Back to results
US 2022/0036893 A1Published application
Language and grammar model adaptation
AssigneeAmazon Technologies, Inc.
InventorsAnkur Gandhe, Ariya Rastrow, Gautam Tiwari, Ashish Vishwanath Shenoy, Chun Chen
Life of this patent
Estimating the term…
Abstract
Systems and methods described herein relate to adapting a language model for automatic speech recognition (ASR) for a new set of words. Instead of retraining the ASR models, language models and grammar models, the system only modifies one grammar model and ensures its compatibility with the existing models in the ASR system.
Claims21
-20. (canceled)
A computer-implemented method, comprising:
- receiving input data representing a first set of words;
- determining a first grammar model corresponding to a second set of words that are different than the first set of words, the first grammar model including first model weight data;
- processing the first model weight data using the input data to determine second model weight data;
- determining first data representing a difference between the first model weight data and the second model weight data;
- using the first data to generate second data corresponding to language processing with regard to a third set of words, wherein at least one word of the third set of words is included in the first set of words but not in the second set of words;
- and
- storing an association between the second data and the first grammar model.
4 more elements
A system comprising:
- at least one processor;
- and
- at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
- receive input data representing a first set of words;
- determine a first grammar model corresponding to a second set of words that are different than the first set of words, the first grammar model including first model weight data;
- process the first model weight data using the input data to determine second model weight data;
- determine first data representing a difference between the first model weight data and the second model weight data;
- use the first data to generate second data corresponding to language processing with regard to a third set of words, wherein at least one word of the third set of words is included in the first set of words but not in the second set of words;
- and
- store an association between the second data and the first grammar model.
7 more elements
A computer-implemented method comprising:
- receiving input data representing a natural language user input;
- processing the input data using a first grammar model corresponding to a first set of words, the first grammar model including first model weight data;
- determining the first grammar model is associated with first data corresponding to a second set of words, the second set of words being different from the first set of words, wherein the first data was generated by:
- processing the first model weight data using second data to determine second model weight data, wherein the second data represents a third set of words different from the second set of words,
- determining third data representing a difference between the first model weight data and the second model weight data, and
- using the third data to generate the first data;
- processing the input data using the first data;
- and
- based at least in part on processing the input data using the first grammar model and the first data, determining output data representing a plurality of words of the natural language user input.
6 more elements
Dependencies are inferred from the claim text.