Dialog interface system

• US 6,330,539 B1
• Filed: 01/21/1999
• Issued: 12/11/2001
• Est. Priority Date: 02/05/1998
• Status: Expired due to Term

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Maeda, Yoshiharu, Naito, Hirohisa, Takayama, Kuniharu, Matsuoka, Masahiro, Koshiba, Takeshi, Hosogi, Shinya, Sekiguchi, Minoru
• Primary Examiner(s): Korzuch, William
• Assistant Examiner(s): Azad, Abul K.
• Application Number:
  US09/234,472
• Time in Patent Office: 1,055 Days
• Field of Search: 704/200, 704/231, 704/258, 704/251, 704/257, 704/270, 704/272, 704/275
• US Class Current: 704/275
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

In the dialog interface apparatus of the present invention, input speech is converted to an input semantic representation by a speech recognition unit, and a dialog management unit outputs an output semantic representation that corresponds to the input semantic representation, based on the input semantic representation obtained by the speech recognition unit. Having received the output semantic representation from the dialog management unit, a speech synthesis unit converts the output semantic representation to output speech identifying a specific dialog target and outputs the output speech. Further, the dialog management unit outputs to an innate operation execution unit an innate operation command that corresponds to the input semantic representation. The innate operation execution unit receives the innate operation command from the dialog management unit and executes an operation corresponding to the innate operation command.

Claims

1. A dialog interface system facilitating communication between humans and inanimate objects, among humans, and among inanimate objects, comprising:

a speech recognition unit converting input speech, identifying a party from among the humans and the inanimate objects initiating the input speech, to an input semantic representation;

a dialog management unit outputting an output semantic representation corresponding to said input semantic representation, based on the input semantic representation obtained by the speech recognition system, and identifying a specific dialog target from among the humans and inanimate objects to which the input speech is directed; and

a speech synthesis unit receiving the output semantic representation from the dialog management unit, converting said output semantic representation to output speech, for which the specific dialog target is designated, and outputting the output speech.

2. The dialog interface system according to claim 1, wherein

the dialog management unit identifies an origin of the input speech, based on the input semantic representation received from the speech recognition unit, and outputs the output semantic representation after consideration of the identified origin.

3. The dialog interface system according to claim 1, wherein

the speech recognition unit outputs a delay command that delays the output of output speech, to the speech synthesis unit, during the time that input speech is being inputted.

4. The dialog interface system according to claim 1, further comprising:

an innate operation execution unit receiving an innate operation command from the dialog management unit and executing a function corresponding to said innate operation command, and wherein

said dialog management unit outputs the innate operation command that corresponds to the input semantic representation to the innate operation execution unit, based on said input semantic representation obtained by the speech recognition unit.

5. The dialog interface system according to claim 4, wherein

the dialog management unit identifies an origin of the input speech, based on the input semantic representation received from the speech recognition unit, and outputs the innate operation command after consideration of the identified origin.

6. The dialog interface system according to claim 4, wherein

the speech synthesis unit and the innate operation execution unit synchronize, by way of a synchronization notification signal, the output of the output speech and the innate operation.

7. The dialog interface system according to claim 4, wherein

the dialog management unit comprises a dialog rules storage unit storing an aggregate of dialog rules for the input semantic representation and the output semantic representation, and outputs at least one of the output semantic representation and innate operation command that correspond to the input semantic representation inputted from the speech recognition unit, based on the dialog rules stored in said dialog rules storage unit.

8. The dialog interface system according to claim 7, wherein

the dialog management unit comprises, with respect to the dialog rules that are stored in the dialog rules storage unit, an add function, a modify function, and a delete function.

9. A dialog interface apparatus facilitating communication between humans and inanimate objects, among humans, and among inanimate objects, comprising:

a speech recognition unit converting input speech, identifying a party from among the humans and the inanimate objects initiating the input speech, to an input semantic representation;

a dialog management unit identifying an origin of said input speech, based on said input semantic representation obtained by said speech recognition unit, identifying a target of output speech from among the humans and inanimate objects, and outputting a corresponding innate operation command based on the identified origin and said input semantic representation; and

an innate operation execution unit executing an operation corresponding to the innate operation command.

10. A dialog interface apparatus facilitating communication between humans and inanimate objects, among humans, and among inanimate objects, comprising:

a dialog management unit system identifying by whom from among the humans and the inanimate objects input speech is initiated and a dialog target from among the humans and inanimate objects to which the input speech is directed, and outputting an output semantic representation and data specifying the dialog target that is to recognize said output semantic representation; and

a speech synthesis unit converting the output semantic representation and said data to output speech that represents said output semantic representation and said dialog target, based on the data received from the dialog management unit, and outputting said output speech.

11. A method, utilizing a dialog management apparatus, that executes processes based on a dialog and facilitates communication between humans and inanimate objects, among humans, and among inanimate objects, comprising:

converting input speech, identifying a party from among the humans and the inanimate objects initiating the input speech, to an input semantic representation;

generating an output semantic representation that corresponds to the input semantic representation, based on said input semantic representation;

identifying a specific dialog target from among the humans and inanimate objects to which the input speech is directed; and

converting said output semantic representation to output speech, for which the specific dialog target is designated, and outputting said output speech.

12. The method according to claim 11, further comprising:

identifying an origin of the input speech, based on the input semantic representation; and

outputting the output semantic representation upon consideration of said identified origin.

13. The method according to claim 11, further comprising:

outputting a delay command that delays the output of the output speech, during the time that input speech is being inputted.

14. The method according to claim 11, further comprising:

dismissing one of the input semantic representations, when one of the successive input semantic representations and the output semantic representations corresponding to the other input semantic representations are identical.

15. The method according to claim 11, further comprising:

generating an innate operation command that corresponds to the input semantic representation, based on said input semantic representation; and

receiving said innate operation command and executing an operation corresponding to said innate operation command.

16. The method according to claim 15, further comprising:

identifying an origin of the input speech, based on the input semantic representation; and

outputting the innate operation command upon consideration of said identified origin.

17. The method according to claim 15, further comprising:

outputting at least one of the output semantic representation that corresponds to the input semantic representation and the innate operation command.

18. The method according to claim 15, further comprising:

synchronizing, by way of a synchronization notification signal, an output of the output speech and an execution of the innate operation.

19. A method, utilizing a dialog management apparatus, that executes processes based on a dialog and facilitates communication between humans and inanimate objects, among humans, and among inanimate objects, comprising:

converting input speech, identifying a party from among the humans and the inanimate objects initiating the input speech, to an input semantic representation;

identifying an origin of said input speech, based on said input semantic representation, identifying a target from among the humans and inanimate objects to which the input speech is directed, and outputting a corresponding innate operation command based on the identified origin and said input semantic representation; and

executing a function corresponding to the innate operation command.

20. A method, utilizing a dialog management apparatus, that executes processes based on a dialog and facilitates communication between humans and inanimate objects, among humans, and among inanimate objects, comprising:

identifying by whom from among the humans and the inanimate objects input speech is initiated and a dialog target from among the humans and inanimate objects to which the input speech is directed;

outputting an output semantic representation and data identifying the dialog target that is to recognize said output semantic representation; and

converting the output semantic representation and said data to output speech that represents said output semantic representation and said dialog target.

21. A computer-readable medium including a program for causing a computer to execute a processing method based on a dialog, said processing method facilitating communication between humans and inanimate objects, among humans, and among inanimate objects and comprising:

converting input speech, identifying a party from among the humans and the inanimate objects initiating the input speech, to an input semantic representation;

generating an output semantic representation that corresponds to said input semantic representation, based on said input semantic representation;

identifying a specific dialog target from among the humans and inanimate objects to which the input speech is directed; and

converting said input semantic representation to output speech, for which the specific dialog target is designated, and outputting the output speech.

22. The computer-readable medium according to claim 21, the processing method further comprising:

identifying an origin of the input speech, based on the input semantic representation; and

outputting the output semantic representation upon consideration of said identified origin.

23. The computer-readable medium according to claim 21, the processing method further comprising:

outputting a delay command that delays the output of the output speech, during the time that input speech is being inputted.

24. The computer-readable medium according to claim 21, the processing method further comprising:

dismissing one of the input semantic representations, when one of the successive input semantic representations and the output semantic representations corresponding to the other input semantic representations are identical.

25. The computer-readable medium according to claim 21, the processing method further comprising:

generating an innate operation command that corresponds to the input semantic representation, based on said input semantic representation; and

receiving said innate operation command and executing an operation corresponding to said innate operation command.

26. The computer-readable medium according to claim 25, the processing method further comprising:

identifying an origin of the input speech, based on the input semantic representation; and

outputting the innate operation command upon consideration of the identified origin.

27. The computer-readable medium according to claim 25, the processing method further comprising:

outputting at least one of the output semantic representation that corresponds to the input semantic representation and the innate operation command.

28. The computer-readable medium according to claim 25, the processing method further comprising:

synchronizing, by way of a synchronization notification signal, an output of the output speech and an execution of the innate operation.

29. A computer-readable medium including a program for causing a computer to execute a processing method based on a dialog, said processing method facilitating communication between humans and inanimate objects, among humans, and among inanimate objects and comprising:

converting input speech, identifying a party from among the humans and inanimate objects initiating the input speech, to an input semantic representation;

identifying an origin of said input speech, based on said input semantic representation, and outputting a corresponding innate operation command based on the identified origin and said input semantic representation;

identifying a target from among the humans and inanimate objects to which the input speech is directed; and

executing an operation corresponding to said innate operation command.

30. A computer-readable medium including a program for causing a computer to execute a processing method based on a dialog, said processing method facilitating communication between humans and inanimate objects, among humans, and among inanimate objects and comprising:

identifying by whom from among the humans and inanimate objects the input speech is initiated and a dialog target from among the humans and inanimate objects to which the input speech is directed;

outputting an output semantic representation and data identifying the dialog target that is to recognize said output semantic representation; and

converting said output semantic representation and said data to output speech that represents said output semantic representation and said dialog target, based on said data, and outputting the output speech.