Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Contextual biasing of neural language models using metadata from a natural language understanding component and embedded recent history

Contextual biasing of neural language models using metadata from a natural language understanding component and embedded recent history

US Patent 11710479 · Granted Jul 25, 2023

Estimated economic value: $384,822,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Customizable latency for automatic speech recognition2025
Customizable latency for automatic speech recognition2025
Dynamic language model updates with boosting2025
Dynamic language model updates with boosting2025
Dynamic language model updates with boosting2025
Infusing knowledge graphs into automatic speech recognition2025
Infusing knowledge graphs into automatic speech recognition2025
Removing bias from automatic speech recognition models using internal language m2025
Removing bias from automatic speech recognition models using internal language m2025
Federated learning service in a provider network and training machine learning m2025
Dynamically selectable automated speech recognition using a custom vocabulary2025
Dynamically selectable automated speech recognition using a custom vocabulary2025