Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

Portable, Speech-Activated, Electronic Mail System

IP.com Disclosure Number: IPCOM000116050D
Original Publication Date: 1995-Jul-01
Included in the Prior Art Database: 2005-Mar-30
Document File: 2 page(s) / 92K

Publishing Venue

IBM

Related People

Cohen, PS: AUTHOR [+2]

Abstract

Disclosed is a portable, speech-driven device with which business professionals can listen and respond to their Electronic mail (E-mail) while driving an automobile. A first version of this device has an RJ-11 jack for connection with standard phone lines to download and upload E-mail messages or in-baskets. This version allows the user to listen to E-mail messages and to respond through speech during driving without using expensive cellular telephone time. A second version of the device provides the capabilities of the first version, along with a receiver, such as a pager, for priority messages. A third version of the device includes a cellular receiver and transmitter. The second and third versions thus receive messages over radio, satellite, or pager systems.

This text was extracted from an ASCII text file.
This is the abbreviated version, containing approximately 53% of the total text.

Portable, Speech-Activated, Electronic Mail System

      Disclosed is a portable, speech-driven device with which
business professionals can listen and respond to their Electronic
mail (E-mail) while driving an automobile.  A first version of this
device has an RJ-11 jack for connection with standard phone lines to
download and upload E-mail messages or in-baskets.  This version
allows the user to listen to E-mail messages and to respond through
speech during driving without using expensive cellular telephone
time.  A second version of the device provides the capabilities of
the first version, along with a receiver, such as a pager, for
priority messages.  A third version of the device includes a cellular
receiver and transmitter.  The second and third versions thus receive
messages over radio, satellite, or pager systems.  Spoken responses
by the user are converted to text and saved to be transmitted when
the device is connected to the e-mail system.  The third version can
transmit and route messages by means of speech commands over radio or
cellular networks.

      The device combines a number of technologies, such as
high-speed context switching, a text-to-speech subsystem,
pre-recorded compressed sound-bytes, and summarization software to
summarize free-form text.  A speech nickname file simplifies filing
and routing messages.  The device may include additional input means,
such as a keyboard or a digitizer-stylus.  The device is implemented
to have a full duplex speech recognition capability, or alternately a
touch-to-speak or interrupt capability.  Software within the device
may be used to download and upload e-mail messages to another
computing device, such as a laptop computer.

      Nickname files for commonly addressed individuals are imbedded
in Backus-Naur Form (BNF) grammars, so that the user can simply say,
for example, "Send this note to Ron Smith in Austin."  Preferably,
the system builds a list of first names, last names, and cities in
both the nickname file and in the inbound and outbound correspondence
log.  The most commonly used names are identified by the device, and
a standard addressing format is supplied by the user.  The system
automatically generates the phoneme strings or baseforms for these
names, either through a table lookup or through an algorithm.
Preferably, the speech recognition system is capable of continuous
speech recognition, co-articulation, and automatic baseform
generation.

      The various features of the device can be understood by
r...