
   return ret;
 }
 
-// Computes the power across ERB filters from the power spectral density |var|.
+// Computes the power across ERB bands from the power spectral density |pow|.
 // Stores it in |result|.
-void FilterVariance(const float* var,
-                    const std::vector<std::vector<float>>& filter_bank,
-                    float* result) {
+void MapToErbBands(const float* pow,
+                   const std::vector<std::vector<float>>& filter_bank,
+                   float* result) {
   for (size_t i = 0; i < filter_bank.size(); ++i) {
     RTC_DCHECK_GT(filter_bank[i].size(), 0u);
-    result[i] = DotProduct(&filter_bank[i][0], var, filter_bank[i].size());
+    result[i] = DotProduct(&filter_bank[i][0], pow, filter_bank[i].size());
   }
 }
 
 }  // namespace
 
-using std::complex;
-using std::max;
-using std::min;
-using VarianceType = intelligibility::VarianceArray::StepType;
-
 IntelligibilityEnhancer::TransformCallback::TransformCallback(
     IntelligibilityEnhancer* parent)
     : parent_(parent) {
 }
 
 void IntelligibilityEnhancer::TransformCallback::ProcessAudioBlock(
-    const complex<float>* const* in_block,
+    const std::complex<float>* const* in_block,
     size_t in_channels,
     size_t frames,
     size_t /* out_channels */,
-    complex<float>* const* out_block) {
+    std::complex<float>* const* out_block) {
   RTC_DCHECK_EQ(parent_->freqs_, frames);
   for (size_t i = 0; i < in_channels; ++i) {
     parent_->ProcessClearBlock(in_block[i], out_block[i]);
@@ -101,13 +89,10 @@ IntelligibilityEnhancer::IntelligibilityEnhancer(const Config& config)
       num_render_channels_(config.num_render_channels),
       analysis_rate_(config.analysis_rate),
       active_(true),
-      clear_variance_(freqs_,
-                      config.var_type,
-                      config.var_window_size,
-                      config.var_decay_rate),
+      clear_power_(freqs_, config.decay_rate),
       noise_power_(freqs_, 0.f),
-      filtered_clear_var_(new float[bank_size_]),
-      filtered_noise_var_(new float[bank_size_]),
+      filtered_clear_pow_(new float[bank_size_]),
+      filtered_noise_pow_(new float[bank_size_]),
       center_freqs_(new float[bank_size_]),
       render_filter_bank_(CreateErbBank(freqs_)),
       rho_(new float[bank_size_]),
@@ -120,12 +105,12 @@ IntelligibilityEnhancer::IntelligibilityEnhancer(const Config& config)
       analysis_step_(0) {
   RTC_DCHECK_LE(config.rho, 1.0f);
 
-  memset(filtered_clear_var_.get(),
+  memset(filtered_clear_pow_.get(),
          0,
-         bank_size_ * sizeof(filtered_clear_var_[0]));
-  memset(filtered_noise_var_.get(),
+         bank_size_ * sizeof(filtered_clear_pow_[0]));
+  memset(filtered_noise_pow_.get(),
          0,
-         bank_size_ * sizeof(filtered_noise_var_[0]));
+         bank_size_ * sizeof(filtered_noise_pow_[0]));
 
   // Assumes all rho equal.
   for (size_t i = 0; i < bank_size_; ++i) {
@@ -176,8 +161,9 @@ void IntelligibilityEnhancer::ProcessRenderAudio(float* const* audio,
   }
 }
 
-void IntelligibilityEnhancer::ProcessClearBlock(const complex<float>* in_block,
-                                                complex<float>* out_block) {
+void IntelligibilityEnhancer::ProcessClearBlock(
+    const std::complex<float>* in_block,
+    std::complex<float>* out_block) {
   if (block_count_ < 2) {
     memset(out_block, 0, freqs_ * sizeof(*out_block));
     ++block_count_;
@@ -186,11 +172,9 @@ void IntelligibilityEnhancer::ProcessClearBlock(const complex<float>* in_block,
 
   // TODO(ekm): Use VAD to |Step| and |AnalyzeClearBlock| only if necessary.
   if (true) {
-    clear_variance_.Step(in_block, false);
+    clear_power_.Step(in_block);
     if (block_count_ % analysis_rate_ == analysis_rate_ - 1) {
-      const float power_target = std::accumulate(
-          clear_variance_.variance(), clear_variance_.variance() + freqs_, 0.f);
-      AnalyzeClearBlock(power_target);
+      AnalyzeClearBlock();
       ++analysis_step_;
     }
     ++block_count_;
@@ -201,23 +185,26 @@ void IntelligibilityEnhancer::ProcessClearBlock(const complex<float>* in_block,
   }
 }
 
-void IntelligibilityEnhancer::AnalyzeClearBlock(float power_target) {
-  FilterVariance(clear_variance_.variance(),
-                 render_filter_bank_,
-                 filtered_clear_var_.get());
-  FilterVariance(&noise_power_[0],
-                 capture_filter_bank_,
-                 filtered_noise_var_.get());
+void IntelligibilityEnhancer::AnalyzeClearBlock() {
+  const float* clear_power = clear_power_.Power();
+  MapToErbBands(clear_power,
+                render_filter_bank_,
+                filtered_clear_pow_.get());
+  MapToErbBands(&noise_power_[0],
+                capture_filter_bank_,
+                filtered_noise_pow_.get());
   SolveForGainsGivenLambda(kLambdaTop, start_freq_, gains_eq_.get());
+  const float power_target = std::accumulate(
+          clear_power, clear_power + freqs_, 0.f);
   const float power_top =
-      DotProduct(gains_eq_.get(), filtered_clear_var_.get(), bank_size_);
+      DotProduct(gains_eq_.get(), filtered_clear_pow_.get(), bank_size_);
   SolveForGainsGivenLambda(kLambdaBot, start_freq_, gains_eq_.get());
   const float power_bot =
-      DotProduct(gains_eq_.get(), filtered_clear_var_.get(), bank_size_);
+      DotProduct(gains_eq_.get(), filtered_clear_pow_.get(), bank_size_);
   if (power_target >= power_bot && power_target <= power_top) {
     SolveForLambda(power_target, power_bot, power_top);
     UpdateErbGains();
-  }  // Else experiencing variance underflow, so do nothing.
+  }  // Else experiencing power underflow, so do nothing.
 }
 
 void IntelligibilityEnhancer::SolveForLambda(float power_target,
@@ -237,7 +224,7 @@ void IntelligibilityEnhancer::SolveForLambda(float power_target,
     const float lambda = lambda_bot + (lambda_top - lambda_bot) / 2.0f;
     SolveForGainsGivenLambda(lambda, start_freq_, gains_eq_.get());
     const float power =
-        DotProduct(gains_eq_.get(), filtered_clear_var_.get(), bank_size_);
+        DotProduct(gains_eq_.get(), filtered_clear_pow_.get(), bank_size_);
     if (power < power_target) {
       lambda_bot = lambda;
     } else {
@@ -290,22 +277,22 @@ std::vector<std::vector<float>> IntelligibilityEnhancer::CreateErbBank(
     size_t lll, ll, rr, rrr;
     static const size_t kOne = 1;  // Avoids repeated static_cast<>s below.
     lll = static_cast<size_t>(round(
-        center_freqs_[max(kOne, i - lf) - 1] * num_freqs /
+        center_freqs_[std::max(kOne, i - lf) - 1] * num_freqs /
             (0.5f * sample_rate_hz_)));
     ll = static_cast<size_t>(round(
-        center_freqs_[max(kOne, i) - 1] * num_freqs /
+        center_freqs_[std::max(kOne, i) - 1] * num_freqs /
             (0.5f * sample_rate_hz_)));
-    lll = min(num_freqs, max(lll, kOne)) - 1;
-    ll = min(num_freqs, max(ll, kOne)) - 1;
+    lll = std::min(num_freqs, std::max(lll, kOne)) - 1;
+    ll = std::min(num_freqs, std::max(ll, kOne)) - 1;
 
     rrr = static_cast<size_t>(round(
-        center_freqs_[min(bank_size_, i + rf) - 1] * num_freqs /
+        center_freqs_[std::min(bank_size_, i + rf) - 1] * num_freqs /
             (0.5f * sample_rate_hz_)));
     rr = static_cast<size_t>(round(
-        center_freqs_[min(bank_size_, i + 1) - 1] * num_freqs /
+        center_freqs_[std::min(bank_size_, i + 1) - 1] * num_freqs /
             (0.5f * sample_rate_hz_)));
-    rrr = min(num_freqs, max(rrr, kOne)) - 1;
-    rr = min(num_freqs, max(rr, kOne)) - 1;
+    rrr = std::min(num_freqs, std::max(rrr, kOne)) - 1;
+    rr = std::min(num_freqs, std::max(rr, kOne)) - 1;
 
     float step, element;
 
@@ -343,8 +330,8 @@ void IntelligibilityEnhancer::SolveForGainsGivenLambda(float lambda,
                                                        size_t start_freq,
                                                        float* sols) {
   bool quadratic = (kConfigRho < 1.0f);
-  const float* var_x0 = filtered_clear_var_.get();
-  const float* var_n0 = filtered_noise_var_.get();
+  const float* pow_x0 = filtered_clear_pow_.get();
+  const float* pow_n0 = filtered_noise_pow_.get();
 
   for (size_t n = 0; n < start_freq; ++n) {
     sols[n] = 1.0f;
@@ -353,11 +340,11 @@ void IntelligibilityEnhancer::SolveForGainsGivenLambda(float lambda,
   // Analytic solution for optimal gains. See paper for derivation.
   for (size_t n = start_freq - 1; n < bank_size_; ++n) {
     float alpha0, beta0, gamma0;
-    gamma0 = 0.5f * rho_[n] * var_x0[n] * var_n0[n] +
-             lambda * var_x0[n] * var_n0[n] * var_n0[n];
-    beta0 = lambda * var_x0[n] * (2 - rho_[n]) * var_x0[n] * var_n0[n];
+    gamma0 = 0.5f * rho_[n] * pow_x0[n] * pow_n0[n] +
+             lambda * pow_x0[n] * pow_n0[n] * pow_n0[n];
+    beta0 = lambda * pow_x0[n] * (2 - rho_[n]) * pow_x0[n] * pow_n0[n];
     if (quadratic) {
-      alpha0 = lambda * var_x0[n] * (1 - rho_[n]) * var_x0[n] * var_x0[n];
+      alpha0 = lambda * pow_x0[n] * (1 - rho_[n]) * pow_x0[n] * pow_x0[n];
       sols[n] =
           (-beta0 - sqrtf(beta0 * beta0 - 4 * alpha0 * gamma0)) /
           (2 * alpha0 + std::numeric_limits<float>::epsilon());