Pull the Voice Activity Detector out from the AGC

webrtc/modules/audio_processing/vad/voice_activity_detector.cc

+/*
+ *  Copyright (c) 2015 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.
+ */
+
+#include "webrtc/modules/audio_processing/vad/voice_activity_detector.h"
+
+#include "webrtc/base/checks.h"
+
+namespace webrtc {
+namespace {
+
+const int kMaxLength = 320;
+const int kNumChannels = 1;
+
+const double kDefaultVoiceValue = 1.0;
+const double kNeutralProbability = 0.5;
+const double kLowProbability = 0.01;
+
+}  // namespace
+
+VoiceActivityDetector::VoiceActivityDetector()
+    : last_voice_probability_(kDefaultVoiceValue),
+      // Initialize to the most common resampling situation.
+      resampler_(kMaxLength, kLength10Ms, kNumChannels),
+      standalone_vad_(StandaloneVad::Create()) {
+}
+
+// Because ISAC has a different chunk length, it updates
+// |chunkwise_voice_probabilities_| and |chunkwise_rms_| when there is new data.
+// Else it clears them.

[Andrew MacDonald, 2015/06/16 22:18:32]

Else -> Otherwise

[aluebs-webrtc, 2015/06/17 01:44:31]

Done.

+void VoiceActivityDetector::ProcessChunk(const int16_t* audio,
+                                         int length,
+                                         int sample_rate_hz) {
+  DCHECK_EQ(length, sample_rate_hz / 100);
+  DCHECK_LE(length, kMaxLength);
+  // Resample to the required rate.
+  const int16_t* resampled_ptr = audio;
+  if (sample_rate_hz != kSampleRateHz) {
+    CHECK_EQ(
+        resampler_.ResetIfNeeded(sample_rate_hz, kSampleRateHz, kNumChannels),
+        0);
+    resampler_.Push(audio, length, resampled_, kLength10Ms, length);
+    resampled_ptr = resampled_;
+  }
+  DCHECK_EQ(length, kLength10Ms);
+
+  CHECK_EQ(standalone_vad_->AddAudio(audio, length), 0);
+
+  audio_processing_.ExtractFeatures(resampled_ptr, length, &features_);
+
+  chunkwise_voice_probabilities_.clear();
+  chunkwise_rms_.clear();
+  if (features_.num_frames > 0) {
+    if (features_.silence) {
+      // The other features are invalid, so set the voice probabilities to an
+      // arbitrary low value.
+      chunkwise_voice_probabilities_.assign(features_.num_frames,
+                                            kLowProbability);
+    } else {
+      chunkwise_voice_probabilities_.assign(features_.num_frames,
+                                            kNeutralProbability);
+      CHECK_GE(
+          standalone_vad_->GetActivity(&chunkwise_voice_probabilities_[0],
+                                       chunkwise_voice_probabilities_.size()),
+          0);
+      CHECK_GE(pitch_based_vad_.VoicingProbability(
+                   features_, &chunkwise_voice_probabilities_[0]),
+               0);
+    }
+    last_voice_probability_ = chunkwise_voice_probabilities_.back();
+  }
+  for (int i = 0; i < features_.num_frames; ++i) {
+    chunkwise_rms_.push_back(features_.rms[i]);
+  }
+}
+
+}  // namespace webrtc