Estás usando una versión más antigua del explorador. Usa una versión compatible para obtener la mejor experiencia en MSN.

Parrotron Demo I

Demonstrating how Parrotron improves communication between Dr. Dimitri Kanevsky, a deaf speaker, and Google Home. Parrotron consists of a single end-to-end deep neural network trained to directly convert speech from a speaker with atypical speech patterns into fluent synthesized speech, without an intermediate step of generating text—skipping speech recognition altogether. See
image beaconimage beaconimage beacon