Speech-to-Text Correction for Mobile Wireless Communications
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Individuals with impaired vision face difficulties in operating mobile wireless communications devices due to the need to read displays and enter text, and drivers using these devices while driving are at risk of accidents due to distraction.
Innovation Solution
A mobile wireless communications device equipped with an audio interface and controller that converts speech input to text, applies grammatical corrections and ambiguity resolutions, and allows users to accept or reject proposed modifications, enabling hands-free operation and reducing visual reliance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users manually enter text or read display on mobile device, then text input accuracy is improved, but ease of operation deteriorates for visually impaired users
Solution Approach 1:
The patent replaces manual text entry and visual reading operations with speech-to-text conversion technology. The system captures spoken input through an audio interface, converts it to text automatically, and presents it for review, eliminating the need for manual keyboard input and visual display reading.
Solution Approach 2:
The patent introduces speech-to-text conversion as an intermediary process between the user's intent and the text input. The system acts as a mediator that translates spoken words into written text, which is then displayed for user verification and correction before final submission.
2Productivity
If drivers use mobile device for text input or reading, then communication efficiency is improved, but safety deteriorates due to distraction
Solution Approach 1:
The patent replaces manual text entry operations with speech-to-text conversion, allowing drivers to communicate without manual interaction with the device. The system captures speech input, converts it to text, and handles communication tasks without requiring the driver to look at or manually operate the device.
Solution Approach 2:
The system provides self-service by automatically converting speech to text and presenting it for review, reducing the cognitive and manual load on the driver. The device handles the complex text input task autonomously based on spoken commands.
3Ease of operation
If speech to text conversion is implemented, then ease of operation is improved for visually impaired users, but device complexity increases
Solution Approach 1:
The patent implements speech-to-text conversion functionality within the existing mobile device framework, making the device capable of serving both visually impaired users and drivers. The same speech recognition and text conversion infrastructure benefits multiple user groups and use cases.
Solution Approach 2:
The patent combines speech-to-text conversion, text review, and text correction functionalities into an integrated system workflow. The audio interface, processor, and display work together in a unified process that adds capability without requiring separate independent systems.
4Measurement precision
If manual text entry is required, then text input precision is improved, but loss of time increases
Solution Approach 1:
The patent replaces time-consuming manual text entry with speech-to-text conversion. Users speak their intended text naturally, and the system converts it to written form automatically, dramatically reducing the time required for text input while maintaining the ability to review and correct for precision.
Solution Approach 2:
The system performs preliminary text generation through speech-to-text conversion before the user needs to review or submit the text. This preliminary creation of the text draft saves time by eliminating the need for character-by-character manual input.
Data Source
AI summary
A communications device and method are provided for converting speech to text and applying corrections to the text. The communications device may include at least one audio interface, such a microphone and/or speaker, and at least one communications subsystem, as well as a controller or processor operative to receive speech input using the at least one audio interface, convert the speech input to input text, correct the input text to corrected text, and send the corrected text over a network using the communications subsystem. The corrected text may involve the application of proposed modification, such as a grammatical correction or ambiguity resolution, to the input text. The application of the proposed modification may be based upon the receipt of an instruction to accept or reject the proposed correction or resolution. The instruction may be a spoken instruction.


