UNTREF Speech Workshop - Revision history

Rtwomey at 01:33, 21 December 2014

2014-12-21T01:33:28Z

Rtwomey at 01:33, 21 December 2014

2014-12-21T01:33:01Z

Rtwomey: /* Introduction */

2013-10-28T04:55:14Z

‎Introduction

Rtwomey: /* Introduction */

2013-10-28T04:54:47Z

‎Introduction

Rtwomey: /* Usage */

2013-09-23T13:08:00Z

‎Usage

Rtwomey: /* Hands-on with Sphinx4 Library for Processing */

2013-09-23T12:54:41Z

‎Hands-on with Sphinx4 Library for Processing

Rtwomey: /* Online Tool for Training Language Models */

2013-09-23T12:52:22Z

‎Online Tool for Training Language Models

Rtwomey: /* Sphinx Knowledge Base - Online Tool for Training Language Models */

2013-09-23T12:51:51Z

‎Sphinx Knowledge Base - Online Tool for Training Language Models

Rtwomey: /* Example - SLM-based Recognition */

2013-09-23T12:48:04Z

‎Example - SLM-based Recognition

Rtwomey: /* Online Tool for Training Language Models */

2013-09-23T12:45:55Z

‎Online Tool for Training Language Models

@@ Line 8: / Line 8: @@
-Background Reading:
+=Background Reading=
 *Natalie Jeremijenko. "If Things Can Talk, What Do They Say?  If We Can Talk To Things, What Do We Say?"  2005-03-05 [http://www.electronicbookreview.com/thread/firstperson/voicechip
 **also see the responses by Simon Penny, Lucy Suchmann, and Natalie linked from that page.

← Older revision		Revision as of 01:33, 21 December 2014
Line 1:		Line 1:
−	~~[[Home \| <<< back to Wiki Home]]~~
−
−	~~=Introduction=~~
−
	http://phenomenologyftw.files.wordpress.com/2011/03/saussure.gif		http://phenomenologyftw.files.wordpress.com/2011/03/saussure.gif

← Older revision		Revision as of 04:55, 28 October 2013
Line 4:		Line 4:

	http://phenomenologyftw.files.wordpress.com/2011/03/saussure.gif		http://phenomenologyftw.files.wordpress.com/2011/03/saussure.gif
−	~~http://www.terrapapers.com/wp-content/uploads/2013/03/Wernicke-5.jpg~~

	'''Talking To Machines'''		'''Talking To Machines'''

← Older revision		Revision as of 04:54, 28 October 2013
Line 4:		Line 4:

	http://phenomenologyftw.files.wordpress.com/2011/03/saussure.gif		http://phenomenologyftw.files.wordpress.com/2011/03/saussure.gif
		+	http://www.terrapapers.com/wp-content/uploads/2013/03/Wernicke-5.jpg

	'''Talking To Machines'''		'''Talking To Machines'''

@@ Line 165: / Line 165: @@
 **
 *to switch voices:
-**
+**<code>(voice_rab_diphone)</code>
 *to exit festival:
 **<code>(exit)</code>

@@ Line 74: / Line 74: @@
 ==Hands-on with Sphinx4 Library for Processing==
-This section includes a wrapper of the CMU Sphinx library for Processing. Read more about the CMU Sphinx project at http://cmusphinx.sourceforge.net/
+*This section includes a wrapper of the CMU Sphinx4 recognizer for Processing. Read more about the CMU Sphinx project at http://cmusphinx.sourceforge.net/.
 ===Library===
 *JAR file and some necessary language and acoustic models to do Sphinx-based speech recognition.
 *Download the zip file below and copy it to your Processing/libraries folder:
-**Download file
+**Download file: http://wiki.dxarts.washington.edu/groups/general/wiki/d7564/attachments/d8bfa/sphinx.zip
 ===Example - Grammar-based Recognition ===
-*Simple grammar-based speech recognitio with Sphinx4 in processing.
+*Simple grammar-based speech recognition with Sphinx4 in processing.
 **Download file: http://wiki.dxarts.washington.edu/groups/general/wiki/d7564/attachments/63c05/sphinxGrammarCustomdict.zip
 this example uses a simple grammar. In the data folder it has a grammar file (.gram), a dictionary file (.dict), and a config file (.xml)
@@ Line 86: / Line 89: @@
 the dict file (upstairs.dict) is a pronunciation dictionary file. It breaks each of those upper-case words fro the grammar into phonemic units. The easiest way to make a new dictionary with your own words is to use the online language tool described below.
 finally, the config file (upstairs.config.xml) specifies various parameters and file-names for the speech recognition engine. In this file you will probably need to change the path to your data files such as the grammar, dict, and the Library files you installed above. If you edit the xml file you will see that a lot of the paths are of the form "/Users/rtwomey/" which is obviously my computer, replace with the path to the file on your system. contact me if this doesn't work
 ===Example - SLM-based Recognition===
 *This example does Sphinx4 automatic speech recognition using a statistical language model (SLM) rather than a grammar.

@@ Line 94: / Line 94: @@
 ===Online Tool for Training Language Models===
 *This produces a statistical language model and dictionary (along with various other products) for the text you upload.
 *Your source file should be plain text, one sentence per line.
@@ Line 103: / Line 102: @@
 *The grammar example above runs from a grammar (.gram) and a dictionary (.dict). This online language tools generates the dictionary for your text but not the grammar. You will need to make the grammar on your own.
 *The SLM example above runs from a grammar (.gram) and a language model (.lm). This online tool generates both files.
 ==Other programming==

@@ Line 93: / Line 93: @@
 *Download file: http://wiki.dxarts.washington.edu/groups/general/wiki/d7564/attachments/01040/sphinxSLMTest.zip
-===Sphinx Knowledge Base - Online Tool for Training Language Models===
+===Online Tool for Training Language Models===
-This produces a statistical language model and dictionary (along with various other products) for any text file you upload: http://www.speech.cs.cmu.edu/tools/lmtool-new.html
+*Sphinx Knowledge Base Tool: http://www.speech.cs.cmu.edu/tools/lmtool-new.html
-your text file should have one sentence per line.
+*This produces a statistical language model and dictionary (along with various other products) for the text you upload.
-upload it and then click "Compile Knowledge Base."
+*Your source file should be plain text, one sentence per line.
-on the results screen, click on the .TAR file to download it. Unzip this, and take the .dic file. This is your pronunciation dictionary. You may want to rename it to .dict to match the files in the sketch. Or change your config file.
+*Upload the file and then click "Compile Knowledge Base."
-The processing example code above runs from a grammar (.gram) and a dictionary (.dict). This online language tools generates the dictionary for your text but not the grammar. You will need to make the grammar on your own.
+*On the results screen, click on the .TAR file to download it. Unzip this file:
 ==Other programming==

@@ Line 89: / Line 89: @@
 *This example does Sphinx4 automatic speech recognition using a statistical language model (SLM) rather than a grammar.
 *I have included two SLMs in the data directory, 3990.lm/3990.dict, and 7707.lm/7707.dict
-*They  were generated with the CMU Sphinx Knowledge Base Tool (see below).
+*They  were generated with the CMU Sphinx Knowledge Base Tool (see below). For each, I uploaded a plain-text file of sentences and saved the resulting tar file with dict, lm, and other results.
 *Download file: http://wiki.dxarts.washington.edu/groups/general/wiki/d7564/attachments/01040/sphinxSLMTest.zip