> On Apr 8, 2016, at 5:42 PM, Paul Kyzivat <[email protected]> wrote: > > Has anyone tried just running the audio from a session through a > speech-to-text processor? (I expect it would be terrible, but one can hope.)
We have actually done something similar. We had a participant who was deaf, and ISOC paid for a speech-to-text PERSON. We took the things she wrote and displayed them on a screen in plenaries in real time, and people said they appreciated it. It helped them understand things that they managed to hear as garbled. Two comments. First, she did a pretty good job - not perfect, but pretty darn good. Second, just like when you see closed-caption on a TV, what she wrote was largely phonetic, and often picked a homonym or was just plain wrong. I would have to believe that speech-to-text software would not do better than she did.
signature.asc
Description: Message signed with OpenPGP using GPGMail
_______________________________________________ NOTE WELL: This list operates according to http://mipassoc.org/dkim/ietf-list-rules.html. https://www.ietf.org/mailman/listinfo/vmeet
