System and method of dynamically modifying a spoken dialog system to reduce hardware requirements
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G10L-021/00
출원번호
US-0690825
(2012-11-30)
등록번호
US-8600757
(2013-12-03)
발명자
/ 주소
Mazin, Rahim
Schroeter, Juergen
출원인 / 주소
AT&T Intellectual Property II, L.P.
인용정보
피인용 횟수 :
0인용 특허 :
19
초록▼
A system and method for providing a scalable spoken dialog system are disclosed. The method comprises receiving information which may be internal to the system or external to the system and dynamically modifying at least one module within a spoken dialog system according to the received information.
A system and method for providing a scalable spoken dialog system are disclosed. The method comprises receiving information which may be internal to the system or external to the system and dynamically modifying at least one module within a spoken dialog system according to the received information. The modules may be one or more of an automatic speech recognition, natural language understanding, dialog management and text-to-speech module or engine. Dynamically modifying the module may improve hardware performance or improve a specific caller's speech processing accuracy, for example. The modification of the modules or hardware may also be based on an application or a task, or based on a current portion of a dialog.
대표청구항▼
1. A method comprising: receiving a time of day associated with a time limited special offer;determining, via a processor, a call volume for a spoken dialog system based on the time limited special offer; andmodifying, via the processor, a dialog manager within the spoken dialog system from a first
1. A method comprising: receiving a time of day associated with a time limited special offer;determining, via a processor, a call volume for a spoken dialog system based on the time limited special offer; andmodifying, via the processor, a dialog manager within the spoken dialog system from a first dialog mode to a second dialog mode based on the call volume. 2. The method of claim 1, wherein the modifying of the dialog manager from the first dialog mode to the second dialog mode results in a change of computational intensity for the spoken dialog system. 3. The method of claim 2, wherein the change of computational intensity occurs when a compute load level surpasses a predetermined threshold. 4. The method of claim 1, further comprising modifying one of an automatic speech recognition module, a natural language understanding module, and a text-to-speech module based on the call volume. 5. The method of claim 1, wherein the call volume is projected. 6. The method of claim 1, wherein the modifying of the dialog manager occurs on a call-by-call basis. 7. The method of claim 1, wherein the modifying of the dialog manager is further based on received information about a particular caller. 8. A system comprising: a processor; anda computer-readable storage medium having instructions stored which, when executed by the processor, cause the processor to perform operations comprising: receiving a time of day associated with a time limited special offer;determining a call volume for a spoken dialog system based on the time limited special offer; andmodifying a dialog manager within the spoken dialog system from a first dialog mode to a second dialog mode based on the call volume. 9. The system of claim 8, wherein the modifying of the dialog manager from the first dialog mode to the second dialog mode results in a change of computational intensity for the spoken dialog system. 10. The system of claim 9, wherein the change of computational intensity occurs when a compute load level surpasses a predetermined threshold. 11. The system of claim 8, the computer-readable storage medium having additional instructions stored which result in the operations further comprising modifying one of an automatic speech recognition module, a natural language understanding module, and a text-to-speech module based on the call volume. 12. The system of claim 8, wherein the call volume is projected. 13. The system of claim 8, wherein the modifying of the dialog manager occurs on a call-by-call basis. 14. The system of claim 8, wherein the modifying of the dialog manager is further based on received information about a particular caller. 15. A computer-readable storage device having instructions stored which, when executed by a computing device, cause the computing device to perform operations comprising: receiving a time of day associated with a time limited special offer;determining a call volume for a spoken dialog system based on the time limited special offer; andmodifying a dialog manager within the spoken dialog system from a first dialog mode to a second dialog mode based on the call volume. 16. The computer-readable storage device of claim 15, wherein the modifying of the dialog manager from the first dialog mode to the second dialog mode results in a change of computational intensity for the spoken dialog system. 17. The computer-readable storage device of claim 16, wherein the change of computational intensity occurs when a compute load level surpasses a predetermined threshold. 18. The computer-readable storage device of claim 15, the computer-readable storage device having additional instructions stored which result in the operations further comprising modifying one of an automatic speech recognition module, a natural language understanding module, and a text-to-speech module based on the call volume. 19. The computer-readable storage device of claim 15, wherein the call volume is projected. 20. The computer-readable storage device of claim 15, wherein the modifying of the dialog manager occurs on a call-by-call basis.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (19)
Amirghodsi Siamak (Prairie View IL) Daneshbodi Farnoud (Prairie View IL), Adaptive natural language computer interface system.
Brode Holger W.,DEX ; Schroer Olaf,DEX ; Marschner Jens F.,DEX ; Aust Harald,DEX ; Marti Del Olmo Enrique,DEX, Method and apparatus for executing a human-machine dialogue in the form of two-sided speech as based on a modular dialogue structure.
Cohen, Michael H.; Wax, Tracy D.; Prince, Michael A.; Ehrlich, Steven C., Method and apparatus for optimizing a spoken dialog between a person and a machine.
Hancock,Peter J.; Hansen,Lee B.; Lenz,Daniel J.; Mikkelsen,Hans C.; Tanning,Ronald S., System and method for scaling performance of a data processing system.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.