Load-shared distribution of a speech system

• US 20030014254A1
• Filed: 07/11/2001
• Published: 01/16/2003
• Est. Priority Date: 07/11/2001
• Status: Abandoned Application

• Current Assignee: Appiant Technologies, Inc.
• Original Assignee: Appiant Technologies, Inc.
• Inventors: Zhang, You, Ram, Mani
• Application Number:
  US09/904,372
• Publication Number:
  US 20030014254A1
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

A method is afforded for providing a load-shared distribution architecture speech system over a network. A speech system is disassembled into independent modules. The modules are divided into separate parts. A portion of a computational capacity of at least one of a plurality of devices utilized by the separate parts of the modules is determined. The modules are then deployed over a network to at least one of the plurality of devices, depending on the computational capacity thereof.

Claims

1. A method for providing a load-shared distribution architecture for a speech system over a network comprising the steps of:

(a) disassembling a speech system into independent modules;

(b) dividing the modules into separate parts;

(c) determining a portion of a computational capacity of at least one of a plurality of devices utilized by the separate parts of the modules; and

(d) deploying the modules over a network to at least one of the plurality of devices, depending on the computational capacity thereof.

2. The method as recited in claim 1, wherein the speech system includes at least one of an automatic speech recognition system (ASR), a text-to-speech systems (TTS), and a translation system.

3. The method as recited in claim 1, wherein the network includes at least one of a wide area network, a local area network, a peer to peer network, a wireless network, and a public telephone network.

4. The method as recited in claim 3, wherein the speech system services are carried out over the wide area network utilizing packet-switching.

5. The method as recited in claim 1, wherein the speech system services are carried out in a customer service environment.

6. The method as recited in claim 1, wherein at least one of the plurality of devices includes at least one of a server, a personal computer, a personal digital assistance, a cell phone, a telephone, web TV, a network router, a wireless device, and a bluetooth enabled device.

7. The method as recited in claim 1, wherein deploying the modules includes at least one of an automated process and a manual process.

8. The method as recited in claim 1, further comprising the steps of providing a translation.

9. The method as recited in claim 8, wherein the steps of providing the translation include receiving speech associated with a first language, transcribing the speech from the first language into text, translating the speech from the first language into text associated with a second language, and converting the text associated with the second language into speech associated with the second language.

10. A computer program embodied on a computer readable medium for providing a load-shared distribution architecture for a speech system over a network comprising the steps of:

(a) a code segment that disassembles a speech system into independent modules;

(b) a code segment that divides the modules into separate parts;

(c) a code segment that determines a portion of a computational capacity of at least one of a plurality of devices utilized by the separate parts of the modules; and

(d) a code segment that deploys the modules over a network to at least one of the plurality of devices, depending on the computational capacities thereof.

11. The computer program as recited in claim 10, wherein the speech system includes at least one of an automatic speech recognition system (ASR), a text-to-speech system (TTS), and a translation system.

12. The computer program as recited in claim 10, wherein the network includes at least one of a wide area network, a local area network, a peer to peer network, a wireless network, and a public telephone network.

13. The computer program as recited in claim 12, wherein the speech system services are carried out over the wide area network utilizing packet-switching.

14. The computer program as recited in claim 10, wherein the speech system services are carried out in a customer service environment.

15. The computer program as recited in claim 10, wherein at least one of the plurality of devices includes at least one of a server, a personal computer, a personal digital assistance, a cell phone, a telephone, and web TV, a network router, a wireless device, and a bluetooth enabled device.

16. The computer program as recited in claim 10, wherein deploying the modules includes at least one of an automated process and a manual process.

17. The computer program as recited in claim 10, further comprising a code segment for providing a translation.

18. The computer program as recited in claim 17, wherein the code segment for providing a translation further includes a code segment from at least one of the group consisting of a code segment that receives speech associated with a first language, a code segment that transcribes the speech from the first language into text, a code segment that translates the speech from the first language into text associated with a second language, and a code segment that converts the text associated with the second language into speech associated with the second language.

20. The system as recited in claim 19, wherein the speech system includes at least one of an automatic speech recognition systems (ASR), a text-to-speech systems (TTS), and a translation system.

21. The system as recited in claim 19, wherein the network includes at least one of a wide area network, a local area network, a peer to peer network, a wireless network, and a public telephone network.

22. The system as recited in claim 21, wherein the speech system services are carried out over the wide area network utilizing packet-switching.

23. The system as recited in claim 19, wherein the speech system services are carried out in a customer service environment.

24. The system as recited in claim 19, wherein at least one of the plurality of devices includes at least one of a server, a personal computer, a personal digital assistance, a cell phone, a telephone, web TV, a network router, a wireless device, and a bluetooth enabled device.

25. The system as recited in claim 19, wherein deploying the modules includes at least one of an automated process and a manual process.

26. The system as recited in claim 19, further comprising logic that provides a translation.

27. The system as recited in claim 26, wherein the logic for providing a translation further includes logic from at least one of the group consisting of logic that receives speech associated with a first language, logic that transcribes the speech from the first language into text, logic that translates the speech from the first language into text associated with a second language, and logic that converts the text associated with the second language into speech associated with the second language.

19. A system for providing a load-shared distribution architecture for a speech system over a network comprising the steps of:

(a) logic that disassembles a speech system into independent modules;

(b) logic that divides the modules into separate parts;

(c) logic that determines a portion of a computational capacity of a at least one of a plurality of devices utilized by the separate parts of the modules; and

(d) logic that deploys the modules over a network to at least one of the plurality of devices, depending on the computational capacity thereof.