| September
2004 |
|
|
Forewords
Dear
Reader,
Welcome to the new issue of Loquendo's Newsletter! You will find
some improvements, it has become richer in contents. This issue
has two main articles, the first on Speech Platforms and
the second on SSML language for TTS; you will also find
more links on standards and resources found on the Web.
Recently,
Loquendo has released a number of new features on several products:
Phonetic Learning on Loquendo ASR, VoxNauta Lite 6.0
platform, and new voices for Loquendo TTS.
We
will be at SpeechTEK to present our latest technologies
at Booth #509 and to give major presentations, for instance
on September 15th a Keynote speech by Marco Romagnoli, CEO
and Managing Director of Loquendo.
See you there!
|
|

|
 |
|
IN-DEPTH
The main article in this issue is on the
role of speech platforms in deploying effective and
reliable speech applications. It gives
a better understanding of the main features you need
to care about when choosing a speech platform. The
paper also presents the latest release of Loquendo's
platforms: VoxNauta Lite 6.0.
>>
Go to the
article.
To endorse W3C Recommendation
for Speech Synthesis Markup Language (SSML)
specification, this article will highlight why SSML
language may enlarge the usage of TTS technology in
a variety of contexts and applications. The main features
of the language are described with extensive examples.
You can test them on the Loquendo interactive demo
(here).
>>
Go to the
article.
STANDARDS
CORNER
- SSML
1.0 reaches W3C Recommendation
September 8, 2004
Congratulations! The Speech Synthesis Markup Language
(SSML 1.0) Specification is now a W3C Recommendation.
This is an important milestone for TTS engine producers
(like Loquendo) and for speech application market.
Read the W3C press
release and testimonials
that acknowledge this achievement.
- VoiceXML
2.1 is W3C Last Call Working Draft
July 28, 2004
This specification is an add-on to VoiceXML 2.0
W3C Recommendation. It defines a set of 8 commonly
implemented additional features, the major are:
to reference grammar and scripts dynamically, to
allow markers in a TTS prompt, to fetch XML data
to be fed in a VoiceXML page, to record speech input
for each recognition, to extend transfer call types,
etc. VoiceXML 2.1 is designed to be fully backwards-compatible
with VoiceXML 2.0.
The next specification step is to provide an Implementation
Report.
- New
Working Draft released for EMMA
September 1, 2004
Extensible Multi-Modal Annotation (EMMA) language
is an interface language to represent speech recognition
results or results from other modalities (i.e. gesture
or handwriting) in a multi-modal application framework.
It is very important for well-known protocol interfaces,
like Media Resource Communication Language (MRCP).
The new Working Draft is almost complete the next
step will be to become a Last Call Working Draft.
- W3C
Workshop on Multimodal Interaction
July 19/20, 2004
Sophia Antipolis, France
This Workshop was co-founded by W3C and European
Commission's IST Programme. The W3C Workshop was
an opportunity to discuss W3C advances in Multimodal
Interaction and to provide feedback and suggestions
for future work.
The schedule
and the paper
presented are accessible to read further on this
activity.
LOQUENDO
Products
- Loquendo
Releases VoxNauta Lite 6.0 Speech Platform
September 9, 2004
Loquendo is pleased to announce the latest release
of Loquendo platform: VoxNauta Lite 6.0, which
is the result of Loquendo's long experience
in providing high-quality speech technologies and minimizing
the customer's service deployment effort. It is a complete multi-lingual
open solution for building customized voice service and improving
communication through voice access to information - anywhere, anytime.
>>
More
- Loquendo
Launches Phonetic Learning Technology
August 10, 2004
Loquendo presents the latest development for Loquendo ASR technology:
the Loquendo Phonetic Learner. It is a semi-automatic tool able to
discover new undefined frequent formulations and to elicit additional
pronunciation variants for the expected formulations. This is particularly
useful to improve performance for non-native speakers and regional accents. >>
More
- A
new female voice to reinforce Loquendo's presence
in the French market
July 22, 2004
Loquendo is pleased to present the latest development
in the world of Loquendo TTS synthetic speech: Juliette,
the brand new French female voice to accompany Bernard
and Sophie, Loquendo's French personas. >>
More
Clients
& Partners
- Loquendo
Technology chosen by Targex Corporation
September 07, 2004
Loquendo's Text-To-Speech was selected by Targex
Corp. based in Miami, Florida to speech enable their
leading vehicle tracking product "Eagle Eye
Embedded AVL Unit". The Loquendo embedded TTS
software will enable Targex customers to enjoy natural
sounding speech output from their on-board vehicle
equipment. >>
More
Events
- SpeechTEK
2004,
New York Marriott Marquis, 13 - 16 September 2004
Meet Loquendo at BOOTH # 509
Loquendo's presentations
Tuesday, September 14, 1:00 PM - 2:30 PM
Technology Insights: Making Speech Available to
Everyone
Piergiorgio Vittori, area manager, Loquendo
Wednesday, September 15, 2:45 PM - 4:00
PM
Industry Visions Keynote
Marco Romagnoli, CEO and managing director,
Loquendo
|
|
 |
|
|