NEW YORK--(BUSINESS WIRE)--Oct. 26, 1999--
ISD's New Speech Recognition Technology Stands
to Change the Way People Interface with Electronics
ISD (Information Storage Devices, Inc.), a Winbond company and the leading supplier of
semiconductor voice solutions, today launched a revolutionary embedded speech recognition engine,
the ISD-SR3000.
The first in a new family of microchips designated the Simon(TM) series, this solution ushers in a
new era of speech recognition, dramatically changing the way people interface with electronic devices.
With the Simon engine, consumers will now be able to operate everything from cell phones and voice
message machines to handheld devices using their voice instead of complex, keyboarded commands.
This new technology offers speaker-independent speech recognition with continuous speech and digit
input in a cost-effective, embedded solution that significantly reduces customers' cost and time to
market. The ISD-SR3000 will be demonstrated at the SpeechTEK Conference and Exposition,
booth no. 178, at the New York Hilton and Towers in New York City, October 26-27.
For the first time, consumers can experience the same voice command and control capabilities
normally reserved for powerful PC- or server-based products -- all in a simple, chip-level solution
that includes hardware, firmware and voice user interface. The product is ideal for small, low-power
consumer products, such as telephony products, home appliances and other electronic devices, as
well as automotive and industrial applications. Simon microchips are expected to begin sampling in the
first quarter of 2000, and will be priced under $5.00 in consumer product quantities.
Historically, speech recognition products haven't been accurate enough to provide significant value
to consumers. ISD's new chip offers 99 percent accuracy for speaker-independent commands and
digits, requires no user training, and works well across dialects and genders. The speaker-independent
commands and speaker-defined voicetags are stored in external memory, allowing for maximum
application flexibility. Typical applications include up to 50 commands and 50 voicetags, stored in
256k of memory. These combined benefits enable manufacturers to develop accurate and affordable
command and control applications for feature-oriented, mainstream electronics.
According to speech recognition expert Bruce Balentine, consultant for Same Page Design Group,
consumers have recently become more comfortable with speech recognition due to its increasing use
in telephony applications, such as messaging and call-center assistance. "This technology has evolved
to a point where it can accurately and easily replace the complex keypad and display controls
currently used in consumer devices. ISD's new microchip features a flexibility normally only available
from robust software engines, and provides manufacturers with a solution that catapults the
human-electronic interface to an entirely new level."
The ISD-SR3000 is ideally suited for command and product applications featuring complex,
cumbersome interfaces. The combination of speaker-independent commands, coupled with
speaker-defined commands, allows for both standard and custom product control. The ISD-SR3000
features American English language capabilities, with additional languages slated for future generations.
In addition, the voice user interface dialogs provide an easy-to-understand natural interface with
context-sensitive help prompts, creating a seamless interaction between human and machine.
"Imagine being able to tell your handheld device to display your calendar, or while driving, to
verbally command your cell phone to dial a number. Speech recognition technology not only makes
complex consumer products easier to use, but also much safer -- for instance, helping to decrease the
number of auto accidents due to cellular phone usage," said Larry Gaddy, senior product marketing
manager for speech recognition products at ISD. "The Simon engine will also allow disabled persons
to operate products purely with voice, thereby enabling increased productivity, greater personal
freedom and improved quality of life."
ISD's speech recognition technology uses a sub-phoneme recognition process. The sampled
speech utterance is split into distinct phonetic sounds, then Hidden Markov models are used to
hypothesize boundaries between sounds, and to form probabilistic models for each possible
combination. This process allows a wide variety of speakers to use the technology, and recognizes
continuous speech patterns in real time. Moreover, the speech recognition function is always active,
enabling voice activation with keyword commands as well as a push-to-talk option for battery
applications.
According to Jock Ochiltree, president and COO of ISD, the development of speech recognition
technology strengthens ISD's position as the market leader in voice solutions. "ISD's mission is to
advance the way people communicate by providing the sophisticated voice technology essential for
leading-edge communication, consumer and automotive products. When integrated into these
products, the Simon engine increases utility and functionality and ultimately humanizes man-machine
interfaces, making it easier for consumers to benefit from increasingly complex electronic appliances,"
said Ochiltree.
Demo units of Simon ICs are now available for beta site partners. Beta site participants will receive
a development system, full documentation, advance access to samples, technology updates and
assistance in developing their own custom applications. These tools accelerate the application
development process by allowing custom vocabulary generation, voice prompt compilation and user
dialog design.
About ISD
As the Voice Solutions in Silicon(TM) Company, ISD provides essential products to the
communications, consumer, automotive, medical and industrial marketplaces using its proprietary
technologies. ISD's ChipCorder(c) product family, featuring exceptional sound quality, low-power
consumption, and non-volatility in a single chip, utilizes ISD's proprietary 8-bit per cell equivalent
multi-level storage technology. Leveraging the company's proprietary advanced, proven digital speech
processing technology and high-quality speech compression algorithms, ISD's VoiceDSP(TM)
products enable an array of digital features and functionality for products such as digital telephone
answering devices. ISD's new Simon(TM) series of speech recognition products enable consumers to
leverage the power of PC- and server-oriented voice command and control capabilities in a simple,
chip-level solution, making it ideal for small, low-power, low-cost products. For more information,
please visit our World Wide Web home page at www.isd.com.
Note: ChipCorder and ISD are registered trademarks and VoiceDSP, Simon and Voice Solutions
in Silicon are trademarks of Information Storage Devices, Inc.
Morning Folks:
Dave |
