Selective enablement of speech recognition grammars

• US 9,196,252 B2
• Filed: 10/26/2009
• Issued: 11/24/2015
• Est. Priority Date: 06/15/2001
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Ruback, Harvey M., Woodward, Steven G.
• Primary Examiner(s): Opsasnick, Michael N
• Application Number:
  US12/605,704
• Publication Number:
  US 20100049521A1
• Time in Patent Office: 2,220 Days
• Field of Search: 704/200, 704/201, 704/270.1, 704/7, 704/277
• US Class Current: 1/1
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

A method for processing speech audio in a network connected client device can include selecting a speech grammar for use in a speech recognition system in the network connected client device; characterizing the selected speech grammar; and, based on the characterization, determining whether to process the speech grammar locally in the network connected client device, or remotely in a speech server in the network. In one aspect of the invention, the selecting step can include establishing a communications session with a speech server; and, querying the speech server for a speech grammar over the established communications session. Additionally, the selecting step can further include registering the speech grammar in the speech recognition system.

Claims

1. A method for processing speech audio in a network connected client device configured to communicate with at least one speech server, the method comprising:

using the network connected client device to perform;

establishing a communications session with the at least one speech server;

querying the at least one speech server for a speech grammar over the established communications session, or selecting a speech grammar stored in the network connected client device and uploading the selected speech grammar to the at least one speech server over the established communications session;

analyzing the speech grammar to determine a complexity of the speech grammar; and

determining whether to process the speech locally in the network connected client device, or remotely in the at least one speech server in the network based on the complexity of the speech grammar.

2. The method of claim 1, further comprising registering said speech grammar.

3. The method of claim 1, wherein the analyzing includes identifying in said speech grammar a pre-determined characterization.

4. The method of claim 3, wherein said pre-determined characterization is a pre-determined complexity.

5. The method of claim 3, wherein said pre-determined characterization specifies a pre-determined preference for processing said speech grammar either locally at the client device or remotely at the at least one speech server.

6. The method of claim 5, wherein said pre-determined characterization further specifies a location of the at least one speech server for remotely processing said speech grammar.

7. A client device connected to a network, the client device configured to communicate with at least one speech server, the client device comprising at least one processor configured to perform:

establishing a communications session with the at least one speech server;

querying the at least one speech server for a speech grammar over the established communications session, or selecting a speech grammar stored in the network connected client device and uploading the selected speech grammar to the at least one speech server over the established communications session;

analyzing the speech grammar to determine a complexity of the speech grammar; and

determining whether to process the speech locally in the network connected client device, or remotely in the at least one speech server in the network based on the complexity of the speech grammar.

8. The client device of claim 7, wherein said analyzing includes identifying in said speech grammar a pre-determined characterization.

9. The client device of claim 8, wherein said pre-determined characterization specifies a pre-determined preference for processing said speech grammar either locally at the client device or remotely at the at least one speech server.

10. The client device of claim 9, wherein said pre-determined characterization further specifies a location of the at least one speech server for remotely processing said speech grammar.

11. A non-transitory machine readable storage medium, having stored thereon a computer program for processing speech audio in a network connected client device configured to communicate with at least one speech server, said computer program having a plurality of code sections that, when executed by the network connected client device, cause the network connected client device to perform a method comprising:

establishing a communications session with the at least one speech server;

querying the at least one speech server for a speech grammar over the established communications session, or selecting a speech grammar stored in the network connected client device and uploading the selected speech grammar to the at least one speech server over the established communications session;

analyzing the speech grammar to determine a complexity of the speech grammar; and

determining whether to process the speech locally in the network connected client device, or remotely in the at least one speech server in the network based on the complexity of the speech grammar.

12. The non-transitory machine readable storage medium of claim 11, wherein the method further comprises registering said speech grammar.

13. The non-transitory machine readable storage medium of claim 11, wherein the analyzing includes identifying in said speech grammar a pre-determined characterization.

14. The non-transitory machine readable storage medium of claim 13, wherein said pre-determined characterization is a pre-determined complexity.

15. The non-transitory machine readable storage medium of claim 13, wherein said pre-determined characterization specifies a pre-determined preference for processing said speech grammar either locally at the client device or remotely at the at least one speech server.

16. The non-transitory machine readable storage medium of claim 15, wherein said pre-determined characterization further specifies a location of the at least one speech server for remotely processing said speech grammar.