Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Optimizations to decoding of WFST models for automatic speech recognition

Optimizations to decoding of WFST models for automatic speech recognition

US Patent 10127902 · Granted Nov 13, 2018

Estimated economic value: $26,640,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Enhanced spatial audio-based virtual seating arrangements2025
Deepfake detection models utilizing subject-specific libraries2025
Adaptively recognizing speech using key phrases2024
Automatic speech recognition with filler model processing2023
Method and system of automatic speech recognition with highly efficient decoding2023
Systems and methods for energy efficient and low power distributed automatic spe2022
Method and system of automatic speech recognition with highly efficient decoding2021
Automatic speech recognition with filler model processing2021
Continuous topic detection and adaption in audio environments2021
Continuous topic detection and adaption in audio environments2021
Low resource key phrase detection for wake on voice2021
Fixed point integer implementations for neural networks2020