This
category tracks significant software/hardware advances, companies and sites in
the area of speech processing, recognition and voice control for computers.
Technically voice recognition to the industry means speaker verification and
identification, i.e., who is speaking - is it Alex or Jane. Speech recognition
is the identification of content - what did Alex say. This category does not,
therefore, take speech recognition to be synonymous with voice recognition.
i)Answers
For Executives.
Fast
loading, informative site addressing typical questions executives might have
about speech recognition
for offices and companies. Contains
product reviews, installation guidelines, provocative analysis of the industry
for people who would rather use voice technology instead of typing
http://www.voicewizard.com
ii)Commercial Speech Recognition
Site
name a bit misleading. It is a broad collection of site links to speech
recognition companies,
services, products, magazines, trade shows, books and online resources with a
brief personal summary of each.
http://www.tiac.net/users/rwilcox/speech.html
iii)Speech
Recognition News and Studies
TMA
Associates publishes Speech Recognition
Update, an industry newsletter on the business, products, markets, and companies
in speech recognition,
text-to-speech, and speaker
verification. The site contains headlines and recent news, as well as
descriptions of TMA conferences and market studies in speech
recognition.
http://www.tmaa.com
iv)
Conversay
Computational
Computing Corp. sells application specific speech
enabled products including voice responsive browsers, office messaging system, speech
SDK's for mobile devices, telephony speech
servers.
http://www.conversay.com
v)Digilog
UK
Develops
computerized lie detector systems that perform realtime diagnosis of vocal
segments. Products include Truster - the world's first personal lie detector,
and Trusterpro - a professional version that provides investigators, law
enforcement agents and executives with reliable truth verification through
multiple modes of operation.
http://www.digilog.org
vi)Dragon Naturally Speaking
Desktop
and mobile dictation, telephony, vertical market add-ons and developers' tools.
Brand and technology acquired by Lernout and Hauspie and recently (November
2001) sold to Scansoft.
Dragon
NaturallySpeaking® v7.0 you can create, edit, and revise documents and
e-mail-even surf the Web by voice, using web browser Internet Explorer. Just
speak, and your words appear in business letters, reports, e-mails and virtually
all Windows®-based applications.
Dragon NaturallySpeaking® Preferred v7.0 makes it easy to edit and format
text-even change fonts, colors, and sizes-by voice. Insert phrases and
paragraphs with only a few words. Listen to text and e-mail read aloud by
replaying your recorded speech. You can browse the Web, hands-free.
http://www.scansoft.com/naturallyspeaking/
vii)Fourth Annual Telephony Voice User Interface Conference
Brings
together leading managers, experts and investors in speech
recognition and telephony, to
explore the business opportunities created by telephone speech
recognition, text-to-speech
synthesis, and Voice Web technology.
http://www.kprinc.com/2001/pr037.htm
viii)Game
Commander
Speaker
independent (no training required) voice control software for Windows games
replaces keystrokes with voice commands for popular games. Template files,
patches, message boards, downloads, free trial version.
http://www.gamecommander.com
ix)Grover
Industries, Inc.
Provides
command and control applications for internet and desktop contexts.
http://www.groverind.com
x)HAL
Hits the Home
Voice
recognition software (with product
names HAL2000 etc.) for Windows 95/98 that supports air conditioning, telephony,
infrared, Internet, X-10 and security - for use in home systems. Site gives
audio examples of the interactions possible.
http://www.automatedliving.com/
xi)HAL2000
Distributor / UK
UK
distributor of HAL2000 voice-activated home operating system.
http://www.habitek.co.uk/
xii)Hand
Held
Site
sells a large-vocabulary continuous speech
recognizer that runs on a PDA. Current offering (free beta download) is a voice
enabled address book for Win 95, Win 98, Win NT, Win CE, Pocket PC.
http://www.handheldspeech.com
xiii)IBM Software - Speech Recognition
Big
Blue's ViaVoice offerings in the desktop continuous speech
dictation arena. Competes with Dragon and Philips. Has mobile dictation and
telephony products as well. Has continuous speech
recognition for the Apple Macintosh
and Linux. Free Linux SDK.
http://www.software.ibm.com/speech/
xiv)IMSI
Software
IMSI
Utilities Group licenses IBM ViaVoice technology to produce their own line of
"VoiceDirect" dictation software.
http://www.imsisoft.com
xv)Mobilethink
Danish
startup specializing in developing mobile phone speech
solutions that are integrated with Internet information systems.
http://www.mobilethink.dk
xvi)MS
Agent Characters and Software
Microsoft
Agent based command and control uses voice to browse the web, receive email,
schedule appointments and participate in chat groups.
http://www.e-clips.com.au
xvii)Natural
Language Recognition
Simplis,
Inc, provides a Java based "natural language" speech
recognition interface designed to
simplify access to existing programs and web applications.
http://www.simplis.com/
xviii)Open Source Speech Recognition System
Carnegie
Mellon Sphinx project. Real-time continuous speech
recognition system. Downloadable
source.
http://fife.speech.cs.cmu.edu/sphinx/
xix)PGPfone
Pretty
Good Privacy internet phone allows encrypted talking over a network. MAC and PC
versions available.
http://web.mit.edu/network/pgpfone/
xx)Philips
Speech Processing
FreeSpeech
2000 is Philips' latest entry to the burgeoning continuous speech
dictation market. Although the software does not quite have the human factors
features of, say, Dragon, it does have multi-lingual recognition
for UK English, French, German, Spanish, Italian. Includes an SDK for speech
enabling custom applications.
http://www.speech.philips.com/
xxi)Scansoft
- Dragon Naturally Speaking
Acquired
Lernout & Hauspie, Dragon Systems speech
recognition and synthesis resources
and products. Also known for digital imaging products.
http://www.scansoft.com
xxii)Speak
Freely for Windows
An
Internet phone program for talking to someone PC-to-PC over a network, i.e., a
voice chat program. No banner ads. No phone charges. Has encryption hooks,
"answering machine," optional text chat, Unix/Linux versions. Also has
facility to run a phonebook addressing server so that you can find out who else
is on-line just like the "commercial" chat programs. Integrates with
ICQ
http://www.speakfreely.org/
xxiii)Speech
and Handwriting Recognition
Advanced
Recognition Technologies, Inc. -
designs, develops and distributes speech
and handwriting recognition software
products and technologies focusing on embedded software for cellular devices,
mobile communicators, and PDAs.
http://www.artcomp.com/
xxiv)Speech
FX
An
ongoing speech recognition
project for the Apple Macintosh, currently concentrating on enhancing command
and control.
http://software.accettura.com/products/speechfx/
xxv)Speech
Recognition for In-car Use
Germany
based BAhme Datentechnik deals in hands-free systems having echo and noise
cancellation features.
http://www.voice-recognition.de/english/start_engl.html
xxvi)Speech Technology Center
Russian
organization providing unusual variety of speech
processing products and services for research and development, speech
recognition, voice verification,
speaker identification, noise reduction in speech
signals, noise cancellation, forensic examination, audio analysis, logging and
communication channel protection.
http://www.speechpro.com
xxvi)Speech
Technology Magazine
Online
edition of the magazine, plus information on an annual 'SpeechTEK'
speech technology business
exposition.
http://www.speechtek.com/
xxvii)Talking Desktop
Speech
recognition, text-to-speech software transforms your Windows
computer into a conversational desktop companion. Provides dictation, web
navigation, voice Email, web cams, on-line news, weather maps, stock ticker, X10
home automation, MP3 music player & 3D avatar, disabilities features.
Project in progress.
http://www.talkingdesktop.com
xxviii)Unix
Speech Recognition
Special
Synapse TAP Workstation translates speech
into mouse events and keystrokes to control all environments - Unix, mainfame,
Mac etc. with speech recognition.
http://www.unixspeech.com
xxix)Voice
Applications, Inc.
Knowledgeable
and un-hyped web site explaining business applications of speech
and voice technology
http://www.voiceio.com
xxx)
Voice
Pilot
Software
attaches speech to e-mail. Demo
downloads.
http://www.voicepilot.com
xxxi)
Voice
Solutions for Warehouse and Manufacturing Environments
Guardian
Business Solutions, Inc. provides speech
software for business applications including voice warehouse picking and
inventory counting. Partnered with Syvox for warehouse applications; has own
software for the manufacturing arena.
http://www.gbsvoice.com
xxxii)Wizzard
Software
Desktop
command and control software with speech
recognition facilities. Useful tips
on getting better accuracy.
http://wizzards.gnc.net
3)
Speech Synthesis
This
category contains links for sites involved in speech synthesis, text to speech
processing or vendors selling such things.
i)Advanced
Technology and Research
Markets
a variety of speech products for industry including voiceprint, text to speech
and airport security systems. Good online text to speech demo.
http://www.atr.net/
ii)Analogue Speech Synthesizers
Comprehensive
site reviewing Vocoders and musical chorus synthesizers by EMS, Moog, Roland,
Korg, Electro Harmonics etc, talking chips (Votrax, TI) and speech recognition
hardware. Information site rather than sales.
http://web.inter.nl.net/hcc/davies/vocpage.htm
iii)
AT&T Natural Voices
AT&T
Labs Natural Voices featuring a line of speech synthesis products. Demos on the
site.
http://www.naturalvoices.att.com
iv)Babel
Techonologies
Multilingual
text to speech technologies for telecom, embedded and multimedia applications.
Available in 17 languages.
http://www.babeltech.com/
iv)Bell
Labs Text-to-Speech
Lucent
Technologies Bell Labs Text-to-Speech Synthesis demo.
http://www.bell-labs.com/project/tts/voices.html
v)Cepstral
Speech Synthesis
Small
footprint text-to-speech synthesis suitable for mobile, handheld, and wearable
computers. Provides a variety of voices and accents. Effective on line demo of
speech quality.
http://www.cepstral.com
vi)CompSpeak
2050
Institute
for the Study of Talking Computers and Oral Culture. The Institute's mission is
to study the social, cultural, and philosophical implications of talking
computers and voice recognition technology. Site taking orders for a
pre-publishing book having a provocative viewpoint on the impact of talking
computers.
http://www.compspeak2050.org
vii)CSLU Speech Synthesis
Center
for speech synthesis research, with demos and downloads available. Has a singing
voice synthesis project.
http://cslu.cse.ogi.edu/tts/index.html
viii)DEMOSTHeNES Speech Composer
DEMOSTHeNES
Speech Composer is a general-purpose multilingual and polyglot software
text-to-speech (TTS) system that supports the Greek language using a wide
variety of e-text sources. Free download has an open and component based
architecture allowing flexibility, customization and expandability.
http://www.di.uoa.gr/speech/synthesis/demosthenes/info_gb.shtml
ix)Desktop
Text to Speech Utility
CyberBuddy
- a freeware utility program that uses MicroSoft Agents to do Instant Messaging
with speech and animation, reminders, time of day, check email, news reports,
weather, stock quotes, text reading, and ICQ status reporting.
http://thecyberbuddy.com/
x)Digalo
TTS engine
Text-To-Speech
engine for Microsoft Agent and SAPI compliant applications. Available in 7
languages (French, German, Spanish, US English, British, Russian, Brazilian
Portuguese). Download free trial.
http://www.digalo.com
xi)e-rhetor
Develops
applications and systems that support the Greek language. Current products
include a series of high quality Text-to-Speech products for the
telecommunications and multimedia market.
http://www.e-rhetor.com
xii)E-Speech
Unusual text-to-speech
synthesis offerings including name pronunciation software for speech recognition
dictionaries and other custom applications.
http://www.espeech.com
xiii)Elan
Text to Speech
Elan
is a worldwide provider of advanced text-to-speech technology for automotive,
desktop and telecom on many platforms and environments. Interactive demo and
free download are available for evaluation of speech quality. Many languages
supported - American English, British English, German, French, Spanish, Italian,
Polish, Russian, Latin American Spanish and Brazilian Portuguese. Has Linux
offeri
http://www.elantts.com
xiv)Eloquent
Technology, Inc.
Offers
multi-language text-to-speech system that produces good-quality synthesized
speech with reasonable sounding voices and intonation.
http://www.eloq.com
xv)ESOPOS-Greek
TTS
An
unusual downloadable program for Win 95/98 that does Greek text-to-speech
processing.
http://esopos.ee.auth.gr
xvi)Festival Speech Synthesis Systems
A
speech synthesis system for Unix and Windows from University of Edinburgh.
English, Spanish and Welsh languages supported. Free download.
http://www.cstr.ed.ac.uk/projects/festival/
xvii)Fonix
Corporation
Text-to-speech
vendor with demo. Free clock application download for PC.
http://www.fonix.com
xviii)Fonix
SpeakThis
Subscription
service that lets you add speech to your website using automatically generated
HTML you paste into your pages. Support for many voices and languages.
http://www.speakthis.com
xix)FreeTTS - Java speech synthesis
A
speech synthesis system written entirely in the Java(TM) programming language.
Based upon Flite: a smallrun-time speech synthesis engine developed at Carnegie
Mellon University and derived from the Festival Speech Synthesis System from the
University of Edinburgh and the FestVox project from Carnegie Mellon University.
http://freetts.sourceforge.net
xx)French speech synthesis
LAIPTTS
is a high-quality speech synthesis for French. Freely downloadable for
non-commercial purposes. Small footprint of 350k. Online synthesis demo
http://www.unil.ch/imm/docs/LAIP/LAIPTTS.html
xxi)German
speech synthesis
Speech
synthesis group at the IMS, University of Stuttgart, Germany: Online demo,
speaking metro information system, various speech synthesis example sand some
downloads. Research is concentrating on getting good prosidy (inflection).
http://www.ims.uni-stuttgart.de/phonetik/synthesis/
xxii)InfoQuick
Software Technology Corp.
Focus
on speech technology research and development in Chinese language, including TTS
and ASR.
http://www.infoquick.com.cn
xxiii)Infovox
Synthetic Speech
Text
to speech for American and British English, Dutch, French, German, Italian,
Spanish, Swedish, Norwegian, Danish, Finnish and Icelandic. Interfaces for MS
Windows, Dos, Apple Mac.
http://www.infovox.se
xxiv)Java
Applet for Speech Synthesis
Java
applet/software for speech synthesis using the concatenation method. Currently
developing formant synthesis version.
http://www.say-it-now.com
xxv)JustSpeak
Text
to speech system converts any readable computer text into speech and MP3 files.
Free online demo.
http://www.justspeak.com
xxvi)Key2Speak
Key2Speak
uses speech synthesis technology to read aloud what you type, as you type it.
For Microsoft Windows.
http://www.key2speak.com
xxvii)Mindmaker
Sells
FlexVoice (TM), a text-to-speech (TTS) engine. Online demo shows good prosidy.
http://www.flexvoice.com/
xxviii)RC
Systems
Text
to speech synthesis products. Boards, modules, and chips. Downloadable data
sheets and product information.
http://www.rcsys.com
xxix)Reading Machine
Reads
text aloud using text-to-speech, converts text into mp3/wave files for use with
any cd player or mp3 player. Extracts text from one web page or whole web sites.
Text is automatically organized into books and chapters for later use. Gives
control over the voice, and the ability to cleanup text automaticaly.
http://www.ultimatereadingmachine.com
xxx)ReadPlease
Text-to-speech
software for Windows 9x/ME/NT/2K/XP. Freeware and commercial versions.
http://www.readplease.com/
xxxi)Rhetorical Systems
Builds
high-quality voices, which in many applications are indistinguishable from the
real voices on which they are modeled. The core product, rVoice, has a wide
range of synthesized voices including several regional accents and speaking
styles. Impressive demo on site.
http://www.rhetoricalsystems.com
xxxii)Sakrament
Speech
recognition and synthesis software company, particularly Russian language.
http://www.sakrament-speech.com
xxxiii)Spanish TTS Systems for Windows
Extracts
text from one web page or whole web sites. Text is automatically organized into
books and chapters for later use. Gives control over the voice and text cleanup.
http://www.internethablado.com
xxxiv)Speaker
- Text to Speech for Konqueror
A
text to speech plug in for the KDE desktop file manager under Linux.
http://dogma.freebsd-uk.eu.org/~grrussel/speaker.html
xxxv)Speech Synthesis Markup Language
The
current version of the (draft) proposal for an XML-based Speech Synthesis Markup
Language, as part of the W3C's Speech Interface Framework. This is an industry
standard in the making.
|
