Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Using corrections, of predicted textual segments of spoken utterances, for training of on-device speech recognition model

Using corrections, of predicted textual segments of spoken utterances, for training of on-device speech recognition model

US Patent 12183321 · Granted Dec 31, 2024

Estimated economic value: $118,851,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Multi-stream recurrent neural network transducer(s)2025
Evaluating on-device machine learning model(s) based on performance measures of 2025
On-device speech synthesis of textual segments for training of on-device speech 2025
On-device speech synthesis of textual segments for training of on-device speech 2025
Multi-modal input on an electronic device2025
Exploring heterogeneous characteristics of layers in ASR models for more efficie2025
Exploring heterogeneous characteristics of layers in ASR models for more efficie2025
Unsupervised federated learning of machine learning model layers2025
Unsupervised federated learning of machine learning model layers2025
Identifying and correcting automatic speech recognition (ASR) misrecognitions in2025
Identifying and correcting automatic speech recognition (ASR) misrecognitions in2025
Using corrections, of automated assistant functions, for training of on-device m2025