Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Predicting word boundaries for on-device batching of end-to-end speech recognition models

Predicting word boundaries for on-device batching of end-to-end speech recognition models

US Patent 12322383 · Granted Jun 3, 2025

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Contextual biasing with text injection2025
Systems and methods for training dual-mode machine-learned speech recognition mo2025
Two-pass end to end speech recognition2025
Large-scale language model data selection for rare-word speech recognition2025
Unified cascaded encoder ASR model for dynamic model sizes2025
Unified cascaded encoder ASR model for dynamic model sizes2025
Lookup-table recurrent language model2025
Convolution-augmented transformer models2025
Emitting word timings with end-to-end models2025
Deliberation by text-only and semi-supervised training2025
Disfluency detection models for natural conversational voice systems2025
Disfluency detection models for natural conversational voice systems2025