Text Prediction System Combining Typed and Voice Inputs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data entry methods, such as typing and voice recognition, often result in inaccurate text prediction due to errors in character sequences or pronunciation variations, especially in languages like Chinese where similar characters have different pronunciations, leading to decreased accuracy in predicting text.
Innovation Solution
A system that concurrently receives typed characters and voice input corresponding to a spoken utterance, using these inputs to determine candidate texts and provide them to the user, with a computing device configured to calculate the likelihood of each candidate text predicting the intended text, thereby improving prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If voice recognition is used for text input, then input speed is improved, but accuracy deteriorates due to pronunciation variations and similar characters
Solution Approach 1:
The patent combines two different input methods (typing and voice input) into a unified text prediction system. The typed characters and voice input are processed together to generate candidate texts, leveraging the strengths of both methods while compensating for their individual weaknesses. This merging approach resolves the contradiction by maintaining the speed benefit of voice input while improving accuracy through the precision of typed character verification.
2Measurement precision
If typed characters are used for text input, then accuracy is improved, but input speed deteriorates
Solution Approach 1:
The system processes only a portion of the text through typing (characters already entered) while the remaining portion is captured through voice input. This partial action approach allows the system to leverage the accuracy of typing for confirmed characters while using faster voice input for the remainder, thereby improving overall input speed without sacrificing accuracy for the typed portion.
3Measurement precision
If multiple input methods are combined, then prediction accuracy is improved, but system complexity increases
Solution Approach 1:
The text prediction system is designed to handle multiple input types (typed characters and voice input) through a unified processing framework. The same prediction algorithm and candidate generation mechanism process both input modalities, making the system multi-functional without requiring separate complex subsystems. This universality approach improves prediction accuracy by incorporating diverse input information while avoiding the complexity increase that would result from maintaining separate processing chains.
Data Source
AI summary
Methods and systems for predicting a text are described. In an example, a computing device may be configured to receive one or more typed characters that compose a portion of a text; and receive, a voice input corresponding to a spoken utterance of at least a portion of the text. The computing device may be configured to determine, based on the one or more typed characters and the voice input, one or more candidate texts predicting the text. Further, the computing device may be configured to provide the one or more candidate texts.