|
|
| Home > Software > comp-speech-faq > |
comp.speech Frequently Asked Questions - part 3/3 |
Section 1 of 7 - Prev - Next
All sections - 1 - 2 - 3 - 4 - 5 - 6 - 7
Archive-name: comp-speech-faq/part3
Last-modified: 1998/07/06
URL: http://www.speech.su.oz.au/comp.speech/
COMP.SPEECH FAQ POSTING - PART 3/3
[Note: this document has been automatically extracted from a WWW site:
http://www.speech.su.oz.au/comp.speech/
This may introduce some formatting errors.]
Speech Synthesis
comp.speech FAQ Section 5
* SpeechLinks: Speech Synthesis
* Q5.1: What is speech synthesis?
* Q5.2: How can speech synthesis be performed?
* Q5.3: References/Books on Synthesis
* Q5.4: Speech Synthesis on the WWW
* Q5.5: Speech Synthesis Software/Hardware
___________________________________________________________________________
Q5.1: What is speech synthesis?
Speech synthesis programs convert written input to spoken output by
automatically generating synthetic speech. Speech synthesis is often
referred to a "Text-to-Speech" conversion (TTS).
___________________________________________________________________________
Q5.2: Performing speech synthesis
There are several algorithms. The choice depends on the task they're
used for. The easiest way is to just record the voice of a person
speaking the desired phrases. This is useful if only a restricted
volume of phrases and sentences is used, e.g. messages in a train
station, or schedule information via phone. The quality depends on the
way recording is done.
More sophisticated but worse in quality are algorithms which split the
speech into smaller pieces. The smaller those units are, the less are
they in number, but the quality also decreases. An often used unit is
the phoneme, the smallest linguistic unit. Depending on the language
used there are about 35-50 phonemes in western European languages,
i.e. there are 35-50 single recordings. The problem is combining them
as fluent speech requires fluent transitions between the elements. The
intellegibility is therefore lower, but the memory required is small.
A solution to this dilemma is using diphones. Instead of splitting at
the transitions, the cut is done at the center of the phonemes,
leaving the transitions themselves intact. This gives about 400
elements (20*20) and the quality increases.
The longer the units become, the more elements are there, but the
quality increases along with the memory required. Other units which
are widely used are half-syllables, syllables, words, or combinations
of them, e.g. word stems and inflectional endings.
The Museum of Speech Analysis and Synthesis has pictures of artificial
speech systems going back over 150 years: worth a visit. (
http://mambo.ucsc.edu/psl/smus/smus.html)
___________________________________________________________________________
Q5.3: References/Books on Synthesis
Books and Papers
* Thierry Dutoit, An Introduction to Text-to-Speech Synthesis,
Kluwer Academic Publishers (Dordrecht), 1997, ISBN 0-7923-4498-7,
312 pages. Volume 3 in the series on Text, Speech and Language
Technology.
* Douglas O'Shaughnessy, Speech Communication: Human and Machine
Addison Wesley series in Electrical Engineering: Digital Signal
Processing, 1987.
* T.V. Raman, Auditory User Interfaces --Toward The Speaking
Computer Kluwer Academic Publishers, Boston, ISBN 0-7923-9984-6,
August 1997, 168 pp.
* D. H. Klatt, "Review of Text-To-Speech Conversion for English",
Jnl. of the Acoustic Society of America (JASA), Vol 82, pp
737-793.
* "Talking Machines, Theories, Models and Designs" Eds, G. Bailly &
C. Benoit (Elsevier: North Holland)
* I. H. Witten. Principles of Computer Speech, London: Academic
Press, Inc., 1982.
* W.B. Kleijn and K.K. Paliwal (Eds.), Speech Coding and Synthesis,
Elsevier, Amsterdam, 1995.
Contents, preface etc on the WWW:
http://www.elsevier.nl/section/engtech/scs/menu.htm
* John Allen, Sharon Hunnicut and Dennis H. Klatt, "From Text to
Speech: The MITalk System", Cambridge University Press, 1987.
* J.P.H. van Santen, R. W. Sproat, J. P. Olive, and J. Hirschberg,
"Progress in Speech Synthesis", Springer, 1996.
On the WWW
* Survey of the State of the Art in Human Language Technology
Report edited by Ronald A. Cole et. al. with a section on
Text-to-Speech Technologies.
http://www.cse.ogi.edu/CSLU/HLTsurvey/ch5node1.html
Bibliographies and Reference Lists
* WWW searchable online-bibiliography for Phonetics and Speech
Technology with more than 8000 entries. Provided by Institut fur
Phonetik at Johann Wolfgang Goethe-Universitat Frankfurt.
http://www.uni-frankfurt.de/~ifb/bib_engl.html
* Computational Speech Processing: Speech Analysis, Recognition,
Understanding, Compression, Transmission, Coding, Synthesis ; Text
to Speech Systems, Speech to Tactile Displays, Speaker
Identification, Prosody Processing : BIBLIOGRAPHY, by Conrad F.
Sabourin, 1994, 2 volumes, 1187p, ISBN 2-921173-21-2, INFOLINGUA
inc., P.O. Box 187 Snowdon, Montreal, H3X 3T4, Canada.
See also: http://gomer.mlink.net/infolingua.html
___________________________________________________________________________
Q5.4: Speech Synthesis on the WWW
Most of the following are links to WWW pages with demonstrations of
speech synthesis. Plenty more links are included in the detailed list
of speech synthesis software/hardware in Q5.5.
Speech Synthesis "Museum"
URL: http://www.cs.bham.ac.uk/~jpi/synth/museum.html
Maintained by Jon Iles (j.p.iles@cs.bham.ac.uk) at the
University of Birmingham.
Information and speech samples for
+ YorkTalk
+ Loughborough Sound Images
+ University of Birmingham - FDFS
+ Eurovocs
+ DECtalk
+ AT&T Bell Labs Synthesiser
+ S.W.A.Ll.C. - Welsh Synthesis from CSTR
+ All-Prosodic Speech Synthesis - IPOX
+ Orator from Bellcore
The Festival Speech Synthesis System
http://www.cstr.ed.ac.uk/projects/festival.html
Pre-synthesized examples in English, Welsh and Spanish, and
online demo of English.
Pavarobotti
http://www.shc.uiowa.edu/fun/pavarobotti/pavarobotti.html
WWW demo of the Pavarobotti synthesis technology developed at
the National Center for Voice and Speech
(http://www.shc.uiowa.edu/ncvs_home.html).
Say...
http://wwwtios.cs.utwente.nl/say
WWW demo of the rsynth speech synthesis software. The WWW
capability was implemented by Axel Belinfante.
Musee sonore de la synthese de la Parole en francais
http://www.icp.grenet.fr/exemples_synthese/ex.html
Speech synthesis examples from a series of French language
speech synthesisers plus links to other speech synthesis demo
pages.
+ ICP-Grenoble
+ CNET-Lannion (with TD-PSOLA)
+ KTH-Stockholm
+ Universite-Mons - several versions
Lucent Technologies Bell Labs Text-to-Speech
http://www.bell-labs.com/project/tts/
Demos and samples of the latest Lucent Technologies Bell Labs
Text-to-Speech system.
WATSON FlexTalk from AT&T Advanced Speech Products Group
http://www.att.com/aspg/demo.html
WWW interface to the WATSON FlexTalk speech synthesis
demonstration.
AT&T Bell Laboratories Voices
http://www.research.att.com/cgi-bin/cgiwrap/mjm/voices.cgi
WWW interface to the AT&T Bell Laboratories text to speech
(TTS) synthesizer
Laureate from British Telecom
http://www.labs.bt.com/innovate/speech/laureate/
Demo of the Laureate speech synthesis system - not yet
commercially available.
ORATOR from Bellcore
Online demo of the ORATOR system developed at Bellcore.
http://www.bellcore.com/ORATOR/
SVOX from TIK, ETH in Zurich
http://www.tik.ee.ethz.ch/cgi-bin/w3svox
Demo of German speech synthesis from Institut fur Technische
Informatik und Kommunikationsnetze.
Speech Synthesis Research at OGI
http://www.cse.ogi.edu/CSLU/research/TTS
Examples of diphone speech corpora and algorithms developed at
OGI for synthesis of American English and Mexican Spanish using
the Festival framework.
Lyricos
http://www.cse.ogi.edu/CSLU/research/TTS/research/sing.html
Demos of the Lyricos singing voice synthesis system.
Concatenation-based synthesis of singing voice from MIDI input.
Multi-Lingual TTS from Gerhard-Mercator University, Duisburg
http://www.fb9-ti.uni-duisburg.de/demos/speech.html
Synthesis in German, English or Japanese.
TMH: Institutionen for Taloverforing och Musikakustik, Kungliga
Tekniska Hogskolan
http://www.speech.kth.se/info/software.html
Synthesis in Swedish, Finish, Norwegian, Icelandic, Danish,
British and American English, French, German, Italian, Spanish,
LA Spanish and Greek.
Haskins Laboratory WWW Site
http://www.haskins.yale.edu/Haskins/MISC/special.html
Examples of several types of speech synthesis. Articulatory
Synthesis by HyperASY. SineWave Synthesis. Gestural
Computational Model. Pattern Playback system of the 1940's!
BeSTspeech from Berkeley Speech Technologies, Inc., (BST)
http://www.bestspeech.com/weblang.html
Eurovocs Multilingual Speech Synthesis
http://www.elis.rug.ac.be/ELISgroups/speech/research/eurovocs.h
tml
Based on Lernout and Hauspie technology.
HADIFIX German Speech Synthesis
http://asl1.ikp.uni-bonn.de/~tpo/Hadiq.en.html
Provided by the Instituts fur Kommunikationsforschung und
Phonetik, Universitat Bonn.
Centigram's TruVoice Demo
http://www.centigram.com/centigram/TruVoice/index.html
Allows control of speech rate, pitch and other prosodic
charateristics.
MBROLA: Free Speech Synthesis Project
http://tcts.fpms.ac.be/synthesis/modelcmp.html
WWW demo of MBROLA which compares the quality of PSOLA,
MBR-PSOLA, LPC, and Hybrid Harmonic/Stochastic concatenative
synthesizers. Provided by the TCTS Lab, Faculti Polytechnique
de Mons, Belgium
Institute of Phonetic Sciences
http://fonsg3.let.uva.nl/IFA-Features.html
Links to lots of on-line speech synthesis demonstrations
provided by the Institute of Phonetic Sciences of the Faculty
of Arts of the University of Amsterdam.
Yahoo page on speech generation
http://www.yahoo.com/Science/Computer_Science/Artificial_Intell
igence/Natural_Language_Processing/Speech_Generation/
___________________________________________________________________________
Q5.5: Speech Synthesis Software/Hardware
Please email any updates, corrections or additions to the following
list. The range of commercially available synthesis software is
growing rapidly so any help in keeping up to date will be appreciated.
Other lists of speech synthesis software on the WWW include:
Kevin Lenzo's list of Macintosh Speech Resources and Apps
http://www.cs.cmu.edu/~lenzo/mac_speech_apps.html
Speech Toys Speech Synthesis Information
http://www.speechtoys.com/spchtoys/spsyn.html
In the FAQ...
The following speech recognition software/hardware is described in the
comp.speech FAQ.
_Apple Macintosh_
* BeSTspeech from Berkeley Speech Technologies, Inc., (BST)
* Infovox Product Range
* Macintosh Speech Output Applications
* Macintosh Speech Synthesis Manager
* MacYack Pro
* MBROLA: Free Speech Synthesis Project
* ProVoice Developer's Speech Toolkit from First Byte
* SENSYN speech synthesizer
* Sound Bytes DeveloperUs Kit
* Macintosh Speech Synthesis Manager
_Windows (including 95, NT, 3.1)_
* AcuVoice
* AT&T Watson Speech Synthesis
* BeSTspeech from Berkeley Speech Technologies, Inc., (BST)
* Creative TextAssist and TextAssist API
* DECtalk: Text-to-Speech from Digital
* ETI-Eloquence
* HADIFIX
* Infovox Product Range
* IPOX: All Prosodic Speech Synthesis Architecture
* Lernout and Hauspie Text-To-Speech Windows SDK
* Listen2 Text Reader
* MBROLA: Free Speech Synthesis Project
* Monologue for Windows from First Byte
* PAM - A Text-To-Speech Application
* ProVerbe Speech Engine from ELAN Informatique
* ProVoice Developer's Speech Toolkit from First Byte
* SENSYN speech synthesizer
* Sound Bytes DeveloperUs Kit
* Tinytalk
* TruVoice from Centigram
* WinSpeech
* ZMD Speech Synthesis
_DOS_
* CSRE: Computerized Speech Research Environment
* Infovox Product Range
* MBROLA: Free Speech Synthesis Project
* ProVoice Developer's Speech Toolkit from First Byte
* SENSYN speech synthesizer
* spchsyn.exe
* Tinytalk
* ZMD Speech Synthesis
_OS/2_
* ProVerbe Speech Engine from ELAN Informatique
* ProVoice Developer's Speech Toolkit from First Byte
* Sound Bytes DeveloperUs Kit
_Unix_
* AcuVoice
* AsTeR
* BeSTspeech from Berkeley Speech Technologies, Inc., (BST)
* DECtalk: Text-to-Speech from Digital
* ETI-Eloquence
* Emacspeak - A Speech Output Subsystem For Emacs
* Festival Speech Synthesis System
* JSRU
* Klatt-style synthesiser
* KPE80 - A Klatt Synthesiser and Parameter Editor
* "learph": Trainable text-to-phoneme software by Antonio Lucca
* Lucent Technologies Bell Labs Text-to-Speech system
* MBROLA: Free Speech Synthesis Project
* Orator from Bellcore
* ProVerbe Speech Engine from ELAN Informatique
* rsynth
* SENSYN speech synthesizer
* SGI Developers Toolbox Synthesiser
* Speak
* TrueTalk
* TruVoice from Centigram
_Integrated Circuits and Dedicated Hardware_
* Eurovocs
* Infovox Product Range
* ProVerbe Speech Engine from ELAN Informatique
* RC Systems V8600/V8601 Text to Speech synthesizers
_Other Platforms_
* BeSTspeech from Berkeley Speech Technologies, Inc., (BST)
* TheBigMouth (NeXT)
* MBROLA: Free Speech Synthesis Project
* Narrator Translator Library (Amiga)
* Narrator (Amiga)
* TextToSpeech Kit (NeXT)
* Orator from Bellcore
* SENSYN speech synthesizer
* WreadFiles: File reader for Commodore Amiga
_Unknown_
* Lernout and Hauspie Text-To-Speech (3 products)
* SIMTEL
* Text to Phoneme Program 1
* Text to phoneme program 2
* Text to phoneme program 3
AcuVoice
* Platform: Windows, Solaris
* Description: AcuVoice is a natural sounding text-to-speech system
built using a concatenative approach. Currently it is available
for an American English Male Voice. Software Developer Kits are
available for the Windows Platform (32-Bit) and also for the
Solaris Platform. More information and samples are available on
the Acuvoice web site.
* Contact: AcuVoice, Inc.
84 W. Santa Clara Street, Suite 720, San Jose, CA 95113-1810
Ph: 1(408)289-1661, Fax: 1(408)289-1201
Demo: 1(408)289-1177
Email: AcuVoice1@AOL.COM
WWW: http://www.acuvoice.com/
AsTeR
* Platform: UNIX
* Description: TTS front-end program which encodes structural
information about documents in speech synthesis. For more
information check out:
http://www.research.digital.com/CRL/personal/raman/aster/
aster-toplevel.html
* Operation requirements: Lisp: Lucid, clisp
* Contact: T. V. Raman
WWW: http://www.research.digital.com/CRL/personal/raman/raman.html
Email: raman@adobe.com
AT&T Watson Speech Synthesis
* Platform: Windows 95/NT on a Pentium 75 Mhz or higher
* Description: Watson is a software implementation of AT&T Bell
Laboratories voice processing technology. Watson includes BLASR
Speech Recognition (see Q6.6) and FlexTalk speech synthesis. It
requires no special hardware to run other than a standard sound
card and/or phone card. Technical details for the FlexTalk speech
synthesis include:
+ Compliant with MS Speech API.
+ Male and Female Voices available
+ 8 KHz and 11 KHz output
+ SoundBlaster compatible sound card and drivers required
+ Context sensitive abbreviation expansion
+ Accurate pronunciation of most proper names
+ Adjustable vocal tract size, speed, volume, pitch, etc.
+ American English only - other languages in development
The AT&T Advanced Speech Products Group home page provides more
detailed information including a Frequently Asked Questions list,
information for application developers on the Independent Software
Vendor (ISV) Program (including info on the SDK, licensing, and
the training program).
* Requirements: Uses 2 MB RAM, 10 MB Disk. Requires a Pentium 75 MHz
or higher (uses
* Cost and Availability: WATSON is a software-based speech platform
with a Software Developers Kit (SDK) that allows application
developers to use voice processing in their applications. It is
not available as a stand-alone product.
Licensing information (inc. price) is provided in the AT&T
Advanced Speech Products Group home page
* See also: Watson BLASR speech recognition in Q6.5, Microsoft
Speech API, and Advanced Speech API.
* Contact: AT&T Advanced Speech Products Group
Suite 700, 44 East Mifflin Street, Madison, WI 53703, USA
Ph: 1-800-5-WATSON, Fax: 1-608-259-2269
Email: aspg@attmail.com
WWW: http://www.att.com/aspg/
BeSTspeech from Berkeley Speech Technologies, Inc., (BST)
* Platform: available for Macintosh, Sun, Silicon Graphics, Windows
PC and IBM RS/6000 platforms, and can be ported to others.
* Description: BeSTspeech reads ASCII text no vocabulary limits.
Available for Dutch, English (male and female), French, German,
Italian, Portuguese, Spanish, Arabic, Cantonese, Japanese, Korean,
Malay, Mandarin and Russian.
* Availability: Berkeley Speech Technologies, Inc does not sell end
user toolkits or products.
* Contact: Berkeley Speech Technologies, Inc.
2246 Sixth Street, Berkeley, California 94710, USA
Ph: (510) 841-5083, Fax: (510) 841-5093
Email: webmaster@bst.com
WWW: http://www.bestspeech.com/index.html
TheBigMouth - a Text to Speech Program
* Platform: NeXT
* Description: Text to speech program based on concatenation of
pre-recorded speech segments.
* Availability:
ftp://ftp.cs.keio.ac.jp/pub/NeXT/source/TheBigMouth1.0.tar.Z
Creative TextAssist
* Platform: Windows
* Description: Based on DECtalk speech synthesis. A detailed
description of TextAssist is provided on the Creative WWW pages.
TextAssist TextReader provides a convenient Windows user interface
for text reading.
* Availability: Creative TextAssist is bundled with most (all?)
Creative Sound Blaster audio cards. TextAssist preview software is
available from the Creative Labs TextAssist home page.
* Contact: Creative Labs, Inc.
Address, phone, email etc unknown
WWW: http://www.creaf.com/ :
http://www.creaf.com/wwwnew/tech/devcnr/tassist.html
Creative TextAssist API
* Platform: Windows
* Description: The TextAssist API (TAAPI) is created for Microsoft
Windows 3.1x and Windows 95 developers who intend to develop
16-bit Text-to-Speech software applications using Creative's
TextAssist speech engine. It supports direct control of speech
output characteristics, concurrent playback of text-to-speech and
wave files, foreign language support, speech synchronization,
exception dictionaries. It also includes a voice editing tool for
creating new custom voices, a Visual Basic Custom Control for
high-level support in Visual Basic and other languages
* Availability: The TextAssist API is released to registered
developers at no cost.
* Contact: WWW: http://www.creaf.com/
FAQ: http://www.creaf.com/wwwnew/tech/devcnr/tassfaq.html
CSRE: Computerized Speech Research Environment
* Platform: DOS
* Description: CSRE is a software system which includes in an
implementation of the Klatt speech synthesizer. See the CSRE entry
in Q1.9 and the AVAAZ WWW pages for more detail.
* Contact: AVAAZ Innovations Inc.
P.O.Box 8040, 1225 Wonderland Rd. N, London, Ontario, CANADA, N6G
2B0
Ph: +1-519-472-7944 , Fax: +1-519-472-7814
Email: info@avaaz.com
WWW: http://www.icis.on.ca/homepages/avaaz/
DECtalk Speech Synthesis
* Platform: Windows NT, Alpha with Digital UNIX and RS232 ports
* Description: Converts ordinary text into natural-sounding,
intelligible speech. Provides personalized voices, and extensive
user controls. DECtalk technology is available for the following
packaging options.
+ DECtalk PC card option: An industry-standard ISA/EISA bus
card implementation that can be integrated with any Intel 486
processor-based system running DOS or Windows. Applications
can be interfaced to the bus via a DOS Terminate and Stay
Resident (TSR) driver or a Windows Dynamic Link Library
(DLL). This option is available with an external speaker with
volume control and headphone jack.
+ DECtalk Express external package: An external, portable
package that you can plug in to any PC or serial port. The
external package includes a built-in speaker and headphone
jack, plus combined on/off and volume controls and a
rechargeable battery pack.
+ DECtalk Software solution: Software-only text to speech for
Alpha or Intel systems running Windows NT or Alpha systems
running Digital UNIX. Provides complete speech synthesis
capabilities so developers can enhance applications with
DECtalk technology. DECtalk Software output can be directed
to audio devices, into WAVE files, or into memory buffers.
* Pricing:
://www.systems.digital.com/DIcatalog/html/DECtalk-Speech-Synthesis
-oi.html
* More Information:
Digital Equipment Corporation WWW pages: http://www.digital.com/
DECtalk page:
http://www.systems.digital.com/DIcatalog/html/DECtalk-Software.htm
l
Ph: 1-800-DIGITAL
DECtalk Software
* Platform: Digital UNIX and Windows NT
* Description: DECtalk converts standard ASCII text into natural,
intelligible speech. Speech output through any audio device is
supported by Microsoft Video for Windows or Multimedia Services
for Digital UNIX. An API gives developers direct access to
text-to-speech functions. Provides nine voice personalities (4
female, 4 male, 1 child). Provides punctuation and tonal control,
supports customized pronunciation of trade jargon and acronyms.
Common programming interface works with both Alpha and Intel
platforms.
* More Information:
Digital Equipment Corporation WWW pages: http://www.digital.com/
DECtalk Software page:
http://www.systems.digital.com/DIcatalog/html/DECtalk-Software.htm
l
WWW:
http://www.systems.digital.com/DIcatalog/html/DECtalk-Speech-Synth
esis.html
Ph: 1-800-DIGITAL
ETI-Eloquence
* Platform: MS Windows (Win95,NT,3.1), Solaris, SunOS, SGI, RS/6000
* Description: ETI-Eloquence is a software based text-to-speech
system. It generates waveforms completely algorithmically instead
of by concatenating waveforms, for maximum flexibility and
naturalism. For instance, when the user requests a deeper voice,
the software simulates a larger vocal tract, instead of simply
pitch-shifting samples. It uses high-level linguistic parsing,
which obviates the need for a huge dictionary. It handles numbers,
acronyms, currency, etc. It includes a set of annotation symbols,
for placing stress on particular words, expressing
excitement/boredom, etc. Also allows phonetic input. Supports MS
SAPI.
Produces male and female voices for General American English.
Dialects under development include Alabama and Brooklyn.
* Price: Flexible license agreements on application.
* Availability:Eloquent Technology, Inc.
2389 North Triphammer Road, Ithaca, NY 14850 , USA
Ph: (607) 266-7025, Fax: (607) 266-7030
Email: info@eloq.com
WWW: http://www.eloq.com/
Emacspeak - A Speech Output Subsystem For Emacs
* Platform: UNIX, Emacs
* Description: Emacspeak is a speech output system that will allow
someone who cannot see to work directly on a UNIX system.
Emacspeak is built on top of Emacs. With emacspeak loaded, Emacs
provides spoken feedback for everything you do. Emacspeak
currently supports the new Dectalk Express speech synthesizer, as
well as older versions of the Dectalk e.g. the MultiVoice. See the
Emacspeak WWW page, the Emacspeak FAQ or the Emacspeak
distribution for additional details.
* Requirements: Requires GNU FSF Emacs 19 (version 19.23 or later)
and TCLX 7.3B (Extended TCL) to run Emacspeak.
* Availability:
Emacspeak WWW page
http://www.research.digital.com/CRL/personal/raman/emacsp
eak/emacspeak.html
Emacspeak source
http://www.research.digital.com/CRL/personal/raman/emacsp
eak/emacspeak.tar.gz
* Contact: T. V. Raman, raman@adobe.com
Eurovocs
* Platform: Various - RS232 hardware connection
* Description: Eurovocs is a stand-alone text-to-speech synthesizer
which uses the text-to-speech technology of Lernout and Hauspie
Speech Products. Available for Dutch, French, German and American
English with other languages planned for release soon. One
Eurovocs device can support two different languages. Eurovocs can
be connected to any computer via a standard serial interface
(RS232). It supports personal dictionaries, generation of DTMF
tones, and pronunciation of special character sequences such as
digit strings, telephone-numbers, date and time indications,
abbreviations, alphanumeric strings etc.
* Contact: Technologie & Revalidatie
Postbus 128, B-9000 Gent, Belgium
Ph: +32-9-264 33 97, Fax: +32-9-264 35 94
E-mail: noe@elis.rug.ac.be
WWW:
http://www.elis.rug.ac.be/ELISgroups/speech/research/eurovocs.html
Festival Speech Synthesis System
* Platform: General Unix (including Solaris (2.4,2.5), SunOS, HPUX,
SGIs, Linux, Dec Alpha, FreeBSD)
* Description: Festival is a general multi-lingual speech synthesis
system developed at CSTR, University of Edinburgh. It offers a
full text to speech system with various APIs, as well an
environment for development and research of speech synthesis
techniques. It is written in C++ with a Scheme-based command
interpreter for general control. Festival's home page offers
demos, the full manual and access to the download page. The
distribution includes full source and documentation, and lexicons
and speech databases for British English text to speech.
* Price: Free for non-commercial use
* Availability: by anonymous ftp:
WWW: http://www.cstr.ed.ac.uk/projects/festival/download.html
ftp: ftp://ftp.cstr.ed.ac.uk/pub/festival/
HADIFIX
* Platform: Windows
* Description: German speech synthesis system developed at the
Institute for Communications Research and Phonetics , University
of Bonn. Provides conversion of input text to phonemes, automatic
prediction of stress, phrasing and pitch, and speech generation by
concatenation of small units of natural speech. Demisyllables and
similar units are used; they comprise all consonants before the
vowel and the beginning of the vowel (initial demisyllable) or the
end of the vowel and the following consonants (final
demisyllable). For example, the word 'Strolch' is formed by
concatenating 'Stro' and 'olch'.
* Demo: Windows demo software available. Limited to synthesis of one
short text (text.txt) at a time. Speech format limitations too.
1.3MB file.
ftp://asl1.ikp.uni-bonn.de/pub/hadifix/hadidemo.zip
A 1993 version is available with unlimited synthesis from a string
of phonemic symbols and accent markers. 6MB file.
ftp://asl1.ikp.uni-bonn.de/pub/hadifix/hadi25.lzh
* WWW: http://asl1.ikp.uni-bonn.de/~tpo/Hadifix.en.html
* On-line demo: http://asl1.ikp.uni-bonn.de/~tpo/Hadiq.en.html
Infovox Product Range
* Description: Multilingual Text-to-speech systems, languages
available: American English, British English, German, French,
Spanish, Italian, Swedish, Norwegian, Icelandic, Danish and
Finnish.
* Product name:INFOVOX 500, PC BOARD
+ Product description: Half length expansion board for IBM PC,
XT, AT, PS/2 model 30 or compatible personal computers. The
board can also be connected via the serial port. Language and
control program for downloading into RAM or mounted on EPROMs
+ Platform: DOS/Windows with IBM PC, XT, AT, PS/2 model 30 or
compatible
+ Delivered standard interface: MS DOS I/O driver
Section 1 of 7 - Prev - Next
All sections - 1 - 2 - 3 - 4 - 5 - 6 - 7
| Back to category comp-speech-faq - Use Smart Search |
| Home - Smart Search - About the project - Feedback |
© allanswers.org | Terms of use