TEXT-TO-SPEECH (TTS) PROCESSING

Patent №

US 10,692,484

Granted

2020-06-23

Filed 2018

Owner

AMAZON TECHNOLOGIES, INC.

AI components

4

ml · nlp · speech · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16007757

A speech model is trained using multi-task learning. A first task may correspond to how well predicted audio matches training audio; a second task may correspond to a metric of perceived audio quality. The speech model may include, during training, layers related to the second task that are discarded at runtime.

Machine learningNatural languageSpeechAI hardwareG10L 13/02G10L 13/08G06N 3/0442G06N 3/045G06N 3/0464G06N 3/0495G06N 3/082G06N 3/09+6 more

AI classification

Speech1.00
Machine learning1.00
Natural language1.00
AI hardware1.00
Vision0.30
Knowledge representation0.01
Planning0.00
Evolutionary computation0.00

Ownership

AMAZON TECHNOLOGIES, INC.

assignment · 460780662

Assignors

MERRITT, THOMAS EDWARD, NADOLSKI, ADAM FRANCISZEK, PRATEEK, NISHANT, PUTRYCZ, BARTOSZ, CHICOTE, ROBERTO BARRA, AGGARWAL, VATSAL, BREEN, ANDREW PAUL

On an employer assignment, the assignors are typically the inventors.

© 2026 NYSGPT2525 LLC