Conversation Support Apparatus with Spatial Display Separation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing conversation support systems struggle to accurately recognize and display multiple speech pieces when there are two or more speakers, leading to difficulties in distinguishing and understanding individual contributions.
Innovation Solution
A conversation support apparatus equipped with a speech input unit, speech recognizing unit, and image processing unit that sets display areas for each user, estimates sound source directions, and separates speech signals to display recognition results accordingly, allowing for the translation and correction of recognition data across multiple devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single speech recognition system is used to handle multiple speakers, then the system complexity is low, but the speech recognition accuracy deteriorates when multiple speech pieces are mixed
Solution Approach 1:
The patent divides the speech signal processing into separate channels for each speaker. The sound source separating unit separates mixed speech signals into individual speaker signals, and the speech recognizing unit processes each separated signal independently. This segmentation allows accurate recognition of multiple speech pieces while maintaining reasonable system complexity through modular architecture.
2Loss of information
If speech signals from multiple users are processed together, then the display unit shows all speech content, but the ability to distinguish individual speakers' contributions deteriorates
Solution Approach 1:
The patent assigns different display areas on the display unit to different speakers based on their sound source directions. Each speaker's recognized speech is displayed in a dedicated region, allowing users to see all speech content while clearly distinguishing which speaker said what. This local differentiation resolves the contradiction between complete information display and speaker identification.
3Device complexity
If display areas are not assigned to specific users, then the display layout is simple, but the ease of operation deteriorates when multiple speakers are present
Solution Approach 1:
The patent uses spatial positioning on the display unit to represent different speakers, creating a two-dimensional display layout where each speaker has a designated area. This spatial organization allows users to easily identify and follow individual speakers' contributions without complex controls or interfaces, improving ease of operation while maintaining intuitive display structure.
Data Source
AI summary
A conversation support apparatus includes: a speech input unit configured to input speech signals of two or more users; a speech recognizing unit configured to recognize the speech signals input from the speech input unit; a display unit configured to display the recognition results of the speech recognizing unit; and an image processing unit configured to set display areas respectively corresponding to the users into an image display area of the display unit.