Talking Avatars Exhibit Accurate Lip Synchronization For Wireless Applications
3Dmsg to bring three-dimensional talking avatars to wireless handsets for
messaging and other applications.
Las Vegas, NV, January 5, 2006-----3Dmsg(tm), a subsidiary of Sensory,
Inc., is now under formation focusing on applications for the cell phone
and wireless handset markets. 3Dmsg's avatars are created with the most
accurate lip-synchronization technology on the market, using a patented
scheme that morphs between visemes (visual phonemes), providing accuracy
that is precise enough for even lip readers to understand. The accuracy
that 3Dmsg lip synchronization provides will enable the development of
products not just for fun, but for communications, and language learning as
well. Additionally, 3Dmsg's avatars can be created, not only from live
speech, but from input text or a combination of text and speech. 3Dmsg
expects to announce its initial products during the first half of 2006. To
see a demonstration of 3Dmsg's talking avatar technology, go to www.3Dmsg.com.
"We've spent a lot of time over the past few years talking to handset
companies and service providers about our speech technologies," states Todd
Mozer, president of Sensory. "We learned that although speech recognition
is interesting, what is really more desirable are applications using
accurate 3D modeling to exploit many of the new features and capabilities
of today's handsets." Development of the technology is underway at
Sensory's facilities in Trivandrum, India, and Portland, Oregon.
The patented 3Dmsg technology takes advantage of a hybrid neural network
and hidden Markov modeling speech technology to analyze spoken data and
break it into components that can be represented visually. These components
may be thought of as visual phonemes or "visemes" and represent different
mouth/teeth/tongue positions and movements. By stringing and morphing
between these visemes, an avatar can be controlled or rendered to represent
a talking person or creature.
The 3Dmsg technology allows MMS, SMS, Instant Messaging, and other text or
voice messages to be delivered as ultra-low bandwidth 3D video-like
messages by a talking avatar. 3Dmsg's avatars achieve the quality and
accuracy of lip synchronized video with the bandwidth of text or voice.
Just as the initial quality of text-to-speech impeded mainstream adoption
by users, so has the "jerky" quality of animated entities done the same.
The introduction of 3Dmsg's technology should open the doors to faster
adoption by users, and will enable creative new products to be developed,
says Nancy Jamison, principal analyst at Jamison Consulting.
3Dmsg's products will include 3D animated messaging (from voice and text),
3D greeting cards, 3D pronunciation and language learning, and much more.
About 3Dmsg
3Dmsg. (www.3Dmsg.com), based in Sunnyvale, Calif., with development
offices in Trivandrum, India and Portland, Oregon, is a development stage
company and a wholly owned subsidiary of Sensory, Inc.
About Sensory
Sensory, Inc., (www.sensoryinc.com) based in Sunnyvale, CA, is the world
leader in embedded speech technologies. Sensory is a profitable private
company offering a complete line of IC and software-only solutions for
speech recognition, speech synthesis, speaker verification, music synthesis
and more. The company's products are widely deployed in consumer
electronics applications including telephones, home automation, toys,
remote controls, automotive, security, and learning aids. Sensory's
customers represent the leaders in consumer electronics, including such
companies as Hasbro, JVC, Kenwood, Mattel, Mitsubishi, Toshiba, Uniden and
Sony. Additional Sensory offices are located in Portland, Hong Kong, Tokyo
and Vienna.
Editorial Contacts:
Tom Tolbert
408 625-3339
ttolbert@3dmsg.com
David Kaye or Roni Kaye 818/368-8212
KPR, Inc. dave@kprinc.com or roni@kprinc.com
