Links
for developers of speech recognition, speech synthesis software. Focus is DLL's,
libraries, components and building blocks for larger applications
I) Audio
search SDK
Compure
has developed Speak&Find, a software technology with a C/C++ API which
allows you to search for keywords or phrases in stored audio data (audio mining)
including a rough transcription of the sound file. SDK allows easy integration
of various audio functionalities and technologies.
http://www.compure.com
ii)Audium
Corporation
Provider
of dynamic voice applications integrating VoiceXML, speech recognition, and
business logic. Free trial of Voice Foundation Classes available for download.
http://www.audiumcorp.com
iii)CSLU Toolkit
A
comprehensive suite of tools to enable exploration, learning, and research into
speech and human-computer interaction. Very impressive, includes facial
animation.
http://cslu.cse.ogi.edu/toolkit/
iv)CTMaker
Real-time
application generator for unified messaging systems; supports TAPI, SAPI,
sharing information between SQL-databases, emails, web-pages, phones, pagers.
Allows development of CTI applications.
http://www.ctmaker.com
v)DDLinux Speech Recognition Mailing List
Site
contains list of speech recognition tools and projects for Linux.
http://leb.net/archives/ddlinux/
vi)Digicleen
Offers
software (DLLs) for noisy environments to improve speech recognition in
dictation, commands, speaker identification. Also hands free cell phone,
headset, desktop, array noise cancelling microphones.
http://www.digicleen.com/Speech_Recognition.html
vii)Engineered
Station
Pakistani
Electrical Engineer offers basic level of information for implementing speech
enabled applications using TAPI, MAPI and WAPI. A starter site for students and
beginners.
http://project.uet.itgo.com
viii)HTK3
- Hidden Markov Toolkit
Development
and distribution site for HTK3, a hidden markov toolkit designed for speech
recognition. HTK3 is available for free download as C source. Used at hundreds
of research sites world wide.
http://htk.eng.cam.ac.uk
ix)IBM
ViaVoice SDK for Linux
Free
download of the ViaVoice speech recognition (ASR) SDK available here. Also
included in RedHat Linux 6.0 (see Application CD). Tech support available by
e-mail along with user group digest. New sample apps continue to be posted.
Great fun for Linux buffs.
http://www-4.ibm.com/software/speech/dev/sdk_linux.html
x)Interactive Speech Technologies
Provides
free plugin for website designers which allows visitors to surf the site by
voice.
http://www.interactivespeech.com
xi)Lucent Speech Solutions
Provider
of leading-edge speech recognition, text-to-speech, and VoiceXML solutions for
voice portal companies, speech application developers, OEMS, and service
providers.
http://www.lucentssg.com/speech
xii)Natlantech
Natlantech
develops and distributes software for speech analysis, speech recogniion and
Natural Language processing.
http://www.natlantech.com
xiii)Nellymoser,
Inc.
Specializes
in speech and audio technologies for wired and wireless networks. Variety of
image, speech, motion and pattern recognition SDK's.
http://www.nellymoser.com
xiv)NeuVoice
Ltd
Provides
a high-accuracy, small foot-print and noise-robust speech recognition systems,
ideal for command and control in noisy environments especially mobile and hand
held devices.
http://www.neuvoice.com
xv)PhantomSpeech
PhantomSpeech
is a speech engine independent TTS component built on the COM specification
providing the same set of APIs for accessing any speech engine. An attempt to
provide a universal standard for Text to Speech conversions. Free download.
http://www.geocities.com/deva_raja1/index.html
xvi)Simplified
Speech Toolkit for the Web
Information,
software, and support for developing applications, web or otherwise, that you
talk with using speech recognition and speech synthesis from Chant Inc
http://www.speechkit.com
xvii)SpeakMed - Medical Vocabularies
Special
medical vocabularies for Dragon NaturallySpeaking. Support US, British, Indian
and SE Asian accents.
http://www.dragonsys.ca/docs/speakm.htm
xix)Speech
Filing System - Tools for Speech Research
SFS
provides a computing environment for conducting research into the nature of
speech. It comprises free software tools; special file and data formats;
subroutine libraries for I/O, signal processing and graphics; use and
documentation standards; and special programming languages.
http://www.phon.ucl.ac.uk/resource/sfs/
xx)Speech
Recognition Kit
Sensory,
Inc. provides low-cost speech recognition technologies for consumer products for
the embedded speech recognition market and also offers a software solution for
DSPs and microcontrollers.
http://www.sensoryinc.com
xxi)Speech
Recognition Resources
Comprehensive
listing of speech recognition resources including integration tools for software
developers
http://www.tiac.net/users/rwilcox/speech.html#SDT
xxii)Speech Solutions, Inc.
Develops,
markets and supports speech recognition software tools. These tools enable
developers to rapidly integrate speech recognition technology into new or
existing software programs - including websites.
http://www.speechsolutions.com
xxiii)SpeechStudio
Suite
A
software toolset to develop, test, refine, deploy and maintain a speech
recognition interface on Microsoft Windows (SAPI 5.0). Takes much of the
difficulty and detail out of programming at the API level.
http://www.SpeechStudio.com
xxiv)TalkSoft
Corporation
TalkSoft
provides speech recognition software for embedded applications, such as
hand-held devices with voice user interfaces. Software-only engine performs
speaker-independent, continuous speech recognition in real time for Windows,
Windows CE, Linux, Macintosh, and most popular embedded microprocessors.
http://www.talksoft.com
xxv)VoiceClient
VoiceClient
is a speech enabled eMail solution based on VoiceXML. Due to VoiceXML and in
contrast to Unified Messaging Solutions the VoiceClient can be easily integrated
into open speech environments and existing messaging solutions.
http://www.voiceclient.com
xxvi)Voxi
A
Swedish startup which develops and licenses a general-purpose software platform
for Intelligent Speech Interfaces (TM), involving speech recognition, language
understanding, and high-quality audio feedback
http://www.voxi.com/
|