Voice-enabled user interface for voicemail systems

• US 20020097848A1
• Filed: 06/22/2001
• Published: 07/25/2002
• Est. Priority Date: 01/22/2001
• Status: Active Grant

• Current Assignee: Intellisync Corporation (Nokia Corporation)
• Original Assignee: Intellisync Corporation (Nokia Corporation)
• Inventors: Nam, Dong-Kyun, Kweon, Tae-Deok, Mason, Makani, Willesen, Jon, Wesemann, Darren L.
• Granted Patent: US 6,731,724 B2
• Time in Patent Office: Days
• US Class Current: 379/88.18
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: H04M 2201/40 using speech recognition speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/533 Voice mail systems
• CPC Class Codes: H04M 3/53308 Message originator indirectly connected to the message centre, e.g. after detection of busy or absent state of a called party

Abstract

A voice-enabled user interface and method for enabling a user that is providing audio and vocal input to access data from telephone service systems that are only responsive to dual tone multi-frequency (“DTMF”) signals. A user access the voice-enabled user interface with a telephone device and provides input that is translated into a DTMF translation that can be recognized by DTMF telephone service system. A template of the voice-enabled user interface maps menu states, prompts, and acceptable inputs of the DTMF telephone service system. The template also monitors the current state of the telephone service system at all times. The invention also enables a user to jump from one menu state to another menu state of the telephone service system without having to enter input for each menu state between the first and the second menu states.

Claims

1. In a network that includes a voice-enabled user interface in communication with a telephone device and a telephone service system, a method performed at the voice-enabled user interface for enabling a user at the telephone device to access data from the telephone service system with user input that is not recognizable by the telephone service system, the method comprising the acts of:

receiving a prompt from the telephone service system;

transferring said prompt to the user at the telephone device;

receiving a user input that is entered at the telephone device, wherein said user input comprises a request for data from the telephone service system, and wherein said user input is not recognizable by the telephone service system;

transmitting a translation of the user input to the telephone service system, wherein said translation of the user input is recognizable by the telephone service system;

receiving the requested data from the telephone service system; and

transferring said requested data to the telephone device.

2. A method as defined in claim 1, wherein said telephone service system comprises a menu having multiple menu states, each menu state having state specific prompts of which said prompt is one of the state specific prompts.

3. A method as defined in claim 2, whereupon receiving said prompt the method further comprises the act of determining which of the multiple menu states the telephone service system is in.

4. A method as defined in claim 3, wherein the act of determining which of the multiple menu states the telephone service system is in comprises the act of using a template to determine which of the multiple menu states said prompt is located in, wherein said template maps the multiple menu states and state specific prompts.

5. A method as defined in claim 4, wherein the act of using a template to determine which of the multiple menu states said prompt is located in further comprises the act of identifying said prompt.

6. A method as defined in claim 5, wherein said prompt comprises speech having multiple sound wave patterns that occur in segments over a period of time.

7. A method as defined in claim 6, wherein the act of identifying said prompt comprises the acts of determining the quantity of said segments and the period of time over which each of said segments occur and comparing said segments and period of time with information stored in said template.

8. A method as defined in claim 1, wherein the act of identifying said prompt comprises performing spectral speech analysis of the multiple recognizable sound wave patterns.

9. A method as defined in claim 1, wherein the user input comprises audio input that is generated by the user speaking into the telephone device.

10. A method as defined in claim 9, further comprising the act of performing speech recognition of the user input.

11. A method as defined in claim 10, wherein the telephone service system only recognizes dual tone multi-frequency signals.

12. A method as defined in claim 11, wherein the content of the translation of the user input that is transmitted to the telephone service system depends upon which of the multiple menu states the telephone service system is in.

13. A method as defined in claim 12, wherein the user input is received prior to the act of receiving the prompt from the telephone service system, and wherein said translation of the user input causes the telephone service system to move from a first of the multiple menu states to a second of the multiple menu states.

14. A method as defined in claim 13, wherein the translation of the user input can only be recognized by the telephone service system when the telephone service system is a third of the multiple menu states.

15. A method as defined in claim 14, wherein prior transmitting the translation of the user input to the telephone service system the voice-enabled user interface transmits output to the telephone service system that causes the telephone service system to move from the third of the multiple menu states to the first of the multiple menu states, such that the translation of the second user input can be recognized by the telephone service system.

16. A method as defined in claim 1, wherein prior to the act of receiving a prompt from the telephone service system, the method further comprises the act of accessing the telephone service system in response to an initial user input.

17. A method as defined in claim 16, wherein the initial user input includes authentication information that verifies the identity of the user.

19. A method as defined in claim 18, wherein said prompt is generated at the telephone service system.

20. A method as defined in claim 18, wherein said prompt is generated at the voice-enabled user interface.

21. A method as defined in claim 18, wherein said first and second user input comprise audio input that is generated by the user speaking.

22. A method as defined in claim 18, wherein said data is transmitted through a simplex channel of the voice-enabled user interface.

23. A method as defined in claim 18, wherein said second user input causes the telephone service system to jump from a first menu state to a second menu state.

24. A method as defined in claim 23, wherein said telephone service system can only recognize the second user input when said telephone service system is in a third menu state.

25. A method as defined in claim 24, wherein said second user input is transmitted prior to the user receiving said prompt from the voice-enabled user interface.

27. A computer program product as defined in claim 26, wherein the computer-readable medium further comprises program code means for authenticating the identity of the user.

28. A computer program product as defined in claim 26, wherein the computer-readable medium further comprises program code means for providing the telephone service system with information that authenticates the identity of the user.

29. A computer program product as defined in claim 26, wherein the computer-readable medium further comprises program code means for controlling the transmission of data between the telephone service system and the telephone device, wherein said program code means comprises program code means for connecting and disconnecting channels of communication between the telephone service system and the telephone device.

30. A computer program product as defined in claim 26, wherein the program code means for determining which state of the multiple states the telephone service system is in comprises a template, wherein said template comprises a map of menu states, prompts and acceptable inputs of the telephone service system.

31. A computer program product as defined in claim 30, wherein the program code means for determining which state of the multiple states the telephone service system is in further comprises program code means for tracking changes to the state of the telephone service system and program code means for determining which state of the multiple states the telephone service system is in at all times;

18. In a network that includes a voice-enabled user interface in communication with a telephone device and a telephone service system, a method performed at the telephone device for enabling a user to access data from the telephone service system with user input that is not recognizable by the telephone service system, the method comprising the acts of:

transmitting a first user input to the voice-enabled user interface, wherein said first user input causes the voice-enabled user interface to access the telephone service system;

receiving a prompt from the voice-enabled user interface;

transmitting a second user input to the voice-enabled user interface, wherein said second user input comprises a request for data from the telephone service system, wherein said second user input is not recognizable by the telephone service system, said second user input causing the voice-enabled user interface to transmit to the telephone service system a translation of the second user input that is recognizable by the telephone service system; and

receiving data from the telephone service system that is responsive to the second user input.

26. A computer program product for implementing, in a voice-enabled user interface that is in communication with a telephone device and a telephone service system, a method for enabling a user using the telephone device to access data from the telephone service system with user input that is not recognizable by the telephone service system, the computer program product comprising:

a computer-readable medium carrying computer-executable instructions for implementing the method, the computer-executable instructions comprising;

program code means for accessing the telephone service system in response to user input;

program code means for receiving a prompt from the telephone service system;

program code means for transferring said prompt to the telephone device;

program code means for receiving user input comprising a request for data from the telephone service system;

program code means for determining which state of multiple states the telephone service system is in;

program code means for transmitting output to the telephone service system that causes the telephone service system to transmit requested data to the telephone device; and

program code means for transmitting output to the telephone service system that causes the telephone service system to move from a first of the multiple states to a second of the multiple states.