US Patent 11538455 Speech style transfer
Patent 11538455 was granted and assigned to Dolby Laboratories on December, 2022 by the United States Patent and Trademark Office.
All edits
Edits on 6 Apr, 2023
Golden AI
Infobox
Is a
Patent Applicant
Current Assignee
Patent Jurisdiction
Patent Number
115384550
Date of Patent
December 27, 2022
0Patent Application Number
169699500
Date Filed
February 14, 2019
0Patent Primary Examiner
Edits on 28 Dec, 2022
Golden AI
Edits made to:
Infobox (+10 properties)
Article (+472 characters)
US Patent 11538455 Speech style transfer
Article
Computer-implemented methods for speech synthesis are provided. A speech synthesizer may be trained to generate synthesized audio data that corresponds to words uttered by a source speaker according to speech characteristics of a target speaker. The speech synthesizer may be trained by time-stamped phoneme sequences, pitch contour data and speaker identification data. The speech synthesizer may include a voice modeling neural network and a conditioning neural network.
Infobox
Is a
Patent Applicant
Current Assignee
Patent Jurisdiction
Patent Number
115384550
Date of Patent
December 27, 2022
0Patent Application Number
169699500
Date Filed
February 14, 2019
0Patent Primary Examiner
Find more entities like US Patent 11538455 Speech style transfer
Use the Golden Query Tool to find similar entities by any field in the Knowledge Graph, including industry, location, and more.
