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

[Airicist]

Developer - Google Inc.

"Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separation"

by Fadi Biadsy, Ron J. Weiss, Pedro J. Moreno, Dimitri Kanvesky, Ye Jia
April 8, 2019


"Parrotron: New Research into Improving Verbal Communication for People with Speech Impairments"

by Fadi Biadsy and Ron Weiss
July 17, 2019

[Airicist]

Parrotron demo I

Published on Jul 16, 2019

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.

[Airicist]

Parrotron demo II

Uploaded on Jul 16, 2019

[Airicist]

Article "Google’s Parrotron is an AI tool for people with speech impediments"

by Kyle Wigger
July 17, 2019