Make the nonlinear beamformer steerable

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.
  */
 
@@ skipping 13 matching lines @@
 // 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 {
  public:
-  explicit NonlinearBeamformer(const std::vector<Point>& array_geometry);
+  static const float kHalfBeamWidthRadians;
+
+  explicit NonlinearBeamformer(
+      const std::vector<Point>& array_geometry,
+      SphericalPointf target_direction = SphericalPointf(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;
 
+  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_; }
 
  protected:
   // Process one frequency-domain block of audio. This is where the fun
   // happens. Implements LappedTransform::Callback.
   void ProcessAudioBlock(const complex<float>* const* input,
                          int num_input_channels,
                          size_t num_freq_bins,
                          int num_output_channels,
                          complex<float>* const* output) override;
 
  private:
+  FRIEND_TEST_ALL_PREFIXES(NonlinearBeamformerTest,
+                           InterfAnglesTakeAmbiguityIntoAccount);
+
   typedef Matrix<float> MatrixF;
   typedef ComplexMatrix<float> ComplexMatrixF;
   typedef complex<float> complex_f;
 
-  void InitFrequencyCorrectionRanges();
+  void InitLowFrequencyCorrectionRanges();
+  void InitHighFrequencyCorrectionRanges();
   void InitInterfAngles();
   void InitDelaySumMasks();
   void InitTargetCovMats();
+  void InitDiffuseCovMats();
   void InitInterfCovMats();
+  void NormalizeCovMats();
 
   // Calculates postfilter masks that minimize the mean squared error of our
   // estimation of the desired signal.
   float CalculatePostfilterMask(const ComplexMatrixF& interf_cov_mat,
                                 float rpsiw,
                                 float ratio_rxiw_rxim,
                                 float rmxi_r);
 
   // Prevents the postfilter masks from degenerating too quickly (a cause of
   // musical noise).
@@ skipping 25 matching lines @@
   // Deals with the fft transform and blocking.
   size_t chunk_length_;
   rtc::scoped_ptr<LappedTransform> lapped_transform_;
   float window_[kFftSize];
 
   // Parameters exposed to the user.
   const int num_input_channels_;
   int sample_rate_hz_;
 
   const std::vector<Point> array_geometry_;
+  // The normal direction of the array in the xy-plane. It is set to null Point

[Andrew MacDonald, 2015/10/28 01:57:57]

origin or zero

[aluebs-webrtc, 2015/10/29 00:34:21]

Not necessary anymore, since using Maybe.

+  // if the array has no normal, or the normal is not in the xy-plane.
+  const Point array_normal_;
 
   // Minimum spacing between microphone pairs.
   const float min_mic_spacing_;
 
   // Calculated based on user-input and constants in the .cc file.
   size_t low_mean_start_bin_;
   size_t low_mean_end_bin_;
   size_t high_mean_start_bin_;
   size_t high_mean_end_bin_;
 
   // Quickly varying mask updated every block.
   float new_mask_[kNumFreqBins];
   // Time smoothed mask.
   float time_smooth_mask_[kNumFreqBins];
   // Time and frequency smoothed mask.
   float final_mask_[kNumFreqBins];
 
+  float target_angle_radians_;
   // Angles of the interferer scenarios.
   std::vector<float> interf_angles_radians_;
+  // The angle between the target and the interferer scenarios.
+  const float away_radians_;
 
   // Array of length |kNumFreqBins|, Matrix of size |1| x |num_channels_|.
   ComplexMatrixF delay_sum_masks_[kNumFreqBins];
   ComplexMatrixF normalized_delay_sum_masks_[kNumFreqBins];
 
-  // Array of length |kNumFreqBins|, Matrix of size |num_input_channels_| x
+  // Arrays of length |kNumFreqBins|, Matrix of size |num_input_channels_| x
   // |num_input_channels_|.
   ComplexMatrixF target_cov_mats_[kNumFreqBins];
-
+  ComplexMatrixF uniform_cov_mat_[kNumFreqBins];
   // Array of length |kNumFreqBins|, Matrix of size |num_input_channels_| x
   // |num_input_channels_|. ScopedVector has a size equal to the number of
   // interferer scenarios.
   ScopedVector<ComplexMatrixF> interf_cov_mats_[kNumFreqBins];
 
   // Of length |kNumFreqBins|.
   float wave_numbers_[kNumFreqBins];
 
   // Preallocated for ProcessAudioBlock()
   // Of length |kNumFreqBins|.
@@ skipping 12 matching lines @@
   // 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_