Cross-Modality Input Learning for Mobile Word Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile devices face inefficiencies in updating language models for voice and keyboard input methods, leading to incorrect word recognition and the need for redundant signal analysis, which affects processing efficiency and system bandwidth.
Innovation Solution
A computing system that integrates voice and keyboard input methods by generating an input context data structure to update language models, allowing seamless learning of new terms across modalities, reducing redundant analysis and enhancing processing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If separate language models are maintained for voice and keyboard IMEs, then each modality can be optimized independently, but redundant signal analysis occurs and processing efficiency decreases
Solution Approach 1:
The patent merges separate language models for voice and keyboard IMEs into a unified language model that serves both modalities. This consolidation eliminates redundant signal analysis and improves processing efficiency while maintaining recognition accuracy through shared learning across input methods.
Solution Approach 2:
The unified language model is designed to serve multiple functions simultaneously - it processes both voice and keyboard input, enabling a single model to handle diverse input modalities. This multi-functionality reduces the need for separate models and improves overall system efficiency.
2Measurement precision
If language models are updated frequently with new terms, then recognition accuracy improves, but system bandwidth and processing resources are consumed
Solution Approach 1:
By combining language model updates from both voice and keyboard inputs into a single unified model, the system reduces the total bandwidth consumption associated with separate model updates. The unified approach consolidates resource usage while maintaining improved recognition accuracy through comprehensive term learning.
3Adaptability or versatility
If cross-modality learning is implemented to enable seamless term recognition across voice and keyboard, then adaptability improves, but device complexity increases
Solution Approach 1:
The unified language model provides a universal structure that handles both voice and keyboard modalities through a single system. This approach achieves cross-modality learning capability without significantly increasing device complexity, as the same model infrastructure serves multiple purposes.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for cross input modality learning in a mobile device are disclosed. In one aspect, a method includes activating a first modality user input mode in which user inputs by way of a first modality are recognized using a first modality recognizer; and receiving a user input by way of the first modality. The method includes, obtaining, as a result of the first modality recognizer recognizing the user input, a transcription that includes a particular term; and generating an input context data structure that references at least the particular term. The method further includes, transmitting, by the first modality recognizer, the input context data structure to a second modality recognizer for use in updating a second modality recognition model associated with the second modality recognizer.