*I think we're less than ten years away from completely generative pop, vocals, ... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

mehwoot on Aug 9, 2015 | parent | context | favorite | on: Classical music generation with recurrent neural n...

I think we're less than ten years away from completely generative pop, vocals, sound design, and all.

I highly doubt this, because of the vocals. Generating coherent appealing lyrics and synthesizing voice to sound natural isn't going to happen in 10 years time. Would be really cool if I was wrong, though.

TheOtherHobbes on Aug 9, 2015 [–]

See also, Vocaloid.

It's not so different to autotuned vocals now. The most recent versions are already significantly better than the original implementation.

Consider applying for YC's Spring batch! Applications are open till Feb 11.
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact