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 104 matching lines @@
 
 // Use to enable 48kHz support in audio processing. Must be provided through the
 // constructor. It will have no impact if used with
 // AudioProcessing::SetExtraOptions().
 struct AudioProcessing48kHzSupport {
   AudioProcessing48kHzSupport() : enabled(true) {}
   explicit AudioProcessing48kHzSupport(bool enabled) : enabled(enabled) {}
   bool enabled;
 };
 
+// Use to enable intelligibility enhancer in audio processing. It can be set
+// in the constructor or using AudioProcessing::SetExtraOptions().
+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 161 matching lines @@
   // may use the same memory, if desired.
   virtual int ProcessStream(const float* const* src,
                             int samples_per_channel,
                             int input_sample_rate_hz,
                             ChannelLayout input_layout,
                             int output_sample_rate_hz,
                             ChannelLayout output_layout,
                             float* const* dest) = 0;
 
   // Analyzes a 10 ms |frame| of the reverse direction audio stream. The frame
-  // will not be modified. On the client-side, this is the far-end (or to be
-  // rendered) audio.
+  // will not be modified, unless intelligibility is enabled. On the client-
+  // side, this is the far-end (or to be rendered) audio.
   //
   // It is only necessary to provide this if echo processing is enabled, as the
   // 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.
   virtual int AnalyzeReverseStream(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|.
-  virtual int AnalyzeReverseStream(const float* const* data,
+  virtual int AnalyzeReverseStream(float* const* data,
                                    int samples_per_channel,
                                    int sample_rate_hz,
                                    ChannelLayout layout) = 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)
@@ skipping 452 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_