Voice processing apparatus
First Claim
Patent Images
1. A method of operating a voice processing system comprising the steps of:
- receiving spoken input from a user;
performing speech recognition to convert said spoken input into a digital equivalent;
identifying at least two information elements in said digital equivalent, each having an uncertainty associated therewith;
selecting a prompt containing said at least two information elements and emphasizing one of said at least two information elements that has the greatest uncertainty associated therewith; and
playing out said selected prompt to the user.
2 Assignments
0 Petitions
Accused Products
Abstract
A voice processing system receives spoken input from a user, which is then subjected to speech recognition to convert the spoken input into a text equivalent. At least two information elements are identified in the text equivalent, each having an associated uncertainty. The system selects a prompt according to which information element has the greatest uncertainty, and this is then played out to the user. Typically the outgoing prompt is arranged to emphasise, via word order, volume, or some other mechanism, the information element in greatest doubt, thereby bringing it to the particular attention of the user, should correction be required.
98 Citations
27 Claims
-
1. A method of operating a voice processing system comprising the steps of:
-
receiving spoken input from a user;
performing speech recognition to convert said spoken input into a digital equivalent;
identifying at least two information elements in said digital equivalent, each having an uncertainty associated therewith;
selecting a prompt containing said at least two information elements and emphasizing one of said at least two information elements that has the greatest uncertainty associated therewith; and
playing out said selected prompt to the user. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
receiving a second spoken input from said user;
performing speech recognition to convert said second spoken input into a second text equivalent;
identifying at least two information elements in said second text equivalent, each having an uncertainty associated therewith;
and reaching an error condition if the uncertainty associated with the at least two information elements in said second text equivalent is greater than that for the at least two information elements in said text equivalent.
-
-
9. The method of claim 1, in which said voice processing system and said user communicate with each other over a telephone network, whereby said spoken input is received over a telephone connection, and said prompt is played out over the telephone connection.
-
10. Voice processing apparatus comprising:
-
an input device which receives spoken input from a user;
a speech recognition unit which converts said spoken input into a digital equivalent;
a natural language understanding unit which identifies at least two information elements in said digital equivalent, each having an uncertainty associated therewith;
a prompt generator which selects a prompt containing said at least two information elements and emphasizing one of said at least two information elements that has the greatest uncertainty associated therewith; and
an output device which plays out said selected prompt to the user. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17, 18)
-
-
19. A computer readable medium containing instructions readable by a computer system operating as a voice processing system, said instructions including instructions for causing the computer system to perform the following steps:
-
receiving spoken input from a user;
performing speech recognition to convert said spoken input into a digital equivalent;
identifying at least two information elements in said digital equivalent, each having an uncertainty associated therewith;
selecting a prompt containing said at least two information elements and emphasizing one of said at least two information elements that has the greatest uncertainty associated therewith; and
playing out said selected prompt to the user. - View Dependent Claims (20, 21, 22, 23, 24, 25, 26, 27)
receiving a second spoken input from said user;
performing speech recognition to convert said second spoken input into a second text equivalent;
identifying at least two information elements in said second text equivalent, each having an uncertainty associated therewith;
and reaching an error condition if the uncertainty associated with the at least two information elements in said second text equivalent is greater than that for the at least two information elements in said text equivalent.
-
-
27. The medium of claim 19, in which said voice processing system and said user communicate with each other over a telephone network, whereby said spoken input is received over a telephone connection, and said prompt is played out over the telephone connection.
Specification