IP Library Granted Patent US 7,136,476
Granted Patent B2
US 7,136,476 · App. 11/223,172 · Granted Nov 14, 2006

Directory assistance dialog with configuration switches to switch from automated speech recognition to operator-assisted dialog

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 7,136,476
App. No.
11/223,172
Granted
Nov 14, 2006
Kind
B2
Abstract

A method of providing a caller with a directory assistance dialog. The dialog is configurable, at any level of the dialog, from an automated speech recognition (ASR) dialog to an operator-assisted (OP) dialog. The dialog is handed off to an operator if any level of the speech recognition dialog fails. Also, a configuration switch may be set to cause the dialog to be handed off to an operator even if a response at some level of the ASR dialog is successfully recognized.

Claims (50)

1. A method of facilitating a dialog for a caller, the dialog being switchable from an automated speech recognition (ASR) path to an operator-assisted (OP) path, the method comprising:

providing a series of one or more ASR sub-dialogs, each sub-dialog including a prompt requesting information from the caller and a response from the caller;

performing an ASR analysis of each received response, wherein each ASR analysis may be successful or unsuccessful;

after each ASR sub-dialog, branching the dialog to the OP path if the ASR analysis for that sub-dialog is not successful; and

providing a configuration switch after a particular ASR sub-dialog that can be set to branch the dialog to the OP path for one or more subsequent ASR sub-dialogs even if the ASR analysis for the caller's response in the particular ASR sub-dialog is successful;

wherein the configuration switch is controlled based at least on a success rate of ASR analyses of previously received caller responses for an ASR sub-dialog that follows the particular ASR sub-dialog in the series of ASR sub-dialogs.

2. The method of claim 1 , wherein the configuration switch is controlled automatically.

3. The method of claim 1 , further comprising:

forwarding at least one response to a speech recognition tuning process; and

tuning an ASR analysis based at least on the forwarded responses.

4. The method of claim 1 , wherein the one or more ASR sub-dialogs include a first sub-dialog prompting the caller for a location response and applying an ASR analysis to the caller's location response and a second sub-dialog prompting the caller for a listing response and applying an ASR analysis to the caller's listing response.

5. The method of claim 4 , wherein the configuration switch follows the caller's listing response.

6. The method of claim 4 , wherein the configuration switch follows the caller's location response.

7. The method of claim 1 , wherein one of the ASR sub-dialogs prompts the caller to respond whether the listing is for a residence.

8. A method of facilitating a dialog for a caller, the dialog being switchable from an automated speech recognition (ASR) path to an operator-assisted (OP) path, the method comprising:

facilitating a first ASR sub-dialog with a caller and performing a first ASR analysis of a response received from the caller during the first ASR sub-dialog;

if the first ASR analysis is unsuccessful, automatically branching the dialog to the OP path;

determining whether a configuration switch is set to branch the dialog to the OP path after the first ASR analysis even if the first ASR analysis is successful;

wherein the configuration switch is controlled based at least on a success rate of ASR analyses of previously received caller responses for a second ASR sub-dialog;

if the first ASR analysis is successful, and if the configuration switch is set to branch the dialog to the OP path, branching the dialog to the OP path prior to a second ASR sub-dialog; and

if the first ASR analysis is successful, and if the configuration switch is not set to branch the dialog to the OP path, proceeding to the second ASR sub-dialog.

9. The method of claim 8 , further comprising:

forwarding multiple responses, including the response received from the caller during the first ASR sub-dialog, to a speech recognition tuning process; and

tuning the first ASR analysis based at least on the forwarded responses.

10. The method of claim 8 , wherein the directory assistance dialog includes one or more ASR sub-dialog preceding the first ASR sub-dialog.

11. The method of claim 8 , wherein the first ASR sub-dialog includes prompting the caller for a location response.

12. The method of claim 8 , wherein the first ASR sub-dialog includes prompting the caller for a listing response.

13. A computer-readable medium having computer-executable instructions for facilitating a dialog for a caller, the dialog being switchable from an automated speech recognition (ASR) path to an operator-assisted (OP) path, comprising:

instructions for facilitating a series of one or more ASR sub-dialogs, each sub-dialog including a prompt requesting information from the caller and a response from the caller;

instructions for performing an ASR analysis of each received response, wherein each ASR analysis may be successful or unsuccessful;

instructions for branching the dialog to the OP path if the ASR analysis for a particular ASR sub-dialog is not successful; and

instructions for providing a configuration switch after a particular ASR sub-dialog that can be set to branch the dialog to the OP path for one or more subsequent ASR sub-dialogs even if the ASR analysis for the caller's response in the particular ASR sub-dialog is successful;

wherein the configuration switch is controlled based at least on a success rate of ASR analyses of previously received caller responses for an ASR sub-dialog that follows the particular ASR sub-dialog in the series of ASR sub-dialogs.

14. The computer-readable medium of claim 13 , further comprising instructions for:

forwarding at least one response to a speech recognition tuning process; and

tuning an ASR analysis based at least on the forwarded responses.

15. The computer-readable medium of claim 13 , wherein the one or more ASR sub-dialogs include a first sub-dialog prompting the caller for a location response and applying an ASR analysis to the caller's location response and a second sub-dialog prompting the caller for a listing response and applying an ASR analysis to the caller's listing response.

16. The computer-readable medium of claim 15 , wherein the configuration switch follows the caller's listing response.

17. The computer-readable medium of claim 15 , wherein the configuration switch follows the caller's location response.

18. A method of facilitating a dialog for a caller, the dialog being switchable from an automated speech recognition (ASR) path to an operator-assisted (OP) path, the method comprising:

providing a series of one or more ASR sub-dialogs, each sub-dialog including a prompt requesting information from the caller and a response from the caller;

performing an ASR analysis of each received response; wherein each ASR analysis may be successful or unsuccessful;

after each ASR sub-dialog, branching the dialog to the OP path if the ASR analysis for that sub-dialog is not successful; and

providing a configuration switch after a particular ASR sub-dialog that can be set to branch the dialog to the OP path for one or more subsequent ASR sub-dialogs independent of the ASR analysis for the caller's response in the particular ASR sub-dialog;

wherein the configuration switch is controlled based at least on a previously-determined success rate of ASR analyses for an ASR sub-dialog that follows the particular ASR sub-dialog in the series of ASR sub-dialogs.

19. A method of facilitating a dialog for a caller, the dialog being switchable from an automated speech recognition (ASR) path to an operator-assisted (OP) path, the method comprising:

providing a series of one or more ASR sub-dialogs, each sub-dialog including an utterance from the caller;

performing an ASR analysis of the received caller utterance in a particular ASR sub- dialog; and

providing a configuration switch after the particular ASR sub-dialog that can be set to branch the dialog to the OP path for one or more subsequent ASR sub-dialogs independent of the ASR analysis;

wherein the configuration switch is controlled based at least on a success rate of ASR analyses of previously received caller utterances for another ASR sub-dialog in the series of ASR sub-dialogs.

Assignments (4)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 26, 2017
From: AT&T INTELLECTUAL PROPERTY I, L.P.
To: NUANCE COMMUNICATIONS, INC.
Reel/Frame 041504/0952 →
CHANGE OF NAME Recorded Mar 26, 2016
From: SBC TECHNOLOGY RESOURCES, INC.
To: SBC LABORATORIES, INC.
Reel/Frame 038262/0913 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Mar 26, 2016
From: AT&T LABS, INC.
To: AT&T INTELLECTUAL PROPERTY I, L.P.
Reel/Frame 038263/0060 →
CHANGE OF NAME Recorded Mar 26, 2016
From: SBC LABORATORIES, INC.
To: AT&T LABS, INC.
Reel/Frame 038263/0064 →