System and method for combining geographic metadata in automatic speech recognition language and acoustic models

• US 10,121,468 B2
• Filed: 06/15/2016
• Issued: 11/06/2018
• Est. Priority Date: 12/15/2009
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Bocchieri, Enrico, Caseiro, Diamantino Antonio
• Primary Examiner(s): Opsasnick, Michael N
• Application Number:
  US15/183,066
• Publication Number:
  US 20160293161A1
• Time in Patent Office: 874 Days
• Field of Search: 704270
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams
• CPC Class Codes: G10L 2015/081 Search algorithms, e.g. Baum-Welch or Viterbi
• CPC Class Codes: G10L 2015/228 of application context
• CPC Class Codes: G10L 25/54 for retrieval

Abstract

Disclosed herein are systems, methods, and computer-readable storage media for a speech recognition application for directory assistance that is based on a user'"'"'s spoken search query. The spoken search query is received by a portable device and portable device then determines its present location. Upon determining the location of the portable device, that information is incorporated into a local language model that is used to process the search query. Finally, the portable device outputs the results of the search query based on the local language model.

Claims

1. A method comprising:

incorporating a granularity description of a present location of a device into a local language model, the granularity description using topologically concentric locations to determine probabilities;

combining the local language model with a global language model according to the probabilities, to yield a combined language model; and

outputting, using the combined language model and via a spoken dialog system, audible spoken language results for a spoken query based on the present location and a term in the spoken query.

2. The method of claim 1, wherein the granularity description uses business density to determine weights.

3. The method of claim 1, further comprising processing the spoken query using the local language model, to yield the results, wherein the local language model comprises the granularity description.

4. The method of claim 1, further comprising:

incorporating the present location into a local acoustic model used to process the spoken query.

5. The method of claim 1 wherein the present location of the device is determined using one of a global positioning system, triangulation, and automatic number identification.

6. The method of claim 1, wherein incorporating of the granularity description into the local language model further comprises:

partitioning training data into geographical areas;

estimating models for each partition; and

selecting a portioned model based on the present location of the device.

7. The method of claim 6, further comprising generating a user model by combining two models using interpolation.

8. The method of claim 1, wherein entities in the local language model are related at one of a city, an area code, and a state level.

9. The method of claim 1, wherein the device is a portable device.

10. A spoken dialog system comprising:

a processor; and

a computer-readable storage medium having instructions stored which, when executed by the processor, result in operations comprising;

incorporating a granularity description of a present location of a device into a local language model, the granularity description using topologically concentric locations to determine probabilities;

combining the local language model with a global language model according to the probabilities, to yield a combined language model; and

outputting, using the combined language model, audible spoken language results for a spoken query based on the present location and a term in the spoken query.

11. The spoken dialog system of claim 10, wherein the device is a portable device.

12. The spoken dialog system of claim 10, wherein the granularity description uses business density to determine weights.

13. The spoken dialog system of claim 10, wherein the computer-readable storage medium stores additional instructions stored which, when executed by the processor, cause the processor to perform operations comprising processing the spoken query using the local language model, to yield the results, wherein the local language model comprises the granularity description.

14. The spoken dialog system of claim 10, the computer-readable storage medium having additional instructions stored which, when executed by the processor, result in operations comprising:

incorporating the present location into a local acoustic model used to process the spoken query.

15. The spoken dialog system of claim 10, wherein the present location of the device is determined using one of a global positioning system, triangulation, and automatic number identification.

16. The spoken dialog system of claim 10, wherein incorporating of the granularity description into the local language model further comprises:

partitioning training data into geographical areas;

estimating models for each partition; and

selecting a portioned model based on the location of the device.

17. The spoken dialog system of claim 16, the computer-readable storage medium having additional instructions stored which, when executed by the processor, result in operations comprising generating a user model by combining two models using interpolation.

18. The spoken dialog system of claim 10, wherein entities in the local language model are related at one of a city, an area code, and a state level.

19. A computer-readable storage device having instructions stored which, when executed by a computing device, result in operations comprising:

incorporating a granularity description of a present location of a device into a local language model, the granularity description using topologically concentric locations to determine probabilities;

combining the local language model with a global language model according to the probabilities, to yield a combined language model; and

outputting, using the combined language model, audible spoken language results for a spoken query based on the present location and a term in the spoken query.

20. The computer-readable storage device of claim 19, wherein the granularity description uses topologically concentric locations to determine weights.