Zoom video communications, inc. (20240212702). MANUAL-ENROLLMENT-FREE PERSONALIZED DENOISE simplified abstract
Contents
MANUAL-ENROLLMENT-FREE PERSONALIZED DENOISE
Organization Name
zoom video communications, inc.
Inventor(s)
Jiachuan Deng of Singapore (SG)
Cheng Lun Hu of Singapore (SG)
Zhaofeng Jia of Saratoga CA (US)
Zhengwei Wei of Singapore (SG)
MANUAL-ENROLLMENT-FREE PERSONALIZED DENOISE - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240212702 titled 'MANUAL-ENROLLMENT-FREE PERSONALIZED DENOISE
The abstract describes a denoise engine that processes voice content from a virtual meeting to generate personalized denoised voice content for a user account.
- The denoise engine collects voice segments from audio data of a virtual meeting.
- It identifies an audio embedding model and receives a speaker embedding based on the collected voice segments.
- By applying the speaker embedding to the audio data, the denoise engine generates personalized denoised voice content for the user account.
Potential Applications: - Enhancing audio quality in virtual meetings - Improving user experience in online communication platforms
Problems Solved: - Reducing background noise in audio data - Enhancing voice clarity for better communication
Benefits: - Improved audio quality for virtual meetings - Personalized denoised voice content for users
Commercial Applications: Title: Enhanced Audio Quality Technology for Virtual Meetings This technology can be used in video conferencing platforms, online education systems, and telecommunication services to provide users with clear and personalized audio experiences.
Questions about the technology: 1. How does the denoise engine differentiate between voice content and other types of audio content in the virtual meeting? 2. What are the potential limitations of the denoise engine in processing audio data from virtual meetings?
Original Abstract Submitted
various embodiments of an apparatus, method(s), system(s) and computer program product(s) described herein are directed to a denoise engine. the denoise engine collects segments of voice content of a first user account from audio data associated with a virtual meeting. the audio data further includes additional types of audio content. the denoise engine identifies an audio embedding model. the denoise engine receives a speaker embedding generated by the audio embedding model. the speaker embedding based on the collected segments of voice content. the denoise engine generates personalized denoised voice content of the first user account for the virtual meeting by applying the speaker embedding to the audio data associated with a virtual meeting.
