Voice Chat Transcription Control for Selective Text Delivery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users desire the option to receive text from voice recognition in voice chat but not all users need or want this feature, leading to unnecessary data traffic.
Innovation Solution
A system that controls whether to provide text from voice recognition based on user preferences, using a voice agent server and management server to manage voice chat systems, allowing selective display of text on auxiliary devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If text from voice recognition is provided to all users in voice chat, then users who want text information can grasp the content, but data traffic unnecessarily increases for users who do not need text
Solution Approach 1:
The patent applies local quality by making the text provision feature selective rather than universal. Different users receive different treatments: some users receive voice recognition text while others receive only audio, based on their individual preferences. This resolves the contradiction by providing text information locally to those who need it without forcing it on all users, thereby reducing unnecessary data traffic.
2Loss of information
If text from voice recognition is provided to all users, then information accessibility is improved, but network bandwidth consumption increases
Solution Approach 1:
The system implements local quality by customizing the information delivery based on user characteristics. Users who prefer text-based communication receive both audio and transcribed text, while audio-only users receive merely the voice stream. This selective approach ensures that voice chat content is made accessible to those who need it without increasing network bandwidth consumption for users who don't require text.
3Ease of operation
If voice recognition text is always provided, then user convenience is improved for text-oriented users, but system resource consumption increases
Solution Approach 1:
The patent applies local quality by making voice recognition text provision user-specific rather than system-wide. The server identifies users who have opted for text-based interaction and provides them with transcribed text, while other users receive only audio. This resolves the contradiction by enhancing ease of operation for text-oriented users without causing system resource consumption to increase for the entire user base.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
Provided are a voice chat apparatus, a voice chat method, and a program that achieve appropriate control on whether or not to provide text obtained as a result of voice recognition on voice in voice chat. A voice receiving unit (44) receives voice in voice chat. A text acquiring unit (46) acquires text obtained as a result of voice recognition on the voice received by the voice receiving unit (44). A transmission control unit (52) controls, on a basis of whether or not display of a voice recognition result is performed in a voice chat system that is a communication destination, whether or not to transmit text data including the text acquired by the text acquiring unit (46) to the communication destination.