Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › System and method for combining geographic metadata in automatic speech recognition language and acoustic models

System and method for combining geographic metadata in automatic speech recognition language and acoustic models

US Patent 10121468 · Granted Nov 6, 2018

Estimated economic value: $11,246,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Contextual biasing with text injection2025
Language models using domain-specific model components2024
System and method for rapid customization of speech recognition models2020
System and method for personalization of acoustic models for automatic speech re2020
Speech recognition using log-linear model2018
System and method of using neural transforms of robust audio features for speech2018
System and method for optimizing speech recognition and natural language paramet2018
System and method for rapid customization of speech recognition models2018
System and method for personalization of acoustic models for automatic speech re2017
Addressing missing features in models2017
System and method for managing models for embedded speech and language processin2017
System and method of using neural transforms of robust audio features for speech2017