Difference between revisions of "UNTREF Speech Workshop"
From Robert-Depot
| Line 1: | Line 1: | ||
[[Home | <<< back to Wiki Home]] | [[Home | <<< back to Wiki Home]] | ||
| + | ='''Background'''= | ||
| + | *If Things Can Talk, What Do They Say? If We Can Talk to Things, What Do We Say? Natalie Jeremijenko. 2005-03-05 [ http://www.electronicbookreview.com/thread/firstperson/voicechip] | ||
| + | *Dialogue with a Monologue: Voice Chips and the Products of Abstract Speech. [http://topologicalmedialab.net/xinwei/classes/readings/Jeremijenko/VoiceChips.pdf] | ||
| + | |||
='''Recognition'''= | ='''Recognition'''= | ||
=Background= | =Background= | ||
| Line 9: | Line 13: | ||
'''Grammars''' versus '''Satistical Language Models'''. | '''Grammars''' versus '''Satistical Language Models'''. | ||
| + | =Using sphinx= | ||
| + | *open a terminal. Windows, Run->Cmd. | ||
| + | *change to the pocketsphinx directory. | ||
| + | **<code>cd Desktop\untref_speech\pocketsphinx-0.8-win32\bin\Release</code> | ||
| + | *run the pocketsphinx command: | ||
| + | **<code>pocketsphinx_continuous.exe -hmm ..\..\model\hmm\en_US\hub4wsj_sc_8k -dict ..\..\model\lm\en_US\cmu07a.dic -lm ..\..\model\lm\en_US\hub4.5000.DMP</code> | ||
| + | **this should transcribe live from the microphone. | ||
| + | |||
=Training your own Models= | =Training your own Models= | ||
grammer is trivial. | grammer is trivial. | ||
Revision as of 06:10, 3 September 2013
Contents
Background
- If Things Can Talk, What Do They Say? If We Can Talk to Things, What Do We Say? Natalie Jeremijenko. 2005-03-05 [ http://www.electronicbookreview.com/thread/firstperson/voicechip]
- Dialogue with a Monologue: Voice Chips and the Products of Abstract Speech. [1]
Recognition
Background
- pocketsphinx on win32 - http://www.aiaioo.com/cms/index.php?id=28
Installing CMU Sphinx
http://cmusphinx.sourceforge.net/wiki/download/
Models
Acoustic models versus language models.
Grammars versus Satistical Language Models.
Using sphinx
- open a terminal. Windows, Run->Cmd.
- change to the pocketsphinx directory.
cd Desktop\untref_speech\pocketsphinx-0.8-win32\bin\Release
- run the pocketsphinx command:
pocketsphinx_continuous.exe -hmm ..\..\model\hmm\en_US\hub4wsj_sc_8k -dict ..\..\model\lm\en_US\cmu07a.dic -lm ..\..\model\lm\en_US\hub4.5000.DMP- this should transcribe live from the microphone.
Training your own Models
grammer is trivial.
slm, can use online tools. or try the sphinxtrain packages.
Programming with Speech Recognition
Processing. Sphinx4, the java interface.
Python or c++, command line, android. pocketsphinx.
Synthesis
Speech synthesis
FestVox. CMU Speech group.
Festival from University of Edinburgh.
