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

I respectfully disagree. As far as I understand, it is not about Q&A/jeopardy kind of context. It's about generating a TED speech that would involve deep domain expertise but more importantly tone and speech technics to make it great to hear...



What is preventing them from just playing back a pre recorded speech from a human?


The topic isn't known in advance. The robot has to prepare a speech on a specified topic without human interaction.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: