News for hackers. Stuff that matters.
Re:Wav2vec Overview: Semi and Unsupervised Speech Recognition by monocasa on Saturday July 03, 2021 @01:00PM (#27723023)
Generalized reverse projection through even non recurrent neural networks is still an open research problem.

So no in this case.

Re:Wav2vec Overview: Semi and Unsupervised Speech Recognition by sdenton4 on Sunday July 04, 2021 @02:23PM (#27731588)
I wouldn't rule it out entirely; you could use these as a replacement for linguistic inputs in a tts system, for example, and I imagine it wouldn't be totally terrible. It would still end up being a pretty heavy system, though, with many other parts.
Re:Wav2vec Overview: Semi and Unsupervised Speech Recognition by spywaregorilla on Saturday July 03, 2021 @01:09PM (#27723095)
That doesn't sound like a particularly realistic problem to solve.
Re:Wav2vec Overview: Semi and Unsupervised Speech Recognition by monocasa on Saturday July 03, 2021 @01:15PM (#27723134)
I agree, but all the more glory if someone does solve it then. And the field is still new enough that I don't want to be cited for decades like the iPod release "no wireless. Less space than a Nomad. Lame." slashdot comment.