Voice Data Keyword Extraction via Touch-Selected Segments
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mobile terminals only display the reproduction progress state of currently output voice data, lacking functionality to provide practical use of voice data information corresponding to a given point on the progress bar.
Innovation Solution
A mobile terminal with a display unit and controller that selects a section of voice data based on user input, converts keyword voice data to text data, and displays it, allowing users to intuitively identify main keywords at specific points in time by determining the extent of touch input and extracting relevant data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If a progress bar showing reproduction progress state of voice data is displayed, then the user can see the current playback position, but the user cannot access or view information about specific sections of the voice data at given points on the progress bar
Solution Approach 1:
The progress bar is divided into multiple selectable sections or segments. When a user touches or selects a specific segment on the progress bar, the system identifies the corresponding voice data section and extracts keyword information from that specific segment, allowing users to access information about particular portions of the voice data without having to navigate through the entire content.
Solution Approach 2:
A graphic object or visual indicator is introduced as an intermediary element between the progress bar and the voice data information. This graphic object responds to user input by highlighting or displaying keyword text data corresponding to the selected section, serving as a mediator that translates user interaction into meaningful information retrieval without requiring complex navigation or processing.
2Loss of information
If keyword voice data is converted to text data for display, then users can read and identify main keywords, but the processing time and computational resources increase
Solution Approach 1:
Instead of converting and displaying all voice data as text, the system extracts only the essential keyword information from the selected voice data section. This selective extraction process identifies and pulls out key terms or phrases that represent the main content, converting only these keywords to text form for display, thereby reducing processing time and computational resources while still providing meaningful information to users.
Solution Approach 2:
The system performs partial conversion of voice data to text by focusing only on keyword extraction rather than full transcription. This partial action approach converts sufficient information to meet user needs (identifying main keywords) without the excessive processing required for complete text conversion, achieving a balance between information quality and processing efficiency.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
A mobile terminal including a wireless communication unit configured to wirelessly communicate with at least one other terminal; a memory configured to store recorded voice data; a display unit configured to display a graphic object representing a reproduction progress of the recorded voice data; and a controller configured to receive a selection signal indicating a portion of the graphic object has been selected, select a section of the recorded voice data including a point-in-time at which the graphic object is selected, convert keyword voice data included in the selected section of the recorded voice data to keyword text data, and display the keyword text data on the display unit.