Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Systems and methods for neural text-to-speech using convolutional sequence learning

Systems and methods for neural text-to-speech using convolutional sequence learning

US Patent 10796686 · Granted Oct 6, 2020

Estimated economic value: $29,212,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Self-improving LLMs through consistency-based self-generated demonstrations2025
Data path circuit design using reinforcement learning2025
Image analysis by prompting of machine-learned models using chain of thought2025
Cloud-based device discovery2025
Active learning via a sample consistency assessment2025
Reinforcement learning based locally interpretable models2024
Data valuation using reinforcement learning2024
Attention neural networks with parallel attention and feed-forward layers2024
Distance-based learning confidence model2024
Interpretable tabular data learning using sequential sparse attention2024
Attention-based prototypical learning2024
Speech denoising via discrete representation learning2024