Pull out the PostFilter to its own NonlinearBeamformer API

webrtc/modules/audio_processing/beamformer/nonlinear_beamformer.h

 /*
  *  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.
  */
 
 #ifndef WEBRTC_MODULES_AUDIO_PROCESSING_BEAMFORMER_NONLINEAR_BEAMFORMER_H_
 #define WEBRTC_MODULES_AUDIO_PROCESSING_BEAMFORMER_NONLINEAR_BEAMFORMER_H_
 
 // MSVC++ requires this to be set before any other includes to get M_PI.
 #define _USE_MATH_DEFINES
 
 #include <math.h>
 
 #include <memory>
 #include <vector>
 
 #include "webrtc/common_audio/lapped_transform.h"
 #include "webrtc/common_audio/channel_buffer.h"
 #include "webrtc/modules/audio_processing/beamformer/beamformer.h"
 #include "webrtc/modules/audio_processing/beamformer/complex_matrix.h"
 
 namespace webrtc {
 
+class PostFilterTransform;
+
 // Enhances sound sources coming directly in front of a uniform linear array
 // and suppresses sound sources coming from all other directions. Operates on
 // multichannel signals and produces single-channel output.
 //
 // The implemented nonlinear postfilter algorithm taken from "A Robust Nonlinear
 // Beamforming Postprocessor" by Bastiaan Kleijn.
 class NonlinearBeamformer
   : public Beamformer<float>,
     public LappedTransform::Callback {
+  friend class PostFilterTransform;
  public:
   static const float kHalfBeamWidthRadians;
 
   explicit NonlinearBeamformer(
       const std::vector<Point>& array_geometry,
       SphericalPointf target_direction =
           SphericalPointf(static_cast<float>(M_PI) / 2.f, 0.f, 1.f));
 
   // Sample rate corresponds to the lower band.
   // Needs to be called before the NonlinearBeamformer can be used.
   void Initialize(int chunk_size_ms, int sample_rate_hz) override;
 
   // Process one time-domain chunk of audio. The audio is expected to be split
   // into frequency bands inside the ChannelBuffer. The number of frames and
   // channels must correspond to the constructor parameters. The same
   // ChannelBuffer can be passed in as |input| and |output|.
   void ProcessChunk(const ChannelBuffer<float>& input,
                     ChannelBuffer<float>* output) override;
+  // Applies the postfilter mask to one chunk of audio. The audio is expected to

[peah-webrtc, 2016/05/22 21:06:48]

I think that this description is longer than required.

The description of the band splitting should not be needed here. It is rather a
description of ChannelBuffer and if it needs to be clarified further it would be
better to do it in a unittest which illustrates the usage of the method.

I think the requirements on the frame size and the number of channels are better
illustrated by a DCHECK inside the code.

[aluebs-webrtc, 2016/05/26 01:04:45]

I personally think adding more documentation than required is not a problem. It
is also consistent (band splitting and requirements on input) with the
ProcessChunk documentation. There is a DCHECK on place as well.

[peah-webrtc, 2016/05/26 08:48:52]

Great! 

+  // be split into frequency bands inside the ChannelBuffer. The number of
+  // frames must correspond to the constructor parameters and the number of
+  // channels is expected to be 1, since that is the output number of channels
+  // of ProcessChunk(). The same ChannelBuffer can be passed in as |input| and
+  // |output|.
+  void PostFilter(const ChannelBuffer<float>& input,
+                  ChannelBuffer<float>* output) override;
 
   void AimAt(const SphericalPointf& target_direction) override;
 
   bool IsInBeam(const SphericalPointf& spherical_point) override;
 
   // After processing each block |is_target_present_| is set to true if the
   // target signal es present and to false otherwise. This methods can be called
   // to know if the data is target signal or interference and process it
   // accordingly.
   bool is_target_present() override { return is_target_present_; }
@@ skipping 43 matching lines @@
   // Postfilter masks are also unreliable at high frequencies. Average mid-high
   // frequency masks to calculate a single mask per block which can be applied
   // in the time-domain. Further, we average these block-masks over a chunk,
   // resulting in one postfilter mask per audio chunk. This allows us to skip
   // both transforming and blocking the high-frequency signal.
   void ApplyHighFrequencyCorrection();
 
   // Compute the means needed for the above frequency correction.
   float MaskRangeMean(size_t start_bin, size_t end_bin);
 
-  // Applies both sets of masks to |input| and store in |output|.
-  void ApplyMasks(const complex_f* const* input, complex_f* const* output);
+  // Applies delay-and-sum mask to |input| and store in |output|.
+  void ApplyDelayAndSum(const complex_f* const* input,
+                        complex_f* const* output);
+  // Applies post-filter mask to |input| and store in |output|.
+  void ApplyPostFilter(const complex_f* input, complex_f* output);
 
   void EstimateTargetPresence();
 
   static const size_t kFftSize = 256;
   static const size_t kNumFreqBins = kFftSize / 2 + 1;
 
   // Deals with the fft transform and blocking.
   size_t chunk_length_;
-  std::unique_ptr<LappedTransform> lapped_transform_;
+  std::unique_ptr<LappedTransform> process_transform_;
+  std::unique_ptr<LappedTransform> postfilter_transform_;
   float window_[kFftSize];
 
   // Parameters exposed to the user.
   const size_t num_input_channels_;
   int sample_rate_hz_;
 
   const std::vector<Point> array_geometry_;
   // The normal direction of the array if it has one and it is in the xy-plane.
   const rtc::Optional<Point> array_normal_;
 
@@ skipping 39 matching lines @@
   // Of length |kNumFreqBins|.
   float rxiws_[kNumFreqBins];
   // The vector has a size equal to the number of interferer scenarios.
   std::vector<float> rpsiws_[kNumFreqBins];
 
   // The microphone normalization factor.
   ComplexMatrixF eig_m_;
 
   // For processing the high-frequency input signal.
   float high_pass_postfilter_mask_;
+  float old_high_pass_mask_;
 
   // True when the target signal is present.
   bool is_target_present_;
   // Number of blocks after which the data is considered interference if the
   // mask does not pass |kMaskSignalThreshold|.
   size_t hold_target_blocks_;
   // Number of blocks since the last mask that passed |kMaskSignalThreshold|.
   size_t interference_blocks_count_;
 };
 
 }  // namespace webrtc
 
 #endif  // WEBRTC_MODULES_AUDIO_PROCESSING_BEAMFORMER_NONLINEAR_BEAMFORMER_H_