Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Unsupervised learning of disentangled speech content and style representation

Unsupervised learning of disentangled speech content and style representation

US Patent 12027151 · Granted Jul 2, 2024

Estimated economic value: $130,174,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Systems and methods for training dual-mode machine-learned speech recognition mo2025
Two-pass end to end speech recognition2025
Anti-tumor compound and preparation method and use thereof2025
End-to-end speech waveform generation through data density gradient estimation2025
Using aligned text and speech representations to train automatic speech recognit2025
Convolution-augmented transformer models2025
Convolution-augmented transformer models2025
Emitting word timings with end-to-end models2025
Two-level speech prosody transfer2025
Neural architecture search with factorized hierarchical search space2025
Advancing the use of text and speech in ASR pretraining with consistency and con2025
Two-level text-to-speech systems using synthetic training data2025