Ubuntu Wiki

   1 Accessibility Project
   2 
   3 https://help.ubuntu.com/community/Accessibility
   4 http://en.wikipedia.org/wiki/Speech_recognition_in_Linux
   5 Using the best voices available:
   6 http://ubuntuforums.org/showthread.php?t=751169
   7 
   8 Accessibility hardware:
   9 http://www.emotiv.com/store/hardware/epoc-bci/epoc-neuroheadset/
  10 
  11 Rating of known voices:
  12 http://www.webbie.org.uk/Veli-Pekka/reviews_of_speech_synths.html
  13 
  14 
  15 Better Voices Effort:
  16 Cambridge University 
  17 (worked on dasher)
  18 
  19 University of Toronto
  20 http://larswiki.atrc.utoronto.ca/wiki/Software
  21 http://larswiki.atrc.utoronto.ca/wiki/LarsGroup
  22 
  23 University of Edinburgh Festival Speech Synthesis System
  24 
  25 MBROLA Faculte Polytechnique de Mons, TCTS Lab (Contact: Thierry Dutoit thierry.dutoit@umons.ac.be) (Belgium) 
  26 
  27 
  28 
  29 Testing:
  30 CNIB
  31 Tamilnadu (India) Krishnakanth Mane (www.elcot.in/tn.gov.in)
  32 openusability.org (Germany) supports usability is OSS development, has many projects (Jan Muehig jan@openusability.org)
  33 
  34 Better understanding effort:
  35 
  36 http://www.gear21.com/speech/big_html/speech_big.html
  37 https://wiki.ubuntu.com/SpeechRecognition
  38 
  39 Free dictation program is highly sought after
  40 
  41 1) WHAT IS GOOGLE USING FOR THEIR MOBILE APP SPEECH RECOGNITION (Google translate, conversation mode) Contact: Hugo Barra (product management director). Basicly finding out if this is in house developed or open source.
  42 
  43 Gnome Voice Control (sphynx back end) is a start to what could be a great project. It is currently limited to window management and starting applications. Being able to select items, speak letters,  words and keys (tab, enter) would allow a quadriplegic person (such as those with muscular dystrophy and multiple sclerosis) to surf the web almost as well as someone with a keyboard.
  44 http://live.gnome.org/GnomeVoiceControl
  45 http://www.youtube.com/watch?v=ZYP0mt8-mV4
  46 
  47 Voximp seems to do the same
  48 
  49 
  50 CMU Sphinx converts speech to text
  51 Carnegie Mellon University, School of Computer Science (CMU Sphynx)
  52 Sphinx is now on version 4 (Sphinx 4). Perhaps the most (or only) popular open source speech recognition tool, Sphinx is licensed under BSD and is written in Java. Sphinx also offers a mobile version called “PocketSphinx”. This may be more useful for developers than the average user, but it’s one of the only solutions available, not to mention a versatile and thorough one. It does not come ready to go out of the box, but rather is a tool that can be utilized by developers. It certainly needs some work before it’s ready to go.
  53 
  54 Julius (Japan?) working with voxforge
  55 
  56 Simon uses HTK (not GPL, can't be distributed)
  57 
  58 Linux does not currently have a complete solution for speech recognition. Though several projects have been started, none have been finished. There are several pieces of software that can perform some of the speech recognition tasks that Windows or Mac can accomplish, but nowhere near as thoroughly or easily. There is also no proprietary software for speech recognition with Linux, however, there are some partially-completed open source solutions for Ubuntu. Julius Speech Recognition engine is one of these utilities – a program used to interpret and execute a set of pre-determined voice commands.
  59 
  60 Documentation on the installation and use of Julius is very limited due to the fact that the program is not completely finished, so you may not want to attempt an install unless you are completely comfortable with the use of Linux. The Julius package available for download contains two parts – an installer, and the program. First run the installer which will take you through the installation of Julius.
  61 
  62 
  63 
  64 VoxForge has created an initial version of a speech submission application (it is a modified version of the MoodleSpeex Java applet). It allows users to read prompts, record their speech, and click one button to upload the audio to VoxForge.  VoxForge is a project working to compile a collection of transcribed speech for use with both open source and free voice recognition engines. Upon the completion of this project, free open source speech recognition programs should be given the jumpstart to increase significantly.
  65 
  66 Testing
  67 http://www.unitedspinal.org/about/quick-facts/
  68 http://www.christopherreeve.org
  69 http://samschmidt.org/grants
  70 
  71 
  72 
  73 Language Technologies Institute
  74 Carnegie Mellon University
  75 School of Computer Science
  76 http://www.lti.cs.cmu.edu/
  77 Staff: http://www.lti.cs.cmu.edu/people/staff.shtml
  78 Current Projects: http://www.lti.cs.cmu.edu/research/projects.shtml#sp
  79 
  80 
  81 Advertising efforts in Trade publication: Speech Technology
  82 http://www.speechtechmag.com/Archives/ArchiveIssue.aspx?IssueID=3188
  83 
  84 Susanne Schötz (susanne.schotz@ling.lu.se)
  85 Department of Linguistics and Phonetics, Lund University
  86 
  87 Ohio State University
  88 http://www.ling.ohio-state.edu/research/comp/
  89 
  90 
  91 Marcia Davidson
  92 Spoken Language Systems
  93 MIT Computer Science and Artificial Intelligence Laboratory
  94 32 Vassar Street 32-G434
  95 Cambridge, MA 02139 USA
  96 E-mail: marcia@csail.mit.edu
  97 Telephone: (+1) 617.253.3049
  98 Fax: (+1) 617.258.8642
  99 http://groups.csail.mit.edu/sls/
 100 
 101 
 102 Chinese University of Hong Kong
 103 Human-Computer Communications Laboratory (HCCL)
 104 Prof. Helen Meng (Lab Coordinator)
 105 http://www.se.cuhk.edu.hk/facilities/lab_hcc.html
 106 http://www.se.cuhk.edu.hk/hmmengweb/
 107 
 108 UNIVERSITY COLLEGE LONDON
 109 Department of Phonetics and Linguistics
 110 Dept of Phonetics and Linguistics in
 111 collaboration with staff from the Dept of Psychology, the Dept of Computer Science and the
 112 Institute of Laryngology and Otology. There will also be contributions from speakers from
 113 industry and other research institutes.
 114 Dr E. Abberton
 115 Phonetics & Linguistics
 116 Senior Lecturer (Production)
 117 Mr M.G. Ashby
 118 Phonetics & Linguistics
 119 Lecturer (Phonetics)
 120 Dr A. Faulkner
 121 Phonetics & Linguistics
 122 Senior Research Fellow (Hearing)
 123 Prof. A.J. Fourcin
 124 Phonetics & Linguistics
 125 Emeritus Professor (Production)
 126 Dr V. Hazan
 127 Phonetics & Linguistics
 128 Lecturer (Perception)
 129 Mrs J.E. House
 130 Phonetics & Linguistics
 131 Lecturer (Production)
 132 Prof. P. Howell
 133 Psychology
 134 Professor (Hearing & Perception)
 135 Dr M.A. Huckvale Phonetics & Linguistics
 136 Lecturer (Technology)
 137 Prof D. Kemp
 138 Inst. Laryng. & Otology
 139 Professor (Hearing)
 140 Dr H. van de Koot Phonetics & Linguistics
 141 Lecturer (Comp. Linguistics)
 142 Mr. J. Maidment
 143 Phonetics & Linguistics
 144 Lecturer (Phonology)
 145 Prof N. Smith
 146 Phonetics & Linguistics
 147 Professor (Linguistics)
 148 Prof J.C. Wells
 149 Phonetics & Linguistics
 150 Professor (Phonetics & Phonology)
 151 -
 152 Course Director:
 153 Dr Mark Huckvale
 154 Dept of Phonetics and Linguistics
 155 University College London
 156 Gower Street
 157 London WC1E 6BT, United Kingdom
 158 Tel:
 159 (071) 387 7050
 160 Fax:
 161 (071) 383 0752
 162 Email:
 163 M.Huckvale@ucl.ac.uk
 164 
 165 
 166 University of Colorado
 167 http://www.colorado.edu/linguistics/programs/grad/index.html
 168 
 169 Sam Jose State University
 170 http://www.sjsu.edu/linguistics/programs/linguistics/ma_linguistics/index.htm
 171 
 172 
 173 Linguilist - Amazing resource for potential leads:
 174 Research/Technology lists: http://linguistlist.org/index-true.cfm
 175 Educational Programs: http://linguistlist.org/teach/programs/browse-prog1.cfm
 176 Conferences: http://linguistlist.org/callconf/browse-current.cfm?type=Conf
 177 
 178 Speech Technologies - Internet Resources
 179 http://liceu.uab.es/~joaquim/speech_technology/tecnol_parla/recursos.html
 180 
 181 Speech Technolgy Research Centres - Internet Resources
 182 http://homepages.inf.ed.ac.uk/hshimoda/speech-links.html
 183 
 184 UNDL Foundation
 185 http://www.undlfoundation.org/undlfoundation/index.php/en/who-we-are
 186 
 187 Steven Greenberg, founder and president of Silicon Speech, trained in linguistics (A.B. – University of Pennsylvania; Ph.D. – University of California, Los Angeles)
 188 http://www.silicon-speech.com/siliconspeechres.html
 189 
 190 
 191 Name and Title: 
 192 Professor Julie Berndsen BA MA PhD: 
 193 Deputy Registrar For Graduate Studies
 194 Research Interests: Computational Linguistics, Speech Technology 
 195 +353 1 716 2493
 196 Email: Julie Berndsen@ucd.ie
 197 UCD School of Computer Science & Informatics
 198 Dublin UK
 199 
 200 Linguistic Society of America
 201 Conferences: http://www.lsadc.org/info/meet-other.cfm
 202 Post a job: http://www.lsadc.org/info/jobs-index.cfm
 203 List of Universities AND contact info: http://www.lsadc.org/programs/browse-programs.cfm
 204 
 205 Renato De Mori
 206 Email: rdemori@cs.mcgill.ca
 207 Office: 204N
 208 Office Hours:
 209 Phone: +1-514-398-7071
 210 Fax: +1-514-398-3883 
 211 http://www.cs.mcgill.ca/people/faculty/profile?uid=renato
 212 
 213 Department of Phonetics, Saint Petersburg State University
 214 http://ngslt.org/docs/lt-ru.html
 215 
 216 The Association for Computational Linguistics
 217 http://www.aclweb.org/
 218 Special Interest Groups : http://www.aclweb.org/index.php?option=com_content&task=view&id=17&Itemid=28
 219 Contact http://www.aclweb.org/index.php?option=com_contact&Itemid=3
 220 Stroudsburg, PA
 221 Email: 	acl@aclweb.org
 222 Telephone: 	+1-570-476-8006
 223 Fax: 	+1-570-476-0860