Support for providing media stream audio track to speech recognition

Source/web/SpeechRecognitionClientProxy.cpp

 /*
  * Copyright (C) 2012 Google Inc. All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions
  * are met:
  *  * Redistributions of source code must retain the above copyright
  *    notice, this list of conditions and the following disclaimer.
  *  * Redistributions in binary form must reproduce the above copyright
  *    notice, this list of conditions and the following disclaimer in the
@@ skipping 15 matching lines @@
 #include "config.h"
 #include "web/SpeechRecognitionClientProxy.h"
 
 #include "core/dom/ExecutionContext.h"
 #include "modules/speech/SpeechGrammarList.h"
 #include "modules/speech/SpeechRecognition.h"
 #include "modules/speech/SpeechRecognitionError.h"
 #include "modules/speech/SpeechRecognitionResult.h"
 #include "modules/speech/SpeechRecognitionResultList.h"
 #include "platform/weborigin/SecurityOrigin.h"
+#include "public/platform/WebMediaStreamTrack.h"
 #include "public/web/WebSecurityOrigin.h"
 #include "public/web/WebSpeechGrammar.h"
 #include "public/web/WebSpeechRecognitionHandle.h"
 #include "public/web/WebSpeechRecognitionParams.h"
 #include "public/web/WebSpeechRecognitionResult.h"
 #include "public/web/WebSpeechRecognizer.h"
 #include "wtf/PassRefPtr.h"
 
 namespace blink {
 
 SpeechRecognitionClientProxy::~SpeechRecognitionClientProxy()
 {
 }
 
 PassOwnPtr<SpeechRecognitionClientProxy> SpeechRecognitionClientProxy::create(WebSpeechRecognizer* recognizer)
 {
     return adoptPtr(new SpeechRecognitionClientProxy(recognizer));
 }
 
-void SpeechRecognitionClientProxy::start(SpeechRecognition* recognition, const SpeechGrammarList* grammarList, const String& lang, bool continuous, bool interimResults, unsigned long maxAlternatives)
+void SpeechRecognitionClientProxy::start(SpeechRecognition* recognition, const SpeechGrammarList* grammarList, const String& lang, bool continuous, bool interimResults, unsigned long maxAlternatives, MediaStreamTrack* audioTrack)
 {
     WebVector<WebSpeechGrammar> webSpeechGrammars(static_cast<size_t>(grammarList->length()));
     for (unsigned long i = 0; i < grammarList->length(); ++i)
         webSpeechGrammars[i] = grammarList->item(i);
 
     WebSpeechRecognitionParams params(webSpeechGrammars, lang, continuous, interimResults, maxAlternatives, WebSecurityOrigin(recognition->executionContext()->securityOrigin()));
-    m_recognizer->start(WebSpeechRecognitionHandle(recognition), params, this);
+    if (audioTrack)
+        m_recognizer->start(WebSpeechRecognitionHandle(recognition), params, audioTrack->component(), this);

[Mike West, 2014/09/17 10:20:27]

Could the new MediaStreamComponent argument instead be added as a property on
the WebSpeechRecognitionParams object? That would avoid the requirement to
overload '::start()' here.

[burnik, 2014/09/17 11:17:20]

Good point as well. Although that would require more changes to align with those
params. Also, notice that most of those params are actually related to the
remote API and have nothing to do with audio.

On 2014/09/17 10:20:27, Mike West wrote:

[Mike West, 2014/09/17 11:30:46]

Sure. But I think it reduces the complexity of the system by ensuring that
there's one point where you make changes to the parameters necessary to
initialize the recognizer, rather than breaking the flow up into multiple
methods.
Well, it's called WebSpeechRecognitionParams, which suggests that it contains
bits and pieces which are necessary to do speech recognition. Adding an audio
track to that object doesn't seem like it's much of a stretch.

I don't think this sort of thing is a requirement, but it would be nice to keep
the public API simpler. *shrug*

+    else
+        m_recognizer->start(WebSpeechRecognitionHandle(recognition), params, this);
 }
 
 void SpeechRecognitionClientProxy::stop(SpeechRecognition* recognition)
 {
     m_recognizer->stop(WebSpeechRecognitionHandle(recognition), this);
 }
 
 void SpeechRecognitionClientProxy::abort(SpeechRecognition* recognition)
 {
     m_recognizer->abort(WebSpeechRecognitionHandle(recognition), this);
@@ skipping 64 matching lines @@
     SpeechRecognition* recognition(handle);
     recognition->didEnd();
 }
 
 SpeechRecognitionClientProxy::SpeechRecognitionClientProxy(WebSpeechRecognizer* recognizer)
     : m_recognizer(recognizer)
 {
 }
 
 } // namespace blink