|
August
2006 |
|
|
SpeechTEK
2006, New York, 7-10 August
Dear
Reader,
This is a special issue of the Loquendo Newsletter, focused on SpeechTEK 2006 in New York.
Loquendo will be unveiling its new range of state-of-the-art technology. Don't miss your chance to try out Loquendo's
latest tools and voices, and to find out how speech technology can help your business. We look forward to seeing you
at Booth #509 from 7-10 August.
Be sure to catch the presentations given by Loquendo's experts, see below for times and venues.
|
|
 |
|
Loquendo at SpeechTEK 2006
Marriott Marquis,
New York,
7-10 August,
What's new from Loquendo:
On the occasion of SpeechTEK 2006, Loquendo is proud to present its latest innovations,
as well as some exciting demos. Here is an outline of the Loquendo products you can see
for yourself at Booth #509 in the Exhibition Area.
- Loquendo TTS, the high quality, natural sounding speech synthesis in 18 languages
and 43 voices, incorporating many features that are unique to Loquendo, is now available as a
Multimedia package. Loquendo TTS Multimedia is specifically designed for all those solutions where
the TTS voice quality is of particular importance: sampling rate is up to 48 KHz and many audio
effects are available.
There are two tools for modifying TTS pronunciation parameters: the new Loquendo Voice Experience and
Loquendo TTS Director, which now includes Voice Creator for the creation of new,
personalized voices to suit your company profile.
With 'Expressive TTS' Loquendo voices pronounce numerous everyday expressions in a really lifelike
way and with a far greater expressive range, bringing Loquendo ever closer to truly emotional speech.
With Loquendo's mixed language support, all Loquendo voices can speak any foreign language with the
correct pronunciation, while keeping their native accent.
- Loquendo ASR is speaker independent and reliably recognizes large scale vocabulary continuous
speech, even in challenging environments. Loquendo ASR fully supports all standards for speech recognition,
such as W3C SRGS and W3C SISR.
A complete set of fast, efficient tools with powerful features make Loquendo ASR one of the most robust
speech recognition engines on the market:
- The Phonetic Learning software package can detect, from field data, users' spoken formulations
that were not covered by the application designers. This is particularly useful for non-native speakers
and regional accents.
- Acoustic Model Adaptation can significantly improve recognition performance when voice
applications are run in a non-standard context: a single speaker, a particular environment (e.g. in-car),
certain kinds of input devices etc.
- Loquendo VoiceXML Platform: VoxNauta supports all the relevant standards in speech:
VoiceXML 2.1, CCXML 1.0 , MRCP v2, SGRS, SISR 1.0 and SSML 1.0.
VoxNauta is one of the very first voice platforms which supports both VoiceXML and CCXML - making
service application completely independent of platform legacy - and one of the very few voice platforms
with a software implementation of the SIP-RTP protocol - making the VoIP connection simply a matter
of software (available on Windows and Linux).
VoxNauta offers outstanding flexibility: by means of a user friendly, message-based protocol interface,
Loquendo's voice platform allows the simple integration of any third party IVR. This means that clients can
retain their existing IVR and at the same time benefit from all the advantages of VoiceXML.
Loquendo VoxNauta has been certified by the VoiceXML forum.
- Loquendo MRCP v1 & v2 Server: Loquendo Speech Suite enables system integrators to choose the
components they need from Loquendo's extensive range of technologies and to exploit them using a flexible,
standard-based, client-server architecture - supporting both MRCPv1 and v2. Its modular architecture makes
Loquendo Speech Suite independent from ASR/TTS engines as well as from languages and voices, allowing
the seamless upgrade to new technology releases and the addition of new languages (ASR) and new
voices (TTS).
Come and try out Loquendo technology for yourself at Booth #509. See you there!
Loquendo presentations:
Here's when and where Loquendo's speakers will be addressing attendees:
-
Monday August 7, 2006
"Advanced Speech Synthesis – Emotion and Affect"
Session: Speech Synthesis and Emotion
10:30 pm - 12:00 pm, (Monica Bisacca)
-
Tuesday August 8, 2006
"TTS in Car Navigaiton Applications"
Session: In-car Computing
2:00 pm - 3:30 pm, (Luisa Cordano)
Panel Discussion
Session: Going International with Speech (Panel)
4:00 pm - 5:00 pm, (Rosanna Duce)
-
Wednesday, August 9, 2006
"VoiceXML Application Development Tools Training"
Session: Hands-on Voice Application Development Tools Training
10:00 am - 11:00 am (Paolo Baggia & Walter Battistetti, SpeechVillage)
"How IPA is Used in the W3C SSML and PLS"
Session: Authoring Synthesized Speech (TTS)
2:00 pm - 3:30 pm, (Paolo Baggia)
Panel Discussion
Session: Overcoming Barriers to Multimodal Application Deployment
2:00 pm - 3:30 pm (Piergiorgio Vittori)
EVENTS
- SpeechTEK 2006,
New York, Marriott Marquis, 7-10 August 2006.
Visit Loquendo at BOOTH #509.
- Human Language Technology Workshop,
Povo - Trento, Italy, 6-8 September 2006.
The workshop will bring together researchers and industry experts in the area of speech and
language research, technology and applications. Workshop attendance is free. Limited seats available.
Need to Register and send email to: HLT06-unitn@dit.unitn.it.
- September 6, 2006 - Room 108
Speech Technologies and Standards (Paolo Baggia)
- Canalys Navigation Forum 2006,
Geneva, Crowne Plaza, Switzerland, 11-13 September 2006.
- Voice Days 2006,
Bonn, Alter Bundestag, 18-19 October 2006.
- Expo Call Center Madrid 2006,
Madrid, Feria de Madrid, Palacio Norte, 7-8 November 2006.
- Expo Call Center Lisbon 2006,
Lisbon, Estoril Congress Center, 28-29 November 2006.
|
|
 |
|
|
