Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Minimum word error rate training for attention-based sequence-to-sequence models

Minimum word error rate training for attention-based sequence-to-sequence models

US Patent 11922932 · Granted Mar 5, 2024

Estimated economic value: $62,822,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Contextual biasing with text injection2025
Contextual biasing with text injection2025
Training for long-form speech recognition2025
Systems and methods for training dual-mode machine-learned speech recognition mo2025
Two-pass end to end speech recognition2025
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
End-to-end speech waveform generation through data density gradient estimation2025
Convolution-augmented transformer models2025