Parrotron, speech technologies to help those with impaired or atypical speech to be understood by both people and devices, Google Inc., Mountain View,

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.

Click to expand...