Changing characteristics of a voice user interface

• US 7,047,197 B1
• Filed: 09/29/2000
• Issued: 05/16/2006
• Est. Priority Date: 09/29/2000
• Status: Expired due to Fees

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Bennett, Steven M.
• Primary Examiner(s): Knepper, David D.
• Assistant Examiner(s): Han, Qi
• Application Number:
  US09/675,907
• Time in Patent Office: 2,055 Days
• Field of Search: 704/275, 704/270.1, 704/270, 704/233, 704/257, 379/88.17
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: H04M 2201/40 using speech recognition
• CPC Class Codes: H04M 2250/74 with voice recognition means

Abstract

The invention generally relates to a method, apparatus, and system capable of changing a voice user interface possessing both operational characteristics and security characteristics based upon user-specific contextual information. The voice processing system consists of at least the following components: a voice user interface possessing both operational characteristics and security characteristics; a database to store user-specific contextual information; and a computer program to use the user-specific contextual information to dynamically change the operational characteristics of the voice user interface.

Claims

1. A voice information system, comprising:

a voice user interface to enable a user to interact with the system using a communication device;

a database to store user-specific contextual information and heterogeneous information; and

a top database table, wherein the top database table is generated from the database, wherein items in the top database table are assigned a priority level based upon the user-specific contextual information;

wherein content is communicated to the user when the user requests information or when the system intelligently chooses to present information to the user based on the priority level assigned to information in the top database table, wherein when the system intelligently chooses to present information to the user based on the priority level assigned to the information in the top database table, the voice user interface to notify the user by directly phoning the user when the system intelligently recognizes that a high priority item from the ton database table requires immediate attention by the user.

2. The voice information system of claim 1, wherein the system dynamically changes the voice user interface and content communicated to the user based upon the user-specific contextual information, environmental information, a sensitivity level of the information being communicated, and the priority level assigned to the information being communicated.

3. The voice information system of claim 2, wherein environmental information comprises:

details of the communication device of the user;

details of a communication channel used by the user to communicate with the system; and

audio scene information.

4. The voice information system of claim 1, wherein the voice user interface to characterize channel characteristics of the communication device of the user and to compare the channel characterization of the communication device to channel characteristics of classes of devices stored in the database.

5. The voice information system of claim 1, wherein the voice user interface to estimate audio scene characteristics associated with a current location of the user and to compare the audio scene characterization to audio scenes stored in the database.

6. The voice information system of claim 1, wherein the voice user interface to detect a sound level of a user'"'"'s voice, and if the sound level is above a barge-in threshold level, the voice user interface to stop generating sound to enable better recognition of the sound that is being received by the system.

7. The voice information system of claim 6, wherein environmental information and the user-specific contextual information is used to determine barge-in threshold levels to reduce false barge-in occurrences.

8. The voice information system of claim 1, wherein when the system intelligently chooses to present information to the user based on the priority level assigned to the information in the top database table, the voice user interface to notify the user using a least intrusive method of communication when the system intelligently recognizes that an item from the top database table does not require immediate attention by the user and to escalate the intrusiveness of the method of communication if a response is not received within a predetermined period of time.

9. The voice information system of claim 8, wherein the method of communication comprises at least one of an email, an instant message, a page, a voice message, or a direct phone call.

10. The voice information system of claim 1, wherein the voice user interface to generate grammar files, wherein the grammar files comprise anticipated responses based on prompted options made available to the user.

11. The voice information system of claim 1, wherein the voice user interface to generate customized grammar files for complex interactions between the system and the user.

12. The voice information system of claim 1, wherein the voice user interface to analyze a voice of the user to authenticate and verify the identity of the user.

13. The voice information system of claim 12, wherein to analyze the voice of the user to authenticate and verify the identity of the user includes to compare the voice of the user with a voice print previously obtained from the user, to provide a confidence level in the authenticity of the identification of the user, and if the confidence level is above a predetermined threshold, to indicate that the identification of the user is verified by the system.

14. The voice information system of claim 1, wherein the voice user interface to mark the information in the database with a privacy level and a security level.

15. The voice information system of claim 1, wherein the voice user interface to determine a security and privacy rating for a communication to a user based upon environmental information of the user.

16. The voice information system of claim 15, wherein if the environmental information of the user indicates a low security rating, the system to dynamically alter the voice user interface to require additional authentication responses from the user.

17. The voice information system of claim 1, wherein user-specific contextual information comprises:

an identity of the user;

a current location of the user;

a current task of the user;

a calendar of the user; and

a schedule of the user.