Abstract
A system and method for real-time media sanitization analyzes audio and video content ahead of playback using on-device artificial intelligence processing. The system analyzes closed captioning or subtitle data, or applies speech-to-text processing to audio, and analyzes video frames to identify content associated with user-defined filtering categories. The system compares detected content with user-defined sensitivity thresholds and selectively applies audio masking or video masking to corresponding portions of the media. Audio masking includes volume reduction or beep insertion, and video masking includes blurring or temporarily displaying a black screen. The system applies the masking during playback without permanently modifying the original media source, allowing remaining content to continue playing without modification.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Agarwal, Nikita, "System And Method For Real-Time Semantic Sanitization Of Media Streams Via On-Device Artificial Intelligence", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/12632