Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Mixture model attention for flexible streaming and non-streaming automatic speech recognition

Mixture model attention for flexible streaming and non-streaming automatic speech recognition

US Patent 12014729 · Granted Jun 18, 2024

Estimated economic value: $142,199,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Guided data selection for masked speech modeling based on an average score assig2025
Instantaneous learning in text-to-speech during dialog2025
Self-adaptive distillation2025
Cross-lingual speech recognition2025
Contextual tagging and biasing of grammars inside word lattices2025
Using aligned text and speech representations to train automatic speech recognit2025
Sub-models for neural contextual biasing with attention and embedding space2025
Rare word recognition with LM-aware MWER training2025
Rare word recognition with LM-aware MWER training2025
End-to-end speech conversion2025
Conformer-based speech conversion model2025
Advancing the use of text and speech in ASR pretraining with consistency and con2025