EP0847179A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
System and method for voiced interface with hyperlinked information
Assignee: AT&T Inc
•
Filing: 1997-10-29
•
Granted: —
•
Expires: 2017-10-29
Abstract
Abstract An improved audio browser is disclosed. In an exemplary embodiment, a plurality of hypertext links (hereafter called "hyperlink words") available from, for example, a World Wide Web document, are used as a vocabulary of a speech recognizer for an audio browser. These hyperlink words are read to the user in the ordinary course of the audio browser's "speaking voice" -- such hyperlink words being identified to the user by, for example, a change in voice characteristics for the "speaking voice." When a user wishes to select a hyperlink word, the user merely repeats the hyperlink word itself, rather than speaking a command or using a DTMF tone. The speech recognizer, which has as its vocabulary some or all of the hyperlink words of the document, recognizes the spoken hyperlink word and causes the jump to the linked address associated with the recognized hyperlink word.
Inventors
- 👤 Daniel Jitzchak Mayer
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-10-30 16:52
CPC Classifications
H; H04; H04M; H04M3/00; H04M3/42; H04M3/487; H04M3/493; H04M3/4938
Claims Analysis
Total Claims: 40
Claim 1
Independent Claim
93 words
A method of facilitating the selection of a hyperlink
from among a plurality of hyperlinks presented to a user in
audio form, said method comprising the steps of: furnishing to said user a first signal representing speech
utterances of said plurality of hyperlinks and one or more other
words, wherein said signal includes an identification of said
hyperlinks; performing speech recognition on a second signal representing
speech uttered by said user, said speech recognition being
performed with use of a recognizer vocabulary which comprises
entries corresponding to at least two of said hyperlinks.
Claim 2
Dependent Claim
32 words
The method of Claim 1 wherein said furnishing step
comprises synthesizing said speech utterances represented in
said first signal based on a corpus of text, said corpus
including said plurality of hyperlinks.
Claim 3
Dependent Claim
21 words
The method of Claim 2 wherein said corpus of text
comprises text of a document provided by a computer network
server.
Claim 4
Dependent Claim
12 words
The method of Claim 3 wherein said document comprises an
HTML page.
Claim 5
Dependent Claim
94 words
The method of Claim 1 wherein at least a portion of said
speech utterances represented in said first signal comprise
prerecorded human voice, or wherein said utterances of hyperlinks furnished to said
user are aurally distinct from said- utterances of said other
words, or wherein said first and second signals are carried over a
telephone network, and further wherein at least a portion of a
routing of said signals is based on a recognized hyperlink, or wherein said at least two of said hyperlinks includes less
than all hyperlinks in said plurality of hyperlinks.
Claim 6
Independent Claim
58 words
The method of one or more of Claims 1-5 further
comprising the step of selecting said recognizer vocabulary
entries to be a subset of all hyperlinks furnished to said user,
or further comprising the step of selecting said at least two
of said hyperlinks in accordance with a temporal window defining
a subset of said plurality of hyperlinks.
Claim 7
Dependent Claim
43 words
The method of Claim 6 wherein the step of performing
speech recognition further comprises selecting a particular
hyperlink as a recognition result from among said at least two
of said hyperlinks based on a temporal location of a particular
hyperlink within said window.
Claim 8
Dependent Claim
38 words
The method of Claim 1 wherein said hyperlink entries
comprising said recognizer vocabulary for said speech recognition
are limited to a subset of said plurality of hyperlinks
which have occurred in said first signal during a predefined
interval.
Claim 9
Dependent Claim
71 words
The method of Claim 8 wherein each of said hyperlink
entries comprising said recognizer vocabulary has an equal
likelihood of representing an unknown speech utterance in said
second signal, or wherein any one of said hyperlink entries comprising said
recognizer vocabulary has a likelihood of representing an
unknown speech utterance in said second signal which is weighted
according to a temporal position of said any one hyperlink in
said predefined interval.
Claim 10
Independent Claim
55 words
The method of one or more of Claims 1-9 further
comprising the step of causing a predefined action to be carried
out based on a recognized hyperlink, or further comprising the step of initiating a transaction
based on a recognized hyperlink, or further comprising the step of performing a transaction
based on a recognized hyperlink.
Claim 11
Independent Claim
23 words
The method of Claims 2 or 3 further comprising the step
of identifying a second corpus of text based on a recognized
hyperlink.
Claim 12
Dependent Claim
22 words
The method of Claim 11 wherein said second corpus of
text comprises text of a document located on a computer network
server.
Claim 13
Independent Claim
96 words
A system for facilitating the selection of a hyperlink
from among a plurality of hyperlinks presented to a user in
audio form, said system comprising: an interface providing to said user a first signal
representing speech utterances of said plurality of hyperlinks
and one or more other words, wherein said signal includes an
identification of said hyperlinks; a speech recognizer for performing speech recognition on a
second signal representing speech uttered by said user, said
speech recognition being performed with use of a recognizer
vocabulary which comprises entries corresponding to at least two
of said hyperlinks.
Claim 14
Dependent Claim
32 words
The system of Claim 13 wherein said interface operates
to synthesize said speech utterances represented in said first
signal based on a corpus of text, said corpus including said
plurality of hyperlinks.
Claim 15
Dependent Claim
21 words
The system of Claim 14 wherein said corpus of text
comprises text of a document provided by a computer network
server.
Claim 16
Dependent Claim
138 words
The system of Claim 13 wherein at least a portion of
said speech utterances represented in said first signal comprise
prerecorded human voice, or wherein identification of said hyperlinks in said first
signal is carried out by providing said utterances of hyperlinks
furnished to said user in an aurally distinct form from said
utterances of said other words, or wherein said first and second signals are carried over a
communications network, and further wherein at least a portion
of a routing of said signals is based on a recognized hyperlink,
or wherein vocabulary entries for said recognition means are
selected to be a subset of all hyperlinks furnished to said
user, or further including means for selecting said at least two of
said hyperlinks in accordance with a temporal window defining a
subset of said plurality of hyperlinks.
Claim 17
Dependent Claim
38 words
The system of Claim 16 wherein said speech recognizer
selects a particular hyperlink as a recognition result from
among said at least two of said hyperlinks based on a temporal
location of a particular hyperlink within said window.
Claim 18
Dependent Claim
38 words
The system of Claim 13 wherein said hyperlink entries
comprising said recognizer vocabulary for said speech recognizer
are limited to a subset of said plurality of hyperlinks which
have occurred in said first signal during a predefined interval.
Claim 19
Dependent Claim
71 words
The system of Claim 18 wherein each of said hyperlink
entries comprising said recognizer vocabulary has an equal
likelihood of representing an unknown speech utterance in said
second signal, or wherein any one of said hyperlink entries comprising said
recognizer vocabulary has a likelihood of representing an
unknown speech utterance in said second signal which is weighted
according to a temporal position of said any one hyperlink in
said predefined interval.
Claim 20
Independent Claim
56 words
The system of one or more of Claims 13-19 including a
means for causing a predefined action to be carried out based on
said recognized hyperlink, or further comprising a transaction initiator which initiates
a transaction based on a recognized hyperlink, or further comprising a transaction processor for performing a
transaction based on a recognized hyperlink.
Claim 21
Independent Claim
22 words
The system of Claims 14 or 15 including a means for
identifying a second corpus of text based on a recognized
hyperlink.
Claim 22
Dependent Claim
22 words
The system of Claim 21 wherein said second corpus of
text comprises text of a document located on a computer network
server.
Claim 23
Dependent Claim
75 words
A voiced information interface system comprising: a database of information including text having one or more
corresponding information links; a means operating in conjunction with said database for
causing information to be provided in voiced form; a means for recognizing a voiced response by a user in
relation to said provided information; and a means for shifting to information related to at least one
of said information links in response to said recognized user
response.
Claim 24
Dependent Claim
34 words
The voiced information interface system of Claim 23
wherein said database of information is arranged as a plurality
of information layers and a linkage between said information
layers is provided by said information links.
Claim 25
Dependent Claim
23 words
The voiced information interface system of Claim 24
wherein said information links are provided as identified
information segments in a given information layer.
Claim 26
Dependent Claim
48 words
The voiced information interface system of Claim 25
wherein said information in said given information layer is
provided as a plurality of textual words, or wherein said voiced response by a user is constituted as a
repeat of one of said identified information segments in said
given layer.
Claim 27
Dependent Claim
41 words
The voiced information interface system of Claim 23
wherein said means for causing information to be provided in
voiced form includes a further means for causing said
information links to be provided in an aurally distinct manner
from other voiced information.
Claim 28
Dependent Claim
46 words
The voiced information interface system of Claim 27
wherein said further means for causing said information links to
be provided in an aurally distinct manner operates to cause said
information links to be voiced in an opposite gender voice from
that of said other voiced information.
Claim 29
Dependent Claim
61 words
The voiced information interface system of Claim 23
wherein said voiced response by a user is constituted as a
direction for a predefined action by said system, or including a further means to provide a confirmation of said
voiced response to said user, or including a further means for providing to a user graphical
information appearing in said database of information.
Claim 30
Dependent Claim
23 words
The voiced information interface system of Claim 29
wherein said graphical information is provided to said user via
a graphical access channel means.
Claim 31
Independent Claim
72 words
A method for providing voiced access to stored
information, wherein said information includes text having one
or more corresponding information links, comprising the steps
of: causing at least a portion of said information to be
provided in voiced form; recognizing a voiced response by a user in relation to said
provided information; and shifting to information related to at least one of said
information links in response to said recognized user response.
Claim 32
Dependent Claim
37 words
The method for providing a voiced access to stored
information of Claim 31 wherein said information is arranged as
a plurality of information layers and a linkage between said
information layers is provided by said information links.
Claim 33
Dependent Claim
28 words
The method for providing a voiced access to stored
information of Claim 32 wherein said information links are
provided as identified information segments in a given
information layer.
Claim 34
Dependent Claim
51 words
The method for providing a voiced access to stored
information of Claim 33 wherein said information in said given
layer is provided as a plurality of textual words, or wherein voiced response by a user is constituted as a
repeat of one of said identified information segments in said
given layer.
Claim 35
Dependent Claim
45 words
The method for providing a voiced access to stored
information of Claim 31 wherein said step of causing information
to be provided in voiced form includes a substep of causing said
information links to be provided in an aurally distinct manner
from other voiced information.
Claim 36
Dependent Claim
50 words
The method for providing a voiced access to stored
information of Claim 35 wherein said substep of causing said
information links to be provided in an aurally distinct manner
operates to cause said information links to be voiced in an
opposite gender voice from that of said other voiced information
Claim 37
Dependent Claim
62 words
The method for providing a voiced access to stored
information of Claim 31 wherein said voiced response by a user
is constituted as a direction for a predefined action, or including a further step of providing a confirmation of
said voiced response to said user, or including a further step of providing to a user graphical
information appearing in said stored information.
Claim 38
Dependent Claim
28 words
The method for providing a voiced access to stored
information of Claim 37 wherein said graphical information is
provided to said user via a graphical access channel means.
Claim 39
Independent Claim
93 words
A system for providing an interface to a stored
database of information comprising: a means for providing said database of information as a set
of linked information layer, wherein said information is stored
in an audio form; a means for causing a particular layer of said information
to be provided to a user; a means for recognizing a voice response by said user in
relation to information in said particular layer; and a means for operating on said recognized user response to
effect a shift from said particular layer to a linked layer.
Claim 40
Independent Claim
136 words
A system for providing an interface to a stored
database of information comprising: a means for establishing said database of information as a
set of linked information layers, where linkage between such
layers is related to linkage words in particular information
layers; a means operating in conjunction with said stored
information layers for causing information in a given layer to
be provided in voiced form, wherein said linkage words in said
given layer are provided in an aurally distinct manner from
other information in said given layer; a means for recognizing a voiced response by a user in
relation to one of said linkage words in said given layer; and a means for operating on said recognized voiced user
response to effect a shift from said given layer to another
layer linked to said linkage word.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.