VOICE RESPONSE SYSTEM

• US 20070198272A1
• Filed: 02/09/2007
• Published: 08/23/2007
• Est. Priority Date: 02/20/2006
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Tahara, Yoshinori, Horioka, Masaru, Atake, Yoshinori
• Granted Patent: US 8,095,371 B2
• Time in Patent Office: Days
• 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: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals

Abstract

A voice response system attempts to respond to spoken user input and to provide computer-generated responses. If the system decides it cannot provide valid responses, the current state of user session is determined and forwarded to a human operator for further action. The system maintains a recorded history of the session in the form of a dialog history log. The dialog history and information as to the reliability of past speech recognition efforts is employed in making the current state determination. The system includes formatting rules for controlling the display of information presented to the human operator.

Claims

1. An automated voice response system comprising:

a voice response unit for recognizing user speech and providing spoken responses to such speech;

a dialog history log for storing a record of a dialog between the user and the voice response unit;

a dialog state diagram definition file for defining each expected dialog state during a session between the user and the voice response unit;

a dialog state determination model for defining a process for determining the current dialog state during the session between the user and the voice response unit;

a dialog information analyzing unit, responsive to a determination by the voice response unit that it cannot provide a valid response to the user, for determining the current dialog state between the user and the voice response unit based on the dialog history log, the dialog state diagram definition file, and the dialog state determination model; and

a dialog information display unit for receiving the determined current dialog state and visually presenting it for use by a human operator.

2. The voice response system according to claim 1, wherein the dialog history log includes at least one speech recognition result occurring between the start of the session and time the dialog information analyzing unit determines the current dialog state for presentation to a human operator, a reliability indicator for the speech recognition result, one or more recognized prior inputs from the user, information identifying the system response to the speech recognition result, information indicating the start of the session, and information indicating the time at which the dialog information analyzing unit decides it cannot provide a valid response to the user.

3. The voice response system according to claim 1, wherein the dialog state diagram definition file defines each expected dialog state and the format in which each dialog state and associated input information is to be displayed to the human operator.

4. The voice response system according to claim 1, wherein the dialog state determination model includes empirical data and/or algorithms for determining a current dialog state from the dialog history log.

5. The voice response system according to claim 1, wherein the dialog information analyzing unit calculates reliability of an item entered by the user and determines an input history.

6. The voice response system according to claim 1, wherein information displayed on the dialog information display unit includes a transition diagram illustration transitions between dialog states, said display unit visually highlighting the determined current dialog state.

7. The voice response system according to claim 1, wherein the dialog information display unit uses the dialog history log to obtain, with respect to an item entered by the user, reliability of a result of speech recognition performed by the voice response unit, and displays the item in a particular color depending on the degree of reliability.

8. The voice response system according to claim 1, wherein the dialog information display unit uses the dialog history log to obtain, with respect to an item entered by the user, an input history of the user, and displays the item in a different character size according to the order in the input history.

9. A method for providing voice responses to spoken input items received from a user, comprising:

providing computer recognition of spoken input items;

providing system responses to spoken input items;

storing, in a dialog history log, a record of recognized spoken input items and system responses thereto, said record representing a dialog history;

responsive to a determination the system cannot provide a valid system response to spoken input items, using a dialog state determination model to determine the current state of the dialog with the user based on the dialog history log and a dialog state diagram definition file defining each expected dialog state; and

forwarding the determined current dialog state to a visual information display for use by a human operator.

10. The method according to claim 9, wherein the dialog history log includes at least one speech recognition result occurring between the start of user input and the time of forwarding of dialog state information to the human operator, a reliability value for the speech recognition result, an already entered item in the speech recognition result, information identifying any system response to the speech recognition result, information indicating the start of the user input, and information indicating the time of forwarding.

11. The method according to claim 9, wherein the dialog state diagram definition file defines each expected dialog state and the format in which each dialog state and associated input information is to be displayed to the human operator.

12. The method according to claim 9, wherein the dialog state determination model includes empirical data and/or algorithms for determining a current dialog state from the dialog history log.

13. The method according to claim 9, wherein, in the dialog information analyzing step, the reliability of an item entered by the user is calculated and an input history is taken into account.

14. The method according to claim 9, further including the step of highlighting the current dialog state in the information displayed to the human operator.

15. A computer program product comprising machine readable media embodying program code for enabling voice responses to be provided to a user based on spoken input provided by the user, said program code when executed on a computer, causing the computer to perform a method comprising the steps of:

providing computer recognition of spoken input items;

providing system responses to spoken input items;

storing, in a dialog history log, a record of recognized spoken input items and system responses thereto, said record representing a dialog history;

responsive to a determination the system cannot provide valid system responses to spoken input items, using a dialog state determination model to determine the current state of the dialog with the user based on the dialog history log and a dialog state diagram definition file defining each expected dialog state; and

forwarding the determined current dialog state to a visual information display for use by a human operator.

16. The computer program product according to claim 15 wherein the program code causes the dialog history log to include at least one speech recognition result occurring between the start of user input and the time of forwarding of dialog state information to the human operator, a reliability value for the speech recognition result, an already entered item in the speech recognition result, information identifying any system response to the speech recognition result, information indicating the start of the user input, and information indicating the time of forwarding.

17. The computer program product according to claim 15, wherein the program code causes the dialog state diagram definition file to include a definition of each expected dialog state and the format in which each dialog state and associated input information is to be displayed to the human operator.

18. The computer program product according to claim 15 wherein the program code causes storage of empirical data and/or algorithms defining at least in part the dialog state determination model.