Audio Feature Extraction for Broadcast Content Synchronization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for providing additional information related to broadcast content on TVs hinder the viewing experience and are not applicable to analog TVs or public displays, and they consume network bandwidth and server resources.
Innovation Solution
A system that extracts audio feature data from broadcast content, groups it into predetermined units, and transmits this data to a viewer terminal, allowing the terminal to determine the temporal location and request additional information, thereby separating the device for viewing content from the device for additional information without interrupting the viewing experience.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If additional information is outputted overlapped on the broadcast content image, then the additional information is provided to viewers, but the viewing experience is hindered
Solution Approach 1:
The system separates the broadcast content display function (TV) from the additional information provision function (independent terminal). The terminal receives audio signals from the TV, extracts audio features, and displays additional information separately, dividing the originally unified display into independent functional segments.
Solution Approach 2:
The independent terminal acts as an intermediary device between the TV and the viewer. It receives audio output from the TV, processes audio features, and provides additional information through the terminal's display interface, mediating the information delivery without affecting the TV screen.
2Loss of information
If a web browser is executed to access URL in the displayed image, then the additional information is accessed, but the viewing experience is interrupted
Solution Approach 1:
The system divides the information access function from the content viewing function by using an independent terminal for accessing additional information. The terminal processes audio features and retrieves additional information separately, allowing simultaneous viewing and information access without screen switching or browser execution on the TV.
Solution Approach 2:
The independent terminal autonomously extracts audio features from the TV audio output, automatically determines temporal locations, and retrieves additional information without requiring viewer intervention to switch screens or execute browsers. The system serves itself by automatically providing additional information in sync with the broadcast content.
3Loss of information
If the display screen is split into broadcast content screen and web page screen, then both are displayed, but the broadcast content image becomes small and viewing experience is still hindered
Solution Approach 1:
The system physically segments the display functions by using the TV for broadcast content and an independent terminal for additional information. This eliminates the need to share the TV screen space, maintaining full broadcast content visibility while providing additional information on a separate device.
Solution Approach 2:
The system transitions from two-dimensional screen space sharing (splitting the TV display) to utilizing a different spatial dimension by introducing an independent terminal with its own display. This moves the additional information display to a separate physical device, preserving the full broadcast content area on the TV.
4Adaptability or versatility
If analog television or public place television is used, then the broadcast content is viewed, but the additional information is not available
Solution Approach 1:
The independent terminal serves multiple functions: it receives audio from any TV (analog or digital), extracts audio features, and provides additional information. This universal terminal can work with any broadcast system without requiring the TV itself to have internet capabilities, making the additional information available across diverse television types.
Solution Approach 2:
The independent terminal acts as an intermediary that bridges the gap between traditional analog/public TVs and digital additional information services. By receiving audio output from the TV and processing it independently, the terminal enables additional information access on legacy or public displays that lack built-in internet connectivity.
5Loss of information
If Internet television is purchased to utilize additional information, then the additional information is available, but financial burden is imposed on the viewer
Solution Approach 1:
The independent terminal autonomously performs audio feature extraction, temporal location determination, and additional information retrieval without requiring the TV to have internet capabilities. This self-service approach allows viewers to use existing TVs with any terminal device, eliminating the need to purchase expensive Internet-capable televisions.
Solution Approach 2:
The system uses inexpensive, readily available terminal devices (smartphones, tablets, computers) instead of requiring expensive Internet televisions. The terminal acts as a temporary, standalone component that provides additional information functionality without the need for costly hardware upgrades to the TV itself.
Data Source
AI summary
The present invention relates to a method and a system for providing additional information on broadcast content, and particularly, to a method and a system for providing additional information corresponding to broadcast content displayed on a television to a separate viewer's terminal. The method for providing additional information on the broadcast content is performed by a voice feature extraction server and comprises the steps of: extracting audio feature data of the broadcast content to store voice feature information previously grouped in preset units in a provided storage space; and detecting voice feature information corresponding to the voice feature data received from the viewer's terminal among the stored one or more pieces of voice feature information and transmitting the detected feature information to the viewer's terminal, wherein the viewer's terminal extracts the voice feature data from an input audio signal according to a preset method and transmits the extracted voice feature data to the voice feature extraction server, a temporal position corresponding to the voice feature data is determined from the received voice feature information, and the additional information is displayed at the temporal position.