Multi-modal Input Method Editor for Mobile Speech Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile devices lack sufficient processing power for efficient speech-to-text conversion, and users often face constraints when typing on small keyboards, especially in situations like walking or driving, where typed input is impractical.
Innovation Solution
A multi-modal input method editor (IME) that provides both typed and spoken input capabilities, using a remote server with a speech recognition system to convert spoken input into text, with context-specific language models for improved accuracy, and the ability to switch between input modes seamlessly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If speech-to-text conversion is implemented on mobile devices, then user input convenience is improved, but processing power requirements increase
Solution Approach 1:
The patent introduces a remote server as an intermediary to perform the computationally intensive speech-to-text conversion. The mobile device acts only as a client that captures speech input and transmits it to the server, which then returns the converted text. This mediator approach allows the mobile device to provide speech input functionality without bearing the processing burden, effectively resolving the contradiction between ease of operation and power requirements.
2Area of moving object
If keyboard size is reduced for mobile devices, then device portability is improved, but typing accuracy deteriorates
Solution Approach 1:
The patent replaces the mechanical typing system (physical or virtual keyboard requiring precise key presses) with an acoustic input system (microphone capturing speech). This substitution eliminates the need for a large keyboard while maintaining or improving input accuracy, as speech recognition can achieve higher precision than small-keyboard typing, especially in mobile contexts where the device may be moving.
3Speed
If speech-to-text conversion is performed locally, then response time is improved, but device complexity increases
Solution Approach 1:
The patent extracts the complex speech-to-text conversion functionality from the mobile device and relocates it to a remote server. The device retains only the essential functions of capturing speech input and displaying the converted text, while the complex processing logic resides externally. This extraction approach maintains relatively simple device architecture while still providing timely responses through efficient server-side processing.
Data Source
AI summary
A computer-implemented input-method editor process includes receiving a request from a user for an application-independent input method editor having written and spoken input capabilities, identifying that the user is about to provide spoken input to the application-independent input method editor, and receiving a spoken input from the user. The spoken input corresponds to input to an application and is converted to text that represents the spoken input. The text is provided as input to the application.