Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Training a language model of an end-to-end automatic speech recognition model using random encoder features

Training a language model of an end-to-end automatic speech recognition model using random encoder features

US Patent 12431122 · Granted Sep 30, 2025

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Multi-stream recurrent neural network transducer(s)2025
Context-aware neural confidence estimation for rare word speech recognition2025
On-device speech synthesis of textual segments for training of on-device speech 2025
Unsupervised federated learning of machine learning model layers2025
Multi-dialect and multilingual speech recognition2025
Joint unsupervised and supervised training for multilingual ASR2025
Generation and utilization of pseudo-correction(s) to prevent forgetting of pers2025
Ephemeral learning of machine learning model(s)2024
Sound model localization within an environment2024
Unsupervised federated learning of machine learning model layers2024
On-device speech synthesis of textual segments for training of on-device speech 2024
Multi-dialect and multilingual speech recognition2024