Ke Hu

Person

Stony Brook, NY, US

People

Patents Grantslast 30 patents

Information Patent Grant
Transducer-based streaming deliberation for cascaded encoders
- Patent number 12,118,988
- Issue date Oct 15, 2024
- Google LLC
- Ke Hu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Deliberation model-based two-pass end-to-end speech recognition
- Patent number 12,027,158
- Issue date Jul 2, 2024
- Google LLC
- Ke Hu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Phoneme-based contextualization for cross-lingual speech recognitio...
- Patent number 11,942,076
- Issue date Mar 26, 2024
- Google LLC
- Ke Hu
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Deliberation model-based two-pass end-to-end speech recognition
- Patent number 11,908,461
- Issue date Feb 20, 2024
- Google LLC
- Ke Hu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Learning word-level confidence for subword end-to-end automatic spe...
- Patent number 11,610,586
- Issue date Mar 21, 2023
- Google LLC
- David Qiu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Phoneme-based contextualization for cross-lingual speech recognitio...
- Patent number 11,270,687
- Issue date Mar 8, 2022
- Google LLC
- Ke Hu
- G10 - MUSICAL INSTRUMENTS ACOUSTICS

Patents Applicationslast 30 patents

Information Patent Application
MIXTURE-OF-EXPERT CONFORMER FOR STREAMING MULTILINGUAL ASR
- Publication number 20240304185
- Publication date Sep 12, 2024
- Google LLC
- Ke Hu
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Deliberation by Text-Only and Semi-Supervised Training
- Publication number 20230298563
- Publication date Sep 21, 2023
- Google LLC
- Ke Hu
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Deliberation Model-Based Two-Pass End-To-End Speech Recognition
- Publication number 20230186907
- Publication date Jun 15, 2023
- Google LLC
- Ke Hu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Transducer-Based Streaming Deliberation for Cascaded Encoders
- Publication number 20230109407
- Publication date Apr 6, 2023
- Google LLC
- Ke Hu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Deliberation of Streaming RNN-Transducer by Non-Autoregressive Deco...
- Publication number 20230107248
- Publication date Apr 6, 2023
- Google LLC
- Weiran Wang
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Learning Word-Level Confidence for Subword End-To-End Automatic Spe...
- Publication number 20220270597
- Publication date Aug 25, 2022
- Google LLC
- David Qiu
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
PHONEME-BASED CONTEXTUALIZATION FOR CROSS-LINGUAL SPEECH RECOGNITIO...
- Publication number 20220172706
- Publication date Jun 2, 2022
- Google LLC
- Ke Hu
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Deliberation Model-Based Two-Pass End-To-End Speech Recognition
- Publication number 20210225369
- Publication date Jul 22, 2021
- Google LLC
- Ke Hu
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
PHONEME-BASED CONTEXTUALIZATION FOR CROSS-LINGUAL SPEECH RECOGNITIO...
- Publication number 20200349923
- Publication date Nov 5, 2020
- Google LLC
- Ke Hu
- G10 - MUSICAL INSTRUMENTS ACOUSTICS

Person

Patents Grantslast 30 patents

Transducer-based streaming deliberation for cascaded encoders

Deliberation model-based two-pass end-to-end speech recognition

Phoneme-based contextualization for cross-lingual speech recognitio...

Deliberation model-based two-pass end-to-end speech recognition

Learning word-level confidence for subword end-to-end automatic spe...

Phoneme-based contextualization for cross-lingual speech recognitio...

Patents Applicationslast 30 patents

MIXTURE-OF-EXPERT CONFORMER FOR STREAMING MULTILINGUAL ASR

Deliberation by Text-Only and Semi-Supervised Training

Deliberation Model-Based Two-Pass End-To-End Speech Recognition

Transducer-Based Streaming Deliberation for Cascaded Encoders

Deliberation of Streaming RNN-Transducer by Non-Autoregressive Deco...

Learning Word-Level Confidence for Subword End-To-End Automatic Spe...

PHONEME-BASED CONTEXTUALIZATION FOR CROSS-LINGUAL SPEECH RECOGNITIO...

Deliberation Model-Based Two-Pass End-To-End Speech Recognition

PHONEME-BASED CONTEXTUALIZATION FOR CROSS-LINGUAL SPEECH RECOGNITIO...