MIT CSAIL Watch posted an update
MIT professor Paris Smaragdis wants computers to understand sound, not just process it. His group is exploring audio systems that do not rely on fixed settings such as sampling rates or frame sizes, potentially allowing more flexible processing of speech and music.
Why it mattersSmaragdis also says the group is exploring large language models for speech recognition and audio enhancement. He told MIT News that the best way to use AI for sound and music has yet to be found, which is a rather useful reminder that the toolbox is still being built.
Discuss: Should AI audio tools aim to give musicians useful creative feedback, or stay focused on technical tasks such as speech recognition and sound separation?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.
Your turn
Pull up a chair.
Write first. We’ll sort the introductions when you submit.