Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › System and method of using neural transforms of robust audio features for speech processing

System and method of using neural transforms of robust audio features for speech processing

US Patent 9754587 · Granted Sep 5, 2017

Estimated economic value: $6,253,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Speaker attributed transcript generation2025
Personalized natural language processing system2024
Dynamic gradient aggregation for training neural networks2024
Processing overlapping speech from distributed devices2024
Audio-visual diarization to identify meeting attendees2024
End-of-turn detection in spoken dialogues2023
Smart interactive media content guide2023
Distributed device meeting initiation2022
Low-latency speech separation2022
Speaker attributed transcript generation2022
Exploiting visual information for enhancing audio signals via source separation 2022
Data-driven and rule-based speech recognition output enhancement2022