David Teh-hwa Kao

Person

San Francisco, CA, US

People

Patents Grantslast 30 patents

Information Patent Grant
Neural-network-based text-to-speech model for novel speaker generation
- Patent number 12,087,275
- Issue date Sep 10, 2024
- Google LLC
- Daisy Antonia Stanton
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Variational embedding capacity in expressive end-to-end speech synt...
- Patent number 12,067,969
- Issue date Aug 20, 2024
- Google LLC
- Eric Dean Battenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Controlling expressivity in end-to-end speech synthesis systems
- Patent number 11,676,573
- Issue date Jun 13, 2023
- Google LLC
- Daisy Stanton
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Variational embedding capacity in expressive end-to-end speech synt...
- Patent number 11,646,010
- Issue date May 9, 2023
- Google LLC
- Eric Dean Battenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Variational embedding capacity in expressive end-to-end speech synt...
- Patent number 11,222,621
- Issue date Jan 11, 2022
- Google LLC
- Eric Dean Battenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS

Patents Applicationslast 30 patents

Information Patent Application
Variational Embedding Capacity in Expressive End-to-End Speech Synt...
- Publication number 20240395238
- Publication date Nov 28, 2024
- Google LLC
- Eric Dean Battenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Neural-Network-Based Text-to-Speech Model for Novel Speaker Generation
- Publication number 20240395239
- Publication date Nov 28, 2024
- Google LLC
- Daisy Antonia Stanton
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Controlling Expressivity In End-to-End Speech Synthesis Systems
- Publication number 20230274728
- Publication date Aug 31, 2023
- Google LLC
- Daisy Stanton
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Variational Embedding Capacity in Expressive End-to-End Speech Synt...
- Publication number 20230260504
- Publication date Aug 17, 2023
- Google LLC
- Eric Dean Battenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Neural-Network-Based Text-to-Speech Model for Novel Speaker Generation
- Publication number 20230206898
- Publication date Jun 29, 2023
- Google LLC
- Daisy Antonia Stanton
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Variational Embedding Capacity in Expressive End-to-End Speech Synt...
- Publication number 20220101826
- Publication date Mar 31, 2022
- Google LLC
- Eric Dean Battenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Controlling Expressivity In End-to-End Speech Synthesis Systems
- Publication number 20210035551
- Publication date Feb 4, 2021
- Google LLC
- Daisy Stanton
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Variational Embedding Capacity in Expressive End-to-End Speech Synt...
- Publication number 20200372897
- Publication date Nov 26, 2020
- Google LLC
- Eric Dean Battenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS

David Teh-hwa Kao

Person

Patents Grantslast 30 patents

Neural-network-based text-to-speech model for novel speaker generation

Variational embedding capacity in expressive end-to-end speech synt...

Controlling expressivity in end-to-end speech synthesis systems

Variational embedding capacity in expressive end-to-end speech synt...

Variational embedding capacity in expressive end-to-end speech synt...

Patents Applicationslast 30 patents

Variational Embedding Capacity in Expressive End-to-End Speech Synt...

Neural-Network-Based Text-to-Speech Model for Novel Speaker Generation

Controlling Expressivity In End-to-End Speech Synthesis Systems

Variational Embedding Capacity in Expressive End-to-End Speech Synt...

Neural-Network-Based Text-to-Speech Model for Novel Speaker Generation

Variational Embedding Capacity in Expressive End-to-End Speech Synt...

Controlling Expressivity In End-to-End Speech Synthesis Systems

Variational Embedding Capacity in Expressive End-to-End Speech Synt...