Word Recognition Using Transformation Commands
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current large-vocabulary speech recognition systems on portable devices face challenges in providing an intuitive user interface for easier creation, editing, and usage, as they often lack features to efficiently correct misrecognitions and adapt to user preferences.
Innovation Solution
The system allows users to select from various word transformations, display choice lists, and favor recognition of user-selected parts of speech, enabling transformations such as changing words to their homonyms or alternative spellings, and integrating features like touch screens and software keyboards for improved input methods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If large-vocabulary speech recognition is implemented on portable devices, then speech recognition capability is provided, but user interface intuitiveness and ease of correction deteriorates
Solution Approach 1:
The system segments the word recognition process into multiple stages: initial recognition, transformation generation, and user selection. By dividing the correction process into discrete steps with choice lists, the system makes complex speech recognition outcomes manageable and intuitive for users to navigate and correct.
Solution Approach 2:
The system dynamically adapts the recognition process by allowing users to select transformations and request alternative interpretations. The choice lists and transformation options are generated on-demand based on user needs, making the system flexible and responsive to user preferences while maintaining speech recognition functionality.
2Ease of repair
If word transformation commands are added to correct misrecognitions, then correction capability is improved, but system complexity increases
Solution Approach 1:
The system introduces choice lists as an intermediary between speech recognition and final output. These lists present transformed word options in an organized, user-friendly format, mediating between the complex recognition process and simple user selection, thereby improving correction ease without exposing users to system complexity.
Solution Approach 2:
The system generates multiple copies or variants of recognized words through transformations (e.g., alternative spellings, homonyms, related terms). By presenting these copies in choice lists, users can easily select the correct meaning without the system needing to inherently understand contextual nuances, simplifying the correction mechanism.
3Measurement precision
If choice lists with transformed words are displayed, then user selection accuracy is improved, but information processing time increases
Solution Approach 1:
The system performs preliminary transformations of recognized words into multiple candidate forms before presenting them to users. By pre-generating choice lists with transformed options (alternative spellings, homonyms, related words), the system prepares accurate selection candidates in advance, reducing the time users need to spend deliberating and improving selection accuracy without adding significant processing delays during interaction.
Data Source
AI summary
Word recognition enables a user to have a selected transformation performed on a given word produced by word recognition. In one aspect of the invention, a selectable transformation changes the given word to a differently spelled word having the same word root. In another, a selectable transformation changes a given word to one or more of its homonyms. In yet another, a selectable transformation changes the given word between a representation that spells the word with letters and one that does not. In one aspect of the invention a user can select to display a choice list of transformed words corresponding to a given recognized word and then select to have one of the listed transformed words replace the given word. In another aspect of the invention word recognition favors recognition of words corresponding to a user selected part of speech.