Integrate Intelligibility with APM

webrtc/modules/audio_processing/include/audio_processing.h

 /*
  *  Copyright (c) 2012 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 98 matching lines @@
   Beamforming()
       : enabled(false),
         array_geometry() {}
   Beamforming(bool enabled, const std::vector<Point>& array_geometry)
       : enabled(enabled),
         array_geometry(array_geometry) {}
   const bool enabled;
   const std::vector<Point> array_geometry;
 };
 
+// Use to enable intelligibility enhancer in audio processing. Must be provided
+// though the constructor. It will have no impact if used with
+// AudioProcessing::SetExtraOptions().
+//
+// Note: If enabled and the reverse stream has more than one output channel,
+// the reverse stream will become an upmixed mono signal.
+struct Intelligibility {
+  Intelligibility() : enabled(false) {}
+  explicit Intelligibility(bool enabled) : enabled(enabled) {}
+  bool enabled;
+};
+
 static const int kAudioProcMaxNativeSampleRateHz = 32000;
 
 // The Audio Processing Module (APM) provides a collection of voice processing
 // components designed for real-time communications software.
 //
 // APM operates on two audio streams on a frame-by-frame basis. Frames of the
 // primary stream, on which all processing is applied, are passed to
 // |ProcessStream()|. Frames of the reverse direction stream, which are used for
 // analysis by some components, are passed to |AnalyzeReverseStream()|. On the
 // client-side, this will typically be the near-end (capture) and far-end
@@ skipping 197 matching lines @@
   // reverse stream forms the echo reference signal. It is recommended, but not
   // necessary, to provide if gain control is enabled. On the server-side this
   // typically will not be used. If you're not sure what to pass in here,
   // chances are you don't need to use it.
   //
   // The |sample_rate_hz_|, |num_channels_|, and |samples_per_channel_|
   // members of |frame| must be valid. |sample_rate_hz_| must correspond to
   // |input_sample_rate_hz()|
   //
   // TODO(ajm): add const to input; requires an implementation fix.
+  // DEPRECATED: Use |ProcessReverseStream| instead.
+  // TODO(ekm): Remove once all users have updated to |ProcessReverseStream|.
   virtual int AnalyzeReverseStream(AudioFrame* frame) = 0;
 
+  // Same as |AnalyzeReverseStream|, but may modify |data| if intelligibility
+  // is enabled.
+  virtual int ProcessReverseStream(AudioFrame* frame) = 0;
+
   // Accepts deinterleaved float audio with the range [-1, 1]. Each element
   // of |data| points to a channel buffer, arranged according to |layout|.
+  // TODO(mgraczyk): Remove once clients are updated to use the new interface.
   //
-  // TODO(mgraczyk): Remove once clients are updated to use the new interface.
+  // DEPRECATED: Use |ProcessReverseStream| instead.
+  // TODO(ekm): Remove once all users have updated to |ProcessReverseStream|.
   virtual int AnalyzeReverseStream(const float* const* data,
                                    int samples_per_channel,
-                                   int sample_rate_hz,
+                                   int rev_sample_rate_hz,
+                                   ChannelLayout layout) = 0;
+
+  virtual int ProcessReverseStream(float* const* data,

[Andrew MacDonald, 2015/07/30 03:53:17]

You don't need this one now...

[ekm, 2015/07/30 06:15:19]

Done. Removed.

+                                   int samples_per_channel,
+                                   int rev_sample_rate_hz,
                                    ChannelLayout layout) = 0;
 
   // Accepts deinterleaved float audio with the range [-1, 1]. Each element of
   // |data| points to a channel buffer, arranged according to |reverse_config|.
+  // DEPRECATED: Use |ProcessReverseStream| instead.
+  // TODO(ekm): Remove once all users have updated to |ProcessReverseStream|.
   virtual int AnalyzeReverseStream(const float* const* data,

[Andrew MacDonald, 2015/07/30 03:53:17]

I don't think any clients are using this yet besides tests. You could remove it
in this CL.

[ekm, 2015/07/30 06:15:19]

Done. Since we're still supporting AnalyzeReverseStream for the other float
interface, and that uses this, I've moved this AnalyzeReverseStream to private.

Also, since this was only used in tests, I've updated this interface to support
a distinct reverse output stream. 

                                    const StreamConfig& reverse_config) = 0;
 
+  virtual int ProcessReverseStream(float* const* data,
+                                   const StreamConfig& reverse_config) = 0;
+
   // This must be called if and only if echo processing is enabled.
   //
   // Sets the |delay| in ms between AnalyzeReverseStream() receiving a far-end
   // frame and ProcessStream() receiving a near-end frame containing the
   // corresponding echo. On the client-side this can be expressed as
   //   delay = (t_render - t_analyze) + (t_process - t_capture)
   // where,
   //   - t_analyze is the time a frame is passed to AnalyzeReverseStream() and
   //     t_render is the time the first sample of the same frame is rendered by
   //     the audio hardware.
@@ skipping 544 matching lines @@
   // This does not impact the size of frames passed to |ProcessStream()|.
   virtual int set_frame_size_ms(int size) = 0;
   virtual int frame_size_ms() const = 0;
 
  protected:
   virtual ~VoiceDetection() {}
 };
 }  // namespace webrtc
 
 #endif  // WEBRTC_MODULES_AUDIO_PROCESSING_INCLUDE_AUDIO_PROCESSING_H_