Google Voice Recognition - Revision history

Rowntreerob: /* Future Development */

2012-10-22T23:17:29Z

‎Future Development

Rowntreerob: /* Future Development */

2012-10-22T23:16:04Z

‎Future Development

Rowntreerob: /* Future Development */

2012-10-22T23:14:09Z

‎Future Development

Rowntreerob: /* Future Development */

2012-10-22T23:11:28Z

‎Future Development

Rowntreerob: /* Future Development */

2012-10-22T23:09:14Z

‎Future Development

Rowntreerob: /* Links */

2012-10-22T22:59:38Z

‎Links

Niebert: /* Future Development */

2011-12-09T08:24:00Z

‎Future Development

Glenn: + Category:Audio Applications

2011-11-30T18:34:15Z

+ Category:Audio Applications

Niebert: /* Compare Performance and Results of Google Voice API with Standalone Speech Recognition on Linux */

2011-11-14T15:40:56Z

‎Compare Performance and Results of Google Voice API with Standalone Speech Recognition on Linux

Niebert: /* Compare Performance and Results of Google Voice API with Standalone Speech Recognition on Linux */

2011-11-14T15:39:47Z

‎Compare Performance and Results of Google Voice API with Standalone Speech Recognition on Linux

@@ Line 88: / Line 88: @@
 * By the Audio-File-Submit and Text-File-Return of a server based speech recognition the Open Source Speech Recognition on Linux can be improved.
 * Most advanced candidate seems to [http://www.simon-listens.org Simon Listens] with server based backend (Tested on Ubuntu).
-'''Google Streaming Remote Engine''' - look over the chrome [http://src.chromium.org/viewvc/chrome/trunk/src/content/browser/speech/google_one_shot_remote_engine_unittest.h?view=markup source]. As you can see in the long introductory comment from the sourcecode from the link, the javascript api work includes a separate streaming feature where there is a full-duplex Http connection. This allows a long running connection for chunking audio data on the submit side. No longer do you have to segment audio clips longer than 15 seconds as mentioned earlier. While there is more data, you just use the Http connection to  write another chunk on the upload channel. The download stream returns the json containing hypotheses and utterance elements.
+'''Google Streaming Remote Engine''' - look over the chrome [http://src.chromium.org/viewvc/chrome/trunk/src/content/browser/speech/google_streaming_remote_engine.h?view=markup source]. As you can see in the long introductory comment from the sourcecode from the link, the javascript api work includes a separate streaming feature where there is a full-duplex Http connection. This allows a long running connection for chunking audio data on the submit side. No longer do you have to segment audio clips longer than 15 seconds as mentioned earlier. While there is more data, you just use the Http connection to  write another chunk on the upload channel. The download stream returns the json containing hypotheses and utterance elements.
 '''TBD''' -  beta URL at google for the streaming-speech engine  ___________

@@ Line 90: / Line 90: @@
 '''Google Streaming Remote Engine''' - look over the chrome [http://src.chromium.org/viewvc/chrome/trunk/src/content/browser/speech/google_one_shot_remote_engine_unittest.h?view=markup source]. As you can see in the long introductory comment from the sourcecode from the link, the javascript api work includes a separate streaming feature where there is a full-duplex Http connection. This allows a long running connection for chunking audio data on the submit side. No longer do you have to segment audio clips longer than 15 seconds as mentioned earlier. While there is more data, you just use the Http connection to  write another chunk on the upload channel. The download stream returns the json containing hypotheses and utterance elements.
-'''FAQ''' - what is the beta URL at google for the streaming-speech engine?
+'''TBD''' -  beta URL at google for the streaming-speech engine  ___________
 ==Links==

@@ Line 88: / Line 88: @@
 * By the Audio-File-Submit and Text-File-Return of a server based speech recognition the Open Source Speech Recognition on Linux can be improved.
 * Most advanced candidate seems to [http://www.simon-listens.org Simon Listens] with server based backend (Tested on Ubuntu).
-'''Google Streaming Remote Engine''' - look over the chrome [http://src.chromium.org/viewvc/chrome/trunk/src/content/browser/speech/google_one_shot_remote_engine_unittest.cc?view=markup source]. As you can see in the comment from the link, the javascript api work includes a separate streaming feature where there is a full-duplex Http connection. This allows a long running connection for chunking audio data on the submit side. No longer do you have to segment audio clips longer than 15 seconds as mentioned earlier. While there is more data, you just use the Http connection to  write another chunk on the upload channel. The download stream returns the json containing hypotheses and utterance elements.
+'''Google Streaming Remote Engine''' - look over the chrome [http://src.chromium.org/viewvc/chrome/trunk/src/content/browser/speech/google_one_shot_remote_engine_unittest.h?view=markup source]. As you can see in the long introductory comment from the sourcecode from the link, the javascript api work includes a separate streaming feature where there is a full-duplex Http connection. This allows a long running connection for chunking audio data on the submit side. No longer do you have to segment audio clips longer than 15 seconds as mentioned earlier. While there is more data, you just use the Http connection to  write another chunk on the upload channel. The download stream returns the json containing hypotheses and utterance elements.
 ==Links==

@@ Line 88: / Line 88: @@
 * By the Audio-File-Submit and Text-File-Return of a server based speech recognition the Open Source Speech Recognition on Linux can be improved.
 * Most advanced candidate seems to [http://www.simon-listens.org Simon Listens] with server based backend (Tested on Ubuntu).
-'''Google Streaming Remote Engine''' look over the chrome [http://src.chromium.org/viewvc/chrome/trunk/src/content/browser/speech/google_one_shot_remote_engine_unittest.cc source]. As you can see the javascript api work includes a separate streaming feature where there is a full-duplex Http connection. This allows a long running connection for chunking audio data on the submit side. No longer do you have to segment audio clips longer than 15 seconds as mentioned earlier. While there is more data, you just use the Http connection to  write another chunk on the upload channel. The download stream returns the json containing hypotheses and utterance elements.
+'''Google Streaming Remote Engine''' - look over the chrome [http://src.chromium.org/viewvc/chrome/trunk/src/content/browser/speech/google_one_shot_remote_engine_unittest.cc?view=markup source]. As you can see in the comment from the link, the javascript api work includes a separate streaming feature where there is a full-duplex Http connection. This allows a long running connection for chunking audio data on the submit side. No longer do you have to segment audio clips longer than 15 seconds as mentioned earlier. While there is more data, you just use the Http connection to  write another chunk on the upload channel. The download stream returns the json containing hypotheses and utterance elements.
 ==Links==

@@ Line 88: / Line 88: @@
 * By the Audio-File-Submit and Text-File-Return of a server based speech recognition the Open Source Speech Recognition on Linux can be improved.
 * Most advanced candidate seems to [http://www.simon-listens.org Simon Listens] with server based backend (Tested on Ubuntu).
 ==Links==

@@ Line 94: / Line 94: @@
 * with the [http://www.google.com/chrome Chrome Browser] on a Linux Box you can test the Google Voice API [http://slides.html5rocks.com/#speech-input http://slides.html5rocks.com/#speech-input] via a Web-Interface.
 * For standalone speech recognition on Linux Systems see [http://en.wikipedia.org/wiki/Speech_recognition_in_Linux Wikipedia-Article].
+* Web Speech API - W3C Spec [http://dvcs.w3.org/hg/speech-api/raw-file/tip/speechapi.html here]
 [[Category:Audio Applications]]

← Older revision		Revision as of 18:34, 30 November 2011
Line 93:		Line 93:
	* with the [http://www.google.com/chrome Chrome Browser] on a Linux Box you can test the Google Voice API [http://slides.html5rocks.com/#speech-input http://slides.html5rocks.com/#speech-input] via a Web-Interface.		* with the [http://www.google.com/chrome Chrome Browser] on a Linux Box you can test the Google Voice API [http://slides.html5rocks.com/#speech-input http://slides.html5rocks.com/#speech-input] via a Web-Interface.
	* For standalone speech recognition on Linux Systems see [http://en.wikipedia.org/wiki/Speech_recognition_in_Linux Wikipedia-Article].		* For standalone speech recognition on Linux Systems see [http://en.wikipedia.org/wiki/Speech_recognition_in_Linux Wikipedia-Article].
		+
		+	[[Category:Audio Applications]]

@@ Line 76: / Line 76: @@
 * Compare results with same audio file by Google Voice API and Simon.
-{{Note|These test might help to create a remote Speech Recognition Solution based on Julius and Simon for usage on a Freerunnner.}}
+{{Note|These test might help to create a remote Speech Recognition Solution based on Julius and Simon for usage on a Freerunnner. Simon can run as server. Tests can be used to connect your freerunner to Simon.}}
 ==Future Development==

@@ Line 68: / Line 68: @@
 * Install the PPA for Ubuntu 10.10 by
    sudo add-apt-repository ppa:grasch-simon-listens/simon
 * Install OpenSource Speech Recognition Software  [http://sourceforge.net/projects/speech2text/ Simon] via Ubuntu Software-Center and configure Simon (see [http://simon.gibolles.com/doc/0.3/simon/en/index.pdf PDF-Simon-Tutorial]).
 * Start Simon from Commandline and test a few words with your mic and record it to an audio file.
 * Compare results with same audio file by Google Voice API and Simon.