Compensate for the IntelligibilityEnhancer processing delay in high bands

webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer_unittest.cc

Index: webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer_unittest.cc
diff --git a/webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer_unittest.cc b/webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer_unittest.cc
index 45f338c642540acaabf8fb96652b55c28f51cce0..cc9aa128b28f1a17f9d39ee4d7465b289c251aad 100644
--- a/webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer_unittest.cc
+++ b/webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer_unittest.cc
@@ -202,7 +202,7 @@ static_assert(arraysize(kTestCenterFreqs) ==
 const float kMaxTestError = 0.005f;
 
 // Enhancer initialization parameters.
-const int kSamples = 1000;
+const int kSamples = 10000;
 const int kSampleRate = 4000;
 const int kNumChannels = 1;
 const int kFragmentSize = kSampleRate / 100;
@@ -229,9 +229,7 @@ void ProcessOneFrame(int sample_rate_hz,
   }
 
   intelligibility_enhancer->ProcessRenderAudio(
-      render_audio_buffer->split_channels_f(kBand0To8kHz),
-      IntelligibilityEnhancerSampleRate(sample_rate_hz),
-      render_audio_buffer->num_channels());
+      render_audio_buffer, IntelligibilityEnhancerSampleRate(sample_rate_hz));
 
   noise_suppressor->AnalyzeCaptureAudio(capture_audio_buffer);
   noise_suppressor->ProcessCaptureAudio(capture_audio_buffer);
@@ -320,7 +318,15 @@ float float_rand() {
 class IntelligibilityEnhancerTest : public ::testing::Test {
  protected:
   IntelligibilityEnhancerTest()
-      : clear_data_(kSamples), noise_data_(kSamples), orig_data_(kSamples) {
+      : clear_buffer_(kFragmentSize,
+                      kNumChannels,
+                      kFragmentSize,
+                      kNumChannels,
+                      kFragmentSize),
+        stream_config_(kSampleRate, kNumChannels),
+        clear_data_(kSamples),
+        noise_data_(kNumNoiseBins),
+        orig_data_(kSamples) {
     std::srand(1);
     enh_.reset(
         new IntelligibilityEnhancer(kSampleRate, kNumChannels, kNumNoiseBins));
@@ -330,11 +336,12 @@ class IntelligibilityEnhancerTest : public ::testing::Test {
     enh_.reset(
         new IntelligibilityEnhancer(kSampleRate, kNumChannels, kNumNoiseBins));
     float* clear_cursor = clear_data_.data();
-    float* noise_cursor = noise_data_.data();
     for (int i = 0; i < kSamples; i += kFragmentSize) {
-      enh_->ProcessRenderAudio(&clear_cursor, kSampleRate, kNumChannels);
+      enh_->SetCaptureNoiseEstimate(noise_data_, 1);
+      clear_buffer_.CopyFrom(&clear_cursor, stream_config_);
+      enh_->ProcessRenderAudio(&clear_buffer_, kSampleRate);
+      clear_buffer_.CopyTo(stream_config_, &clear_cursor);
       clear_cursor += kFragmentSize;
-      noise_cursor += kFragmentSize;
     }
     for (int i = 0; i < kSamples; i++) {
       if (std::fabs(clear_data_[i] - orig_data_[i]) > kMaxTestError) {
@@ -345,6 +352,8 @@ class IntelligibilityEnhancerTest : public ::testing::Test {
   }
 
   std::unique_ptr<IntelligibilityEnhancer> enh_;
+  AudioBuffer clear_buffer_;
+  StreamConfig stream_config_;
   std::vector<float> clear_data_;
   std::vector<float> noise_data_;
   std::vector<float> orig_data_;
@@ -357,10 +366,11 @@ TEST_F(IntelligibilityEnhancerTest, TestRenderUpdate) {
   std::fill(orig_data_.begin(), orig_data_.end(), 0.f);
   std::fill(clear_data_.begin(), clear_data_.end(), 0.f);
   EXPECT_FALSE(CheckUpdate());
-  std::generate(noise_data_.begin(), noise_data_.end(), float_rand);
-  EXPECT_FALSE(CheckUpdate());
   std::generate(clear_data_.begin(), clear_data_.end(), float_rand);
   orig_data_ = clear_data_;
+  EXPECT_FALSE(CheckUpdate());
+  std::generate(noise_data_.begin(), noise_data_.end(), float_rand);
+  FloatToFloatS16(noise_data_.data(), noise_data_.size(), noise_data_.data());
   EXPECT_TRUE(CheckUpdate());
 }
 
@@ -418,7 +428,8 @@ TEST_F(IntelligibilityEnhancerTest, TestNoiseGainHasExpectedResult) {
   float* clear_cursor = clear_data_.data();
   for (size_t i = 0; i < kNumFramesToProcess; ++i) {
     enh_->SetCaptureNoiseEstimate(noise, kGain);
-    enh_->ProcessRenderAudio(&clear_cursor, kSampleRate, kNumChannels);
+    clear_buffer_.CopyFrom(&clear_cursor, stream_config_);
+    enh_->ProcessRenderAudio(&clear_buffer_, kSampleRate);
   }
   const std::vector<float>& estimated_psd =
       enh_->noise_power_estimator_.power();