|
IN-DEPTH
In this edition the main focus is on the Loquendo
ASR Phonetic Learning. This technique helps
speech application developers to improve speech
performance. It addresses two main issues: automatic
discovery of pronunciation variants for vocabulary
words, and clustering of frequent not foreseen linguistic
formulations to improve a speech recognition grammar.
>>
Go to the
article.
STANDARDS
CORNER
- Tim
Berners-Lee keynote at SpeechTEK
September 14, 2004
Tim Berners-Lee, the W3C's director, gave a leading keynote speech during
the last SpeechTEK conference in New York. The presentation was
focused on both the challenges of speech interaction and the opportunities
given by the Semantic Web in synergy with speech technologies.
- What is Semantic
Web?
Is it time to start to read and think about Semantic Web? There is a great
excitement on it from many areas, see for instance Semantic Web for
Life Sciences.
To start understanding terms and goals of the Semantic Web, the
following two presentations
given by Ivan Herman of W3C may be helpful:
- Towards
the Semantic Web
- Questions
(and Answers) on the Semantic Web
Loquendo is currently involved in a IST European project,
called HOPS, whose goal is
to address the mass-scale deployment of new online public
services supported and accessible by voice channels (basically phone,
both fixed and mobile). The partners include research labs, companies and
municipalities of Turin (Italy), Barcelona (Spain), and Camden (UK).
- New
Requirements for Pronunciation Lexicon (PLS)
October 29, 2004
The Voice Browser Working Group has recently restarted the activity
to develop a standard format for a pronunciation lexicon, in short PLS,
which will impact on both ASR and TTS to improve the recognition and
speech synthesis of proper names and other application dependent words.
Loquendo is leading this activity and the first step has been to
release the Requirement document. A first working draft is
expected by early 2005.
- New
Working Draft released for InkML
September 28, 2004
This specification describes the syntax and semantics for
the Ink Markup Language to be used in the W3C Multimodal Interaction
Framework.
The InkML serves as the data format for representing digital ink entered
with an electronic pen or stylus. It provides a common format for the
exchange of ink data between components such as handwriting and
gesture recognizers, signature verifiers, and other ink-aware modules.
- W3C
Voice Browser and Multimodal Interaction meetings
September 17-24, 2004
The meetings were hosted by IBM in the research center at Hawthorne,
NY. To learn more about the main achievements reached during the
meetings read the public notes: Voice
Browser meeting and Multimodal
Interaction meeting.
The next W3C VB and MMI meetings will be held in Turin (Italy)
on the first week of December and will be hosted by Loquendo.
- Architecture
of the World Wide Web is a W3C Proposed Recommendation
November 5, 2004
This document presents the general architecture of the Web, by highlighting
substantial architectural points regarding Web identifiers, protocols, and formats.
It also discusses some important general architectural principles and how
they apply to the Web.
Pulic comments and proposals are welcome through 3rd December, by
sending e-mails to public-webarch-comments@w3.org.
LOQUENDO
Products
- Loquendo
Studio 6.0 - the new Service Creation Environment
November 8, 2004
Loquendo Studio is a comprehensive suite of tools supporting
VoiceXML 2.0 and SRGS 1.0 grammar creation and testing. It is a web-based
graphic environment providing tools that automatically adapt themselves
according to the specific Loquendo product: Loquendo ASR or
Loquendo Speech Suite.
>>
More
- Loquendo
Launches Expressive TTS
October 18, 2004
Having been among the very first players to adopt the Unit Selection
technique, Loquendo is now the first company to bring expressive
synthetic speech to the market.
Loquendo's voices have been enriched with a repertoire of
"expressive cues", which enable TTS users to enliven their
voice prompts. This new development is the first concrete landmark
in the direction of expressive synthetic speech.
>>
More
- Loquendo
TTS news: Meet Willem, the new Dutch Male Voice!
October 11, 2004
Loquendo is pleased to announce that a new European country has
been added in its portfolio: Holland! Willem, the new male Dutch
voice able of being as natural as never before, is the latest
development in Loquendo's multilingual world of lifelike synthetic
speech.
Customers now can leverage on a High Quality Dutch Voice that
can be used in different applications such as Voice Activated Dialing,
Email Reading, Voice Portals, Navigation, Timetable & Traffic Information,
Call Center, CRM and Unified Messaging.
This new entry into the family of Loquendo TTS is a new landmark
in Loquendo's commitment to providing customers with expanded
reach in today's global marketplace for both embedded and
network-based applications. Quite soon Willem will be joined
by the Loquendo TTS bubbly Dutch female voice.
>>
More
Clients
& Partners
- Loquendo
and NMS Communications Certify Interoperability
Under NMS Universal Speech Access
September 27, 2004
NMS Communications, the leading provider of technologies and solutions
for enhanced services and efficient networks, announced that
Loquendo's Automatic Speech Recognition (ASR) software based
on the popular Media Resource Control Protocol (MRCP) 1.0
has been certified by NMS as compliant with the NMS Universal Speech
Access interface.
The NMS interface is the only enabling technology product currently
available for MRCP 1.0, which is widely endorsed as a de facto
standard by today's major speech engine vendors. NMS' Universal
Speech Access provides developers with a common application programming
interface (API) offering standards-based access to today's most
in-demand speech resources.
>>
More
- New York
Metropolitan Transportation Authority (MTA) selected Loquendo
Embedded Technology
September 13, 2004
Loquendo's embedded text-to-speech technology has been selected
by MTA Long Island Rail Road and MTA Metro-North Railroad.
Loquendo's software will be integrated into the Pocatec
communication system onboard the new M-7 fleet supplied by
Bombardier Transportation. This will allow text messages issued
from the Railroads remote facilities to be broadcast throughout the
audio/visual information system on board railcars.
Loquendo is the only speech technology vendor that provides
a complete product line for servers, desktop, multimedia, automotive,
PDA and embedded devices, guaranteeing the same wide range of
high-quality voices and languages, and the same core engine in
all these environments.
>>
More
Events
- Mobile Office
4th edition,
Palais des Congrès de Paris, Porte Maillot, 7-8-9 December 2004
Meet Loquendo at STAND # T62
- Expo Call Center
2004,
Lisbon, Hotel Marriott , 11-12 November 2004
- Mundo Oracle
2004,
Barcelona, 4 November 2004
- SYSTEM 2004 Fair
2004,
Munich, Conference Room K A21in Hall A2, 20 October 2004
- Oracle OpenWorld
2004,
Milan, Fiera Milano Congressi,
L.go Domodossola 1, Pavilion 17, Stand 6828
30 September 2004
- Mundo Oracle
2004,
Madrid, 28-29 September 2004
Barcelona, 4 November 2004
|
