Method and apparatus for optimizing a spoken dialog between a person and a machine
First Claim
1. A method of executing a spoken dialog between a user and a speech-enabled site in a network including a plurality of voice-hyperlinked speech-enabled sites, the method comprising:
- acquiring information associated with the user at a first speech-enabled site of the plurality of speech-enabled sites during a first spoken dialog between the user and the first speech-enabled site;
in response to the user initiating a voice hyperlink to access a second speech-enabled site of the plurality of speech-enabled sites, providing the information associated with the user to the second speech-enabled site; and
optimizing a second spoken dialog between the user and the second speech-enabled site by applying the information associated with the user to reduce a number of states of the second spoken dialog.
5 Assignments
0 Petitions
Accused Products
Abstract
A network comprises a number of speech-enabled sites maintaining a number of voice pages. A central server on the network executes a voice browser which provides users with access to the sites using voice-activated hyperlinks. The server also maintains and brokers information associated with the users based on spoken dialogs between the users and the sites. In response to a user accessing a given ASR site, information about that user is provided by the server for use by that ASR site. The information is used by the ASR site to optimize a spoken dialog between the user and the ASR site by reducing the amount of information the user is required to provide during the dialog. Information about the user can thereby be shared between separate speech enabled sites, in a manner which is transparent to the user, in order to expedite the user'"'"'s interaction with those sites.
-
Citations
13 Claims
-
1. A method of executing a spoken dialog between a user and a speech-enabled site in a network including a plurality of voice-hyperlinked speech-enabled sites, the method comprising:
-
acquiring information associated with the user at a first speech-enabled site of the plurality of speech-enabled sites during a first spoken dialog between the user and the first speech-enabled site;
in response to the user initiating a voice hyperlink to access a second speech-enabled site of the plurality of speech-enabled sites, providing the information associated with the user to the second speech-enabled site; and
optimizing a second spoken dialog between the user and the second speech-enabled site by applying the information associated with the user to reduce a number of states of the second spoken dialog. - View Dependent Claims (2, 3)
-
-
4. An apparatus configured to allow a user to interactively browse a telephony-based network, the apparatus comprising:
-
means for coupling a user to a first speech-enabled service at a first location on the network;
means for acquiring information associated with the user;
means for outputting an indication audibly detectable by the user, the indication corresponding to a second speech-enabled service at second location on the network;
means for detecting the user speaking an utterance matching the indication;
means for coupling the user to the second speech-enabled service in response to the user speaking an utterance matching the indication; and
means for providing the information associated with the user to the second speech-enabled service in response to the user speaking an utterance matching the indication, the information for use by the second speech-enabled service to optimize a spoken dialog between the user and the second speech-enabled service. - View Dependent Claims (5)
-
-
6. A system comprising:
-
a first processing system configured to execute a speech-enabled browser, the browser configured to maintain information associated with a user; and
a second processing system coupled on a network to the first processing system and configured to operate as a speech-enabled site, the second processing system configured to in response to receiving an access request from a remote user, transmit a request to the browser for the information associated with the user;
receive the information associated with the user in response to transmitting the request;
apply the information associated with the user to optimize a dialog with the user by reducing the number of required states of the dialog; and
execute the optimized dialog with the user. - View Dependent Claims (7, 8, 9)
-
-
10. A system comprising:
-
a first processing system configured to execute a speech-enabled browser, the browser configured to maintain information associated with a user; and
a second processing system coupled on a network to the first processing system and configured to operate as a speech-enabled site, the second processing system configured to maintain data for executing a dialog with a user of a third processing system on the network;
receive an access request corresponding to activation of a voice hyperlink by the user;
in response to receiving the access request, transmit a request to the browser for the information associated with the user;
receive the information associated with the user in response to transmitting the request;
use the information associated with the user to optimize the dialog with the user; and
execute the optimized dialog with the user. - View Dependent Claims (11, 12, 13)
-
Specification