Patent Leaderboard
USPTO Patent Rankings Data through Dec 31, 2025
Home › Contextualized streaming end-to-end speech recognition with trie-based deep biasing and shallow fusion

Contextualized streaming end-to-end speech recognition with trie-based deep biasing and shallow fusion

US Patent 12087306 · Granted Sep 10, 2024

Estimated economic value: $981,989,000 ⓘ

Assignee

Inventors

View full patent text on Google Patents →

More Patents by These Inventors

Audio processing apparatus and method for denoising a multi-channel audio signal2024
Efficient memory transformer based acoustic model for low latency streaming spee2023
Stylizing text-to-speech (TTS) voice response for assistant systems2023
Evaluation infrastructure for testing real-time content search2022
Methods and systems for performing end-to-end spoken language analysis2021
Social hash for language models2021
Social hash for language models2021
Evaluation infrastructure for testing real-time content search2019
Hybrid, offline/online speech translation system2019
User-specific pronunciations in a social networking system2018
Clustering web pages on a search engine results page2017
Hybrid, offline/online speech translation system2016