Only update Intelligibility Enhancer gains every 10 chunks

webrtc/modules/audio_processing/intelligibility/intelligibility_enhancer.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.
  */
 
@@ skipping 22 matching lines @@
 const float kLambdaTop = -1e-5f;      // search for lamda.
 const float kVoiceProbabilityThreshold = 0.02f;
 // Number of chunks after voice activity which is still considered speech.
 const size_t kSpeechOffsetDelay = 80;
 const float kDecayRate = 0.994f;              // Power estimation decay rate.
 const float kMaxRelativeGainChange = 0.006f;
 const float kRho = 0.0004f;  // Default production and interpretation SNR.
 const float kPowerNormalizationFactor = 1.f / (1 << 30);
 const float kMaxActiveSNR = 128.f;  // 21dB
 const float kMinInactiveSNR = 32.f;  // 15dB
+const size_t kGainUpdatePeriod = 10u;
 
 // Returns dot product of vectors |a| and |b| with size |length|.
 float DotProduct(const float* a, const float* b, size_t length) {
   float ret = 0.f;
   for (size_t i = 0; i < length; ++i) {
     ret += a[i] * b[i];
   }
   return ret;
 }
 
@@ skipping 28 matching lines @@
       center_freqs_(bank_size_),
       capture_filter_bank_(CreateErbBank(num_noise_bins)),
       render_filter_bank_(CreateErbBank(freqs_)),
       gains_eq_(bank_size_),
       gain_applier_(freqs_, kMaxRelativeGainChange),
       audio_s16_(chunk_length_),
       chunks_since_voice_(kSpeechOffsetDelay),
       is_speech_(false),
       snr_(kMaxActiveSNR),
       is_active_(false),
+      num_chunks_(0u),
       noise_estimation_buffer_(num_noise_bins),
       noise_estimation_queue_(kMaxNumNoiseEstimatesToBuffer,
                               std::vector<float>(num_noise_bins),
                               RenderQueueItemVerifier<float>(num_noise_bins)) {
   RTC_DCHECK_LE(kRho, 1.f);
 
   const size_t erb_index = static_cast<size_t>(
       ceilf(11.17f * logf((kClipFreqKhz + 0.312f) / (kClipFreqKhz + 14.6575f)) +
             43.f));
   start_freq_ = std::max(static_cast<size_t>(1), erb_index * kErbResolution);
@@ skipping 36 matching lines @@
     const std::complex<float>* const* in_block,
     size_t in_channels,
     size_t frames,
     size_t /* out_channels */,
     std::complex<float>* const* out_block) {
   RTC_DCHECK_EQ(freqs_, frames);
   if (is_speech_) {
     clear_power_estimator_.Step(in_block[0]);
   }
   SnrBasedEffectActivation();
-  if (is_active_) {
+  if (is_active_ && num_chunks_++ % kGainUpdatePeriod == 0) {
     MapToErbBands(clear_power_estimator_.power().data(), render_filter_bank_,
                   filtered_clear_pow_.data());
     MapToErbBands(noise_power_estimator_.power().data(), capture_filter_bank_,
                   filtered_noise_pow_.data());
     SolveForGainsGivenLambda(kLambdaTop, start_freq_, gains_eq_.data());
     const float power_target = std::accumulate(
         filtered_clear_pow_.data(),
         filtered_clear_pow_.data() + bank_size_,
         0.f);
     const float power_top =
@@ skipping 184 matching lines @@
   vad_.ProcessChunk(audio_s16_.data(), chunk_length_, sample_rate_hz_);
   if (vad_.last_voice_probability() > kVoiceProbabilityThreshold) {
     chunks_since_voice_ = 0;
   } else if (chunks_since_voice_ < kSpeechOffsetDelay) {
     ++chunks_since_voice_;
   }
   return chunks_since_voice_ < kSpeechOffsetDelay;
 }
 
 }  // namespace webrtc