Distributed speech recognition system with speech recognition engines offering multiple functionalities

• US 6,785,654 B2
• Filed: 11/30/2001
• Issued: 08/31/2004
• Est. Priority Date: 11/30/2001
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Dictaphone Corporation (Microsoft Corporation)
• Inventors: MacGintie, Andrew, Greene, Channell, Cyr, James, Hold, Martin, Kuhnen, Regina
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Azad, Abul K.
• Application Number:
  US09/997,220
• Publication Number:
  US 20030105623A1
• Time in Patent Office: 1,005 Days
• Field of Search: 704/6, 704/7, 704/8, 704/9, 704/10, 704/251, 704/252, 704/253, 704/255, 704/257, 704/270.1, 704/276, 704/235, 704/260
• US Class Current: 704/270.1
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems

Abstract

A distributed speech recognition system includes a speech processor linked to a plurality of speech recognition engines. The speech processor includes an input for receiving speech files from a plurality of users and storage means for storing the received speech files until such a time that they are forwarded to a selected speech recognition engine for processing. Each of the speech recognition engines includes a plurality of servers selectively performing different functions. The system further includes means for selectively activating or deactivating the plurality of servers based upon usage of the distributed speech recognition system.

Claims

1. A distributed speech recognition system, comprising:

a speech processor linked to a plurality of speech recognition engines, the speech processor includes an input for receiving speech files from a plurality of users and storage means for storing the received speech files until such a time that they are forwarded to a selected speech recognition engine for processing;

each of the speech recognition engines includes a plurality of servers selectively performing different functions; and

means for selectively activating or deactivating the plurality of servers based upon usage of the distributed speech recognition system.

2. The distributed speech recognition engine according to claim 1, wherein the plurality of servers are selected from the group consisting of an acoustic adaptation logical server, a language model adaptation logical server, a speech recognition server, a language model identification server and a fluency server.

3. The distributed speech recognition engine according to claim 1, wherein the servers include a speech recognition server and an acoustic adaptation logical server.

4. The distributed speech recognition engine according to claim 1, wherein the servers include a speech recognition server and a language model adaptation logical server.

5. The distributed speech recognition engine according to claim 1, wherein the servers include a speech recognition server and a language model identification server.

6. The distributed speech recognition engine according to claim 1, wherein the servers include a speech recognition server and a fluency server.

7. The distributed speech recognition engine according to claim 1, wherein the means for activating or deactivating includes an administrator workstation.

8. The distributed speech recognition engine according to claim 1, further including a speech engine monitoring agent monitoring usage of the plurality of speech recognition engines.

9. The distributed speech recognition engine according to claim 8, wherein the means for activating or deactivating includes an administrator workstation.

10. The distributed speech recognition engine according to claim 9, wherein the plurality of servers are selected from the group consisting of an acoustic adaptation logical server, a language model adaptation logical server, a speech recognition server, a language model identification server and a fluency server.

11. A method for optimizing the operation of a distributed speech recognition system, comprising the following steps:

linking a speech processor to a plurality of speech recognition engines, the speech processor including an input for receiving speech files from a plurality of users and storage means for storing the received speech files until such a time that they are forwarded to a selected speech recognition engine for processing;

providing each of the speech recognition engines with a plurality of servers performing different functions; and

selectively activating or deactivating the plurality of servers based upon usage of the distributed speech recognition system.

12. The method according to claim 11, wherein the plurality of servers are selected from the group consisting of an acoustic adaptation logical server, a language model adaptation logical server, a speech recognition server, a language model identification server and a fluency server.

13. The method according to claim 11, wherein the servers include a speech recognition server and an acoustic adaptation logical server.

14. The method according to claim 11, wherein the servers include a speech recognition server and a language model adaptation logical server.

15. The method according to claim 11, wherein the servers include a speech recognition server and a language model identification server.

16. The method according to claim 11, wherein the servers include a speech recognition server and a fluency server.

17. The method according to claim 11, wherein the means for activating or deactivating includes an administrator workstation.

18. The method according to claim 11, further including a speech engine monitoring agent monitoring usage of the plurality of speech recognition engines.

19. The method according to claim 18, wherein the step of activating or deactivating is performed by an administrator workstation associated with the speech processor.

20. The method according to claim 19, wherein the plurality of servers are selected from the group consisting of an acoustic adaptation logical server, a language model adaptation logical server, a speech recognition server, a language model identification server and a fluency server.