Stylizing Text-to-Speech (TTS) Voice Response for Assistant Systems

Patent №

US 11,562,744

Granted

2023-01-24

Filed 2020

Owner

FACEBOOK TECHNOLOGIES, LLC

AI components

4

ml · nlp · speech · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16790497

In one embodiment, a method includes receiving a voice input from a user and determining a first style of the voice input, based on first features extracted from the voice input. A second style for a voice response having second features may then be determined based on the first style. Finally, the voice response may be generated based on the second features of the second style, and this voice response may be provided in response to the voice input.

Machine learningNatural languageSpeechAI hardwareG10L 13/033G10L 15/26G10L 13/08G10L 15/02G10L 15/22G06F 40/30G10L 13/047G10L 25/48+2 more

AI classification

Natural language1.00
Speech1.00
AI hardware0.99
Machine learning0.96
Knowledge representation0.27
Evolutionary computation0.02
Vision0.00
Planning0.00

Ownership

FACEBOOK TECHNOLOGIES, LLC

assignment · 520160407

Assignors

GAO, YANG, ZHENG, WEIYI, YANG, ZHAOJUN, KOEHLER, THILO WOLFGANG, FUEGEN, CHRISTIAN, HE, QING

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

© 2026 NYSGPT2525 LLC