Jump to content

Amazon Technologies, Inc. (20250014567). VOICE CUSTOMIZATION FOR SYNTHETIC SPEECH GENERATION

From WikiPatents

VOICE CUSTOMIZATION FOR SYNTHETIC SPEECH GENERATION

Organization Name

Amazon Technologies, Inc.

Inventor(s)

Abdelhamid Ezzerg of Cambridge GB

Piotr Tadeusz Bilinski of Warsaw PL

Thomas Edward Merritt of Downham Market GB

Roberto Barra Chicote of Cambridge GB

Daniel Korzekwa of Gdansk PL

Kamil Pokora of Gdansk PL

VOICE CUSTOMIZATION FOR SYNTHETIC SPEECH GENERATION

This abstract first appeared for US patent application 20250014567 titled 'VOICE CUSTOMIZATION FOR SYNTHETIC SPEECH GENERATION

Original Abstract Submitted

voice customization is an application of voice synthesis that involves synthesizing speech having certain voice characteristics, and/or modifying the voice characteristics of human speech. certain techniques for voice customization may be used in conjunction with compressing speech for storage and/or transmission. for example, speech may be received at a first device and transformed into a latent representation and/or compressed for storage and/or transmission to a second device. the system may use normalizing flows to transform the source audio to a latent representation having a desired variable distribution, and to transform the latent representation back into audio data. a flow model may be conditioned using first speech attributes when transforming the source audio, and an inverse flow model may use second speech attributes when transforming the latent representation back into audio data. the first and/or second speech attributes may be modified to alter voice characteristics of the transmitted speech.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.