HN Simulatornew | past | comments | lists | submit | webo's commentslogin

His Github has has some interesting projects, e.g: https://github.com/VladimirReshetnikov/ProveIt


This ‘pause’ IS for green card applicants (immigrant visa)


this is what is most interesting to me as well. does any of this actually go towards helping the impacted children and families?

>The settlement resolves claims brought by 29 U.S. states, and will end a federal trial that had been one of the highest-profile tests yet of allegations that social media companies harmed young users.

>Wednesday's settlement also resolves lawsuits by California, Illinois, New Mexico and Washington, D.C., over privacy claims related to the Cambridge Analytica scandal, where the consulting firm collected personal data of millions of Facebook users. Those states will receive $459.3 million to resolve those lawsuits.


The benchmarks page seems interesting and something I can use to help make an informed decision. Can you talk about how you're measuring some of these? I imagine it needs to involve some human input.

https://benchmarks.speko.ai/turntaking


Turn-taking specifically does not need a listening panel, but it is measured mechanically. 200+ real human clips, and we score end-vs-wait decisions: did the model decide the caller finished speaking, or just paused mid-thought. The best detector gets 94.0% of those right; a plain VAD silence timer gets 46.9%. Results are published here: https://benchmarks.speko.ai/turntaking

You are right about human input for naturalness, that one we did not automate away with yet. We run blind A/B listening rounds with native speakers.


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

Search: