Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Multi-task learning for end-to-end automated speech recognition confidence and deletion estimation

Multi-task learning for end-to-end automated speech recognition confidence and deletion estimation

US Patent 12456460 · Granted Oct 28, 2025

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Data processing system2025
Unsupervised data selection via discrete speech representation for automatic spe2025
Guided data selection for masked speech modeling based on an average score assig2025
Parallel tacotron non-autoregressive and controllable TTS2025
Training for long-form speech recognition2025
Locking mechanism and rotating lifting platform employing mechanism2025
Rocking arm structure providing additional-wheel support and device having the s2025
Two-pass end to end speech recognition2025
Two-pass end to end speech recognition2025
Context-aware neural confidence estimation for rare word speech recognition2025
Unified cascaded encoder ASR model for dynamic model sizes2025
4-bit conformer with accurate quantization training for speech recognition2025