Abstract
Online video conference tools provide for the ability to conduct meetings among multiple participants are remote from each other. While such tools are useful to enable remote people to communicate in a group setting, it can often be challenging to conduct online meetings when it is difficult to understand what participants may be saying, for example due to participants speaking different language. Utilizing a combination of camera intelligence, large language models (LLMs), and directional audio, techniques proposed herein provide for the ability to perform automatic, instant, personal language translation in meeting spaces.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Klasson, Sigurd, "LIVE LANGUAGE TRANSLATION UTILIZING DIRECTIONAL AUDIO AND FACIAL RECOGNITION", Technical Disclosure Commons, (October 29, 2024)
https://www.tdcommons.org/dpubs_series/7481