He added that the models are automatically deleted after every meeting and that Microsoft won’t use or store any of the data to improve its own AI. The feature uses details such as meeting invitations, participant names, and attachments to automatically improve the accuracy of each transcript. Chhabra said this means no one at Microsoft ever sees the content. Over the last two years we’ve made significant strides in solving this problem and have dramatically improved our models for accuracy using meeting context in real time and cutting edge AI. Shalendra Chhabra, a Teams program manager, said Microsoft had been working on the tool for years:ĭelivering live transcription with high accuracy, minimal latency, and cost efficiency at enterprise scale has been one of the toughest challenges in the industry.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |