Flexible Schema for Language Model Customization

• US 20150278191A1
• Filed: 03/27/2014
• Published: 10/01/2015
• Est. Priority Date: 03/27/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Levit, Michael, Chang, Shuangyu, Parthasarathy, Sarangarajan, Dumoulin, Benoit, Guelman, Hernan
• Granted Patent: US 9,529,794 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• 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 of customizing language modeling components, comprising:

presenting, by a computing device, a list of language modeling components;

sending, by the computing device, 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; and

receiving, by the computing device, a customized combination of the plurality of the language modeling components based on the hint.

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.

3. The method of claim 1, wherein sending, by the computing device, a 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, a 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 1, wherein sending, by the computing device, a 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.

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

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

11. The method of claim 1, wherein sending, by the computing device, a hint for combining a plurality of the language modeling components from the list comprises sending the hint prior to initiating an offline intiliazation process.

12. 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;

present a list of language modeling components;

send 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;

receive a customized combination of the plurality of the conversational understanding components based on the hint; and

maintain a connection between the hint and the one or more of the plurality of the language modeling components.

14. The system of claim 12, wherein the processor, in sending a 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.

15. The system of claim 12, wherein the processor, in sending a 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.

13. The system of 12, wherein the processor, in sending a 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.

16. A computer-readable storage medium storing computer executable instructions which, when executed by a computer, will cause computer to perform a method of customizing language modeling components, the method comprising:

presenting a list of distinct language modeling components;

sending a hint for combining a plurality of the distinct language modeling components from the list, the hint being based on one or more of a plurality of domains, the one or more of the plurality of domains comprising one or more of a voice search domain and a short message dictation domain;

receiving a customized combination of the plurality of the distinct language modeling components based on the hint; and

maintaining a connection between the hint and the one or more of the plurality of the distinct language modeling components.

17. The computer-readable storage medium of claim 16, wherein sending a hint for combining a plurality of the distinct 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.

18. The computer-readable storage medium of claim 16, wherein sending a hint for combining a plurality of the distinct language modeling components from the list comprises sending a selection of a fixed weight combination of the plurality of the distinct language modeling components based on the one or more of the plurality of domains.

19. The computer-readable storage medium of claim 16, wherein sending a hint for combining a plurality of the distinct language modeling components from the list comprises:

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

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

20. The computer-readable storage medium of claim 16, wherein the hint comprises at least one of an in-domain text corpus and an in-domain audio corpus.