Patents/Inventors

Tara N. Sainath

Jersey City, NJUS45 patents

42 Patents

US125974172026
Exporting Modular Encoder Features for Streaming and Deliberation ASR
Google LLC
0 cites
US125865792026
End-to-end Segmentation in a Two-pass Cascaded Encoder Automatic Speech Recognition Model
Google LLC
0 cites
US125555732026
Mixture-of-expert Conformer for Streaming Multilingual ASR
Google LLC
0 cites
US125485612026
Universal Monolingual Output Layer for Multilingual Speech Recognition
Google LLC
0 cites
US124887912025
Contextual Biasing with Text Injection
Google LLC
0 cites
US124824552025
Systems and Methods for Training Dual-mode Machine-learned Speech Recognition Models
GOOGLE LLC
0 cites
US124444082025
Two-pass End to End Speech Recognition
GOOGLE LLC
0 cites
US124377522025
Large-scale Language Model Data Selection for Rare-word Speech Recognition
Google LLC
0 cites
US124177702025
Unified Cascaded Encoder ASR Model for Dynamic Model Sizes
Google LLC
0 cites
US124125662025
Lookup-table Recurrent Language Model
Google LLC
0 cites
US123619272025
Emitting Word Timings with End-to-end Models
Google LLC
0 cites
US123545952025
Deliberation by Text-only and Semi-supervised Training
Google LLC
0 cites
US123545972025
Disfluency Detection Models for Natural Conversational Voice Systems
Google LLC
0 cites
US123545982025
Rare Word Recognition with Lm-aware MWER Training
Google LLC
0 cites
US123223832025
Predicting Word Boundaries for On-device Batching of End-to-end Speech Recognition Models
Google LLC
0 cites
US123154972025
Intended Query Detection Using E2E Modeling for Continued Conversation
Google LLC
0 cites
US122548652025
Multi-dialect and Multilingual Speech Recognition
Google LLC
0 cites
US122493172025
Joint Unsupervised and Supervised Training for Multilingual ASR
Google LLC
0 cites
US122115092025
Fusion of Acoustic and Text Representations in RNN-T
Google LLC
0 cites
US121908692025
Optimizing Inference Performance for Conformer
Google LLC
0 cites
US121833222024
Language Agnostic Multilingual End-to-end Streaming On-device ASR System
Google LLC
0 cites
US121189882024
Transducer-based Streaming Deliberation for Cascaded Encoders
Google LLC
0 cites
US121067492024
Speech Recognition with Sequence-to-sequence Models
Google LLC
0 cites
US120738242024
Two-pass End to End Speech Recognition
GOOGLE LLC
0 cites
US120514072024
Contextual Biasing for Speech Recognition
Google LLC
0 cites
US120271542024
Emitting Word Timings with End-to-end Models
Google LLC
0 cites
US120271582024
Deliberation Model-based Two-pass End-to-end Speech Recognition
Google LLC
0 cites
US120147252024
Large-scale Language Model Data Selection for Rare-word Speech Recognition
Google LLC
0 cites
US119420762024
Phoneme-based Contextualization for Cross-lingual Speech Recognition in End-to-end Models
Google LLC
0 cites
US119229322024
Minimum Word Error Rate Training for Attention-based Sequence-to-sequence Models
Google LLC
0 cites
US119084612024
Deliberation Model-based Two-pass End-to-end Speech Recognition
Google LLC
0 cites
US119009152024
Multi-dialect and Multilingual Speech Recognition
Google LLC
0 cites
US117838492023
Enhanced Multi-channel Acoustic Models
Google LLC
0 cites
US117565342023
Adaptive Audio Enhancement for Multichannel Speech Recognition
Google LLC
0 cites
US117492592023
Proper Noun Recognition in End-to-end Speech Recognition
Google LLC
0 cites
US117413662023
Compressed Recurrent Neural Network Models
Google LLC
0 cites
US117154862023
Convolutional, Long Short-term Memory, Fully Connected Deep Neural Networks
Google LLC
0 cites
US116640212023
Contextual Biasing for Speech Recognition
Google LLC
0 cites
US116460192023
Minimum Word Error Rate Training for Attention-based Sequence-to-sequence Models
Google LLC
0 cites
US115942122023
Attention-based Joint Acoustic and Text On-device End-to-end Model
Google LLC
0 cites
US115809562023
Emitting Word Timings with End-to-end Models
Google LLC
0 cites
US115451422023
Using Context Information with End-to-end Models for Speech Recognition
Google LLC
0 cites