Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Neural-network-based text-to-speech model for novel speaker generation

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

US Patent 12087275 · Granted Sep 10, 2024

Estimated economic value: $77,150,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Synthesizing speech from text using neural networks2024
Multilingual speech synthesis and cross-language voice cloning2024
Variational embedding capacity in expressive end-to-end speech synthesis2024
Variational embedding capacity in expressive end-to-end speech synthesis2024
Variational embedding capacity in expressive end-to-end speech synthesis2024
Variational embedding capacity in expressive end-to-end speech synthesis2024
Variational embedding capacity in expressive end-to-end speech synthesis2024
Variational embedding capacity in expressive end-to-end speech synthesis2024
Variational embedding capacity in expressive end-to-end speech synthesis2024
Encoder-decoder models for sequence to sequence mapping2023
Controlling expressivity in end-to-end speech synthesis systems2023
Controlling expressivity in end-to-end speech synthesis systems2023