Google open-sources AI that can distinguish between voices with 92 percent accuracy

Diarization — the process of partitioning out a speech sample into distinctive, homogeneous segments according to who said what — doesn’t come as easy to machines as it does to humans, and training machine learning algorithm to perform it is tougher than it sounds.


View original article


Posted

in

by

Tags:

Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Discover more from try {} except

Subscribe now to keep reading and get access to the full archive.

Continue reading