System and method of dynamically modifying a spoken dialog system to reduce hardware requirements
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.
1. A method comprising:
receiving a time of day and an associated prediction of call volume to a spoken dialog system based on a time limited special offer; and
modifying, via a processor, a dialog manager module within the spoken dialog system according to the time of day and the associated prediction of call volume, from a first dialog mode to a second dialog mode, wherein modifying the dialog manager module results in a change of computational intensity for the spoken dialog system.
2. The method of claim 1 , wherein modifying the dialog manager module within the spoken dialog system further comprises modifying an automatic speech recognition module, a natural language understanding module, and a text-to-speech module.
3. The method of claim 2 , further comprising:
receiving a plurality of calls to the spoken dialog system, and wherein modifying the dialog manager module within the spoken dialog system occurs on a call-by-call basis.
4. The method of claim 2 , wherein modifying the dialog manager module within the spoken dialog system further comprises modifying each of the automatic speech recognition module, the natural language understanding module and the text-to-speech module according to parameters individually associated with each respective module.
5. The method of claim 4 , further comprising, when both the automatic speech recognition module and the text to speech module are modified, selecting a smaller beam width in searching candidates, wherein hardware requirements for the spoken dialog system may be reduced.
6. The method of claim 1 , wherein modifying the dialog manager module within the spoken dialog system further comprises modifying an accuracy operating point of the dialog manager module.
7. The method of claim 1 , wherein the change in computation intensity occurs when a compute load level surpasses a predetermined threshold.
8. The method of claim 1 , wherein modifying the dialog manager module within the spoken dialog system further comprises modifying an accuracy of the dialog manager module to speed up a response time.
9. The method of claim 1 , wherein modifying the dialog manager module within the spoken dialog system further comprises adjusting a predetermined operating point.
10. The method of claim 1 , wherein modifying the dialog manager module more efficiently utilizes compute resources upon which the spoken dialog system runs.
11. The method of claim 1 , further comprising:
receiving a plurality of calls to the spoken dialog system, and wherein modifying the dialog manager module is based on received information about a particular caller.
12. A system comprising:
a processor; and
a computer-readable storage medium storing instructions which, when executed by the processor, cause the processor to perform a method comprising:
receiving a time of day and an associated prediction of call volume to the spoken dialog system based on a time limited special offer; and
modifying a dialog manager module within the spoken dialog system, according to the time of day and the associated prediction of call volume, from a first dialog mode to a second dialog mode, wherein modifying the dialog manager module results in a change of computational intensity of the spoken dialog system.
13. The system of claim 12 , wherein the computer-readable storage medium stores additional instructions which result in the method further comprising:
receiving a plurality of calls to the spoken dialog system, and wherein modifying the dialog manager module within the spoken dialog system occurs on a call-by-call basis.
14. The system of claim 12 , wherein modifying the dialog manager module further comprises modifying an accuracy operating point of the dialog manager module.
15. The system of claim 12 , wherein the computer-readable storage medium stores additional instructions which result in the method further comprising:
receiving a plurality of calls to the spoken dialog system; and
wherein modifying the dialog manager module within the spoken dialog system is further based on a rating assigned to each particular caller of the plurality of calls.
16. A non-transitory computer-readable medium storing instructions for controlling a computing device to perform a method comprising:
receiving a time of day and an associated prediction of call volume to a spoken dialog system based on a time limited special offer; and
modifying a dialog manager module within the spoken dialog system, according to the time of day and the associated prediction of call volume received, from a first dialog mode to a second dialog mode, wherein modifying the dialog manager module results in a change of computational intensity for the spoken dialog system.
17. The non-transitory computer-readable storage medium of claim 16 , wherein the spoken dialog system is associated with one of a customer care application, a technical help desk application and a sales application.
18. The non-transitory computer-readable storage medium of claim 16 , wherein modifying the dialog manager module within the spoken dialog system further comprises modifying a hardware resource.