Application-Independent Multi-Modal Input Editor With Split Speech Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile computing devices face challenges in processing speech-to-text conversion due to limited processing power and the need for user-specific training, while conventional keyboards are constrained by size and usability in various environments.
Innovation Solution
A multi-modal input method editor (IME) that integrates speech-to-text functionality, allowing users to switch between typed and spoken input, utilizing context-specific language models and remote server processing to enhance accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If speech-to-text conversion is implemented on mobile devices, then input convenience is improved, but processing power requirements increase
Solution Approach 1:
The speech-to-text processing is divided into two segments: initial processing and conversion happens locally on the mobile device using the IME, while more complex speech recognition and language model processing is offloaded to remote servers. This segmentation allows the mobile device to maintain low processing power requirements while still providing speech input functionality.
Solution Approach 2:
The IME acts as an intermediary layer between the user's speech input and the application. It captures speech input locally, performs initial processing, and then communicates with remote servers for more intensive speech recognition tasks. This intermediary approach enables speech-to-text conversion without requiring the mobile device to have high processing power for all speech processing operations.
2Length of moving object
If conventional keyboards are made smaller for mobile devices, then device portability is improved, but typing accuracy deteriorates
Solution Approach 1:
The patent replaces the mechanical keyboard typing system with a speech-based input system. Instead of requiring physical key presses on a small keyboard, users can speak their input which is then converted to text. This substitution eliminates the need for large keyboards while maintaining or improving input accuracy, as speech recognition can achieve high accuracy rates even on mobile devices.
3Speed
If speech-to-text conversion is performed locally, then response time is improved, but processing power consumption increases
Solution Approach 1:
The speech processing workload is segmented between local and remote processing. Quick, simple conversions are handled locally by the IME for fast response, while more complex speech recognition tasks are sent to remote servers. This segmentation optimizes both response time and power consumption by matching task complexity with appropriate processing location.
Solution Approach 2:
The IME performs partial speech-to-text conversion locally without requiring complete local processing. It handles the essential function of capturing and initially processing speech input, then offloads more intensive recognition tasks to servers. This partial local action provides sufficient response time improvement while avoiding excessive power consumption that would result from complete local 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.