Flexible schema for language model customization

• US 10,497,367 B2
• Filed: 12/22/2016
• Issued: 12/03/2019
• Est. Priority Date: 03/27/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Levit, Michael, Guelman, Hernan, Chang, Shuangyu, Parthasarathy, Sarangarajan, Dumoulin, Benoit
• Primary Examiner(s): Augustin, Marcellus J
• Application Number:
  US15/389,088
• Publication Number:
  US 20170103753A1
• Time in Patent Office: 1,076 Days
• Field of Search: 704 10, 704243-250, 704257, 704265, 704275
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications

Abstract

The customization of language modeling components for speech recognition is provided. A list of language modeling components may be made available by a computing device. A hint may then be sent to a recognition service provider for combining the multiple language modeling components from the list. The hint may be based on a number of different domains. A customized combination of the language modeling components based on the hint may then be received from the recognition service provider.

Claims

1. A method, executed by a computing device, of customizing language modeling components, the method comprising:

displaying, by the computing device, a list of language modeling components;

sending, by the computing device to a service provider, a hint for combining a plurality of the language modeling components from the list, the hint being based on one or more of a plurality of domains, wherein sending the hint for combining a plurality of the language modeling components from the list comprises sending the hint prior to initiating an offline initialization process; and

receiving, by the computing device from the service provider, a customized combination of the plurality of the language modeling components based on the hint;

capturing speech input; and

recognizing the captured speech input based on the received customized combination of the plurality of the language modeling components.

2. The method of claim 1, further comprising maintaining a connection between the hint and the one or more of the plurality of the language modeling components by assigning an ID associated with the hint to the plurality of language modeling components.

3. The method of claim 1, wherein sending, by the computing device, the hint for combining a plurality of the language modeling components from the list comprises sending a selection of a pre-compiled language model based on the one or more of the plurality of domains.

4. The method of claim 1, wherein sending, by the computing device, the hint for combining a plurality of the language modeling components from the list comprises sending a selection of a fixed weight combination of the plurality of the language modeling components based on the one or more of the plurality of domains.

5. The method of claim 4, further comprising applying one or more weights to the one or more of the plurality of language modeling components.

6. The method of claim 1, wherein sending, by the computing device, the hint for combining a plurality of the language modeling components from the list comprises sending a selection of one or more recognition topics from a pre-complied list, the one or more recognition topics corresponding to one or more of the plurality of the language modeling components.

7. The method of claim 1, wherein sending, by the computing device, the hint for combining a plurality of the language modeling components from the list comprises sending an in-domain text corpus.

8. The method of claim 1, wherein sending, by the computing device, the hint for combining a plurality of the language modeling components from the list comprises sending an in-domain audio corpus.

9. The method of claim 1, wherein sending, by the computing device, the hint for combining a plurality of the language modeling components from the list comprises sending an existing combination of language modeling components for re-use.

10. The method of claim 1, wherein sending, by the computing device, the hint for combining a plurality of the language modeling components from the list comprises sending a recognition request comprising the hint.

11. A system for customizing language modeling components, comprising:

a memory for storing executable program code; and

a processor, functionally coupled to the memory, the processor being responsive to computer-executable instructions contained in the program code and operative to;

display, by the system, a list of language modeling components;

send, by the system to a service provider, a hint generated by the system for combining a plurality of language modeling components from the list, the hint being based on one or more of a plurality of domains;

receive, by the system from the service provider, a customized combination of the plurality of the language modeling components based on the hint;

maintain a connection between the hint and the one or more of the plurality of the language modeling components by assigning an ID associated with the hint to the plurality of language modeling components;

receive speech input into the system; and

recognize the speech input based on the customized combination of the plurality of the language modeling components.

13. The system of claim 11, wherein the processor, in sending the hint for combining a plurality of the language modeling components from the list, is operative to send a selection of a fixed weight combination of the plurality of the language modeling components based on the one or more of the plurality of domains.

14. The system of claim 11, wherein the processor, in sending the hint for combining a plurality of the language modeling components from the list, is operative to:

send a selection of one or more recognition topics from a pre-complied list, the one or more recognition topics corresponding to one or more of the plurality of the language modeling components; and

apply one or more weights to the one or more of the plurality of language modeling components.

12. The system of 11, wherein the processor, in sending the hint for combining a plurality of the language modeling components from the list, is operative to send a selection of a pre-compiled language model based on the one or more of the plurality of domains.

15. A computer-implemented method of customizing language modeling components, comprising:

receiving an identification of one or more language modeling components from a client device for use in recognizing speech;

receiving a selection of a weight value for the selected one or more of the language modeling components; and

generating a customized combination of language modeling components for speech recognition based on the identified one or more language modeling components and the weight value;

sending the customized combination of language modeling components to the client device to recognize speech based on the customized combination of language modeling components;

receiving speech input; and

recognizing the speech input based on the customized combination of the plurality of the language modeling components.

16. The method of claim 15, wherein the information received includes at least a portion of an in-domain text corpus.

17. The method of claim 15, wherein the information received includes at least a portion of an in-domain audio corpus.

18. The method of claim 15, wherein the information received identifies at least an existing combination of language modeling components for re-use.

19. The method of claim 15, wherein the information is received as part of a recognition request for use in on-the-fly language model interpolation.

20. The method of claim 15, further comprising recognizing speech based on the customized combination of language modeling components.