Transparent Speech Display With Speaker-Differentiated Captions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication systems fail to effectively facilitate communication between individuals with hearing impairments or language barriers, particularly in settings where direct speech is difficult to hear or understand.
Innovation Solution
A projector display system that uses a transparent screen with a light-shielding portion to display speech content of both users in a manner that allows each user to easily read their own language, with options for translation and emphasis, and includes sensors to identify the speaker.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If both users' speech content is displayed on the same transparent display, then communication between hearing-impaired or language-diverse individuals is facilitated, but it becomes difficult for users to distinguish and read their own speech content clearly
Solution Approach 1:
The patent applies local quality by displaying speech content with different visual characteristics based on the speaker identity. Specifically, the display controller changes the display mode (such as color, font, or position) of speech content depending on whether it is from the first user or the second user, allowing each user to easily distinguish and read their own speech content while viewing the other's speech content on the same transparent display
Solution Approach 2:
The patent segments the display of speech content by creating distinct visual representations for different speakers. The display controller divides the speech content into separate display modes (e.g., different colors or positions) for the first user's speech and the second user's speech, enabling clear differentiation and readability for each user
2Speed
If a transparent display is used to show speech content, then real-time captioning is achieved, but speech content may be missed or misrecognized due to automatic speech recognition limitations
Solution Approach 1:
The patent implements feedback by allowing users to view their own speech content displayed on the transparent display. This enables users to check for misconversions or misrecognitions in real-time and provides feedback that can be used to improve the accuracy of automatic speech recognition, while maintaining the speed advantage of real-time captioning
3Adaptability or versatility
If speech content from multiple users is displayed simultaneously, then language translation between different languages is enabled, but it becomes difficult to distinguish which content belongs to which user
Solution Approach 1:
The patent applies local quality by assigning different display modes (such as different colors, positions, or visual styles) to speech content from different users. This allows the system to maintain language translation capability while preserving speaker identification information, as each user's speech content is visually distinguished from the other's on the transparent display
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
A program causes an electronic device that controls a display system that displays a first character that is based on speech of a first user and a second character that is based on speech of a second user on a display to perform the following steps: Acquiring at least one of the first character or the second character. Determining, based on a predetermined condition, whether at least one of the first character or the second character is based on the speech of the first user or the second user. Displaying the first character and the second character on the display while changing the display mode of at least one of the first character or the second character so that the display modes of the first character and the second character are different from each other.