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