Bhuvana Ramabhadran

Person

Mount Kisco, NY, US

People

Patents Grantslast 30 patents

Information Patent Grant
Supervised and unsupervised training with contrastive loss over seq...
- Patent number 12,230,249
- Issue date Feb 18, 2025
- Google LLC
- Andrew Rosenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Using non-parallel voice conversion for speech conversion models
- Patent number 12,190,862
- Issue date Jan 7, 2025
- Google LLC
- Andrew M. Rosenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Injecting text in self-supervised speech pre-training
- Patent number 12,159,617
- Issue date Dec 3, 2024
- Google LLC
- Zhehuai Chen
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Mixture model attention for flexible streaming and non-streaming au...
- Patent number 12,136,415
- Issue date Nov 5, 2024
- Google LLC
- Kartik Audhkhasi
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Regularizing word segmentation
- Patent number 12,087,279
- Issue date Sep 10, 2024
- Google LLC
- Bhuvana Ramabhadran
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Training speech synthesis to generate distinct speech sounds
- Patent number 12,087,272
- Issue date Sep 10, 2024
- Google LLC
- Andrew Rosenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Multilingual speech synthesis and cross-language voice cloning
- Patent number 12,087,273
- Issue date Sep 10, 2024
- Google LLC
- Yu Zhang
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Multilingual re-scoring models for automatic speech recognition
- Patent number 12,080,283
- Issue date Sep 3, 2024
- Google LLC
- Neeraj Gaur
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Mixture model attention for flexible streaming and non-streaming au...
- Patent number 12,014,729
- Issue date Jun 18, 2024
- Google LLC
- Kartik Audhkhasi
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Using speech recognition to improve cross-language speech synthesis
- Patent number 11,990,117
- Issue date May 21, 2024
- Google LLC
- Zhehuai Chen
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Consistency prediction on streaming sequence models
- Patent number 11,929,060
- Issue date Mar 12, 2024
- Google LLC
- Zhehuai Chen
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Speech recognition using unspoken text and speech synthesis
- Patent number 11,837,216
- Issue date Dec 5, 2023
- Google LLC
- Zhehuai Chen
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Improving speech recognition with speech synthesis-based model adap...
- Patent number 11,823,697
- Issue date Nov 21, 2023
- Google LLC
- Andrew Rosenberg
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Training of student neural network with teacher neural networks
- Patent number 11,741,355
- Issue date Aug 29, 2023
- International Business Machines Corporation
- Takashi Fukuda
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Instantaneous learning in text-to-speech during dialog
- Patent number 11,676,572
- Issue date Jun 13, 2023
- Google LLC
- Vijayaditya Peddinti
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Language-agnostic multilingual modeling using effective script norm...
- Patent number 11,615,779
- Issue date Mar 28, 2023
- Google LLC
- Arindrima Datta
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Training of student neural network with switched teacher neural net...
- Patent number 11,610,108
- Issue date Mar 21, 2023
- International Business Machines Corporation
- Takashi Fukuda
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Speech recognition using unspoken text and speech synthesis
- Patent number 11,605,368
- Issue date Mar 14, 2023
- Google LLC
- Zhehuai Chen
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Multilingual speech synthesis and cross-language voice cloning
- Patent number 11,580,952
- Issue date Feb 14, 2023
- Google LLC
- Yu Zhang
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Generating diverse and natural text-to-speech samples
- Patent number 11,475,874
- Issue date Oct 18, 2022
- Google LLC
- Yu Zhang
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Teacher and student learning for constructing mixed-domain model
- Patent number 11,416,741
- Issue date Aug 16, 2022
- International Business Machines Corporation
- Takashi Fukuda
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Transliteration for speech recognition training and scoring
- Patent number 11,417,322
- Issue date Aug 16, 2022
- Google LLC
- Bhuvana Ramabhadran
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Soft label generation for knowledge distillation
- Patent number 11,410,029
- Issue date Aug 9, 2022
- International Business Machines Corporation
- Takashi Fukuda
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Speech recognition using unspoken text and speech synthesis
- Patent number 11,222,620
- Issue date Jan 11, 2022
- Google LLC
- Zhehuai Chen
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Symbol sequence estimation in speech
- Patent number 11,145,308
- Issue date Oct 12, 2021
- International Business Machines Corporation
- Kenneth W. Church
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Cognitive scheduler
- Patent number 11,036,552
- Issue date Jun 15, 2021
- International Business Machines Corporation
- I-Hsin Chung
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Grant
Combining installed audio-visual sensors with ad-hoc mobile audio-v...
- Patent number 11,019,306
- Issue date May 25, 2021
- International Business Machines Corporation
- Stanley Chen
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Priors adaptation for conservative training of acoustic model
- Patent number 10,991,363
- Issue date Apr 27, 2021
- International Business Machines Corporation
- Gakuto Kurata
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Priors adaptation for conservative training of acoustic model
- Patent number 10,923,110
- Issue date Feb 16, 2021
- International Business Machines Corporation
- Gakuto Kurata
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Grant
Sound identification utilizing periodic indications
- Patent number 10,832,661
- Issue date Nov 10, 2020
- International Business Machines Corporation
- Takashi Fukuda
- G10 - MUSICAL INSTRUMENTS ACOUSTICS

Patents Applicationslast 30 patents

Information Patent Application
Mixture Model Attention for Flexible Streaming and Non-Streaming Au...
- Publication number 20250022458
- Publication date Jan 16, 2025
- Google LLC
- Kartik Audhkhasi
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Multilingual Re-Scoring Models for Automatic Speech Recognition
- Publication number 20240420692
- Publication date Dec 19, 2024
- Google LLC
- Neeraj Gaur
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
MULTILINGUAL SPEECH SYNTHESIS AND CROSS-LANGUAGE VOICE CLONING
- Publication number 20240404506
- Publication date Dec 5, 2024
- Google LLC
- Yu Zhang
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
USING TEXT-INJECTION TO RECOGNIZE SPEECH WITHOUT TRANSCRIPTION
- Publication number 20240304178
- Publication date Sep 12, 2024
- Google LLC
- Andrew M Rosenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Self-Training With Oracle And Top-Ranked Hypotheses
- Publication number 20240296832
- Publication date Sep 5, 2024
- Google LLC
- Andrew M. Rosenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
MASK-CONFORMER AUGMENTING CONFORMER WITH MASK-PREDICT DECODER UNIFY...
- Publication number 20240296837
- Publication date Sep 5, 2024
- Google LLC
- Andrew M. Rosenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
USING SPEECH RECOGNITION TO IMPROVE CROSS-LANGUAGE SPEECH SYNTHESIS
- Publication number 20240282292
- Publication date Aug 22, 2024
- Google LLC
- Zhehuai Chen
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Multilingual Re-Scoring Models for Automatic Speech Recognition
- Publication number 20240203409
- Publication date Jun 20, 2024
- Google LLC
- Neeraj Gaur
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Modular Training for Flexible Attention Based End-to-End ASR
- Publication number 20240185839
- Publication date Jun 6, 2024
- Google LLC
- Kartik AUDHKHASI
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
MASSIVE MULTILINGUAL SPEECH-TEXT JOINT SEMI-SUPERVISED LEARNING FOR...
- Publication number 20240153484
- Publication date May 9, 2024
- Google LLC
- Andrew M. Rosenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Using Aligned Text and Speech Representations to Train Automatic Sp...
- Publication number 20240029715
- Publication date Jan 25, 2024
- Google LLC
- Andrew Rosenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Alignment Prediction to Inject Text into Automatic Speech Recogniti...
- Publication number 20230317059
- Publication date Oct 5, 2023
- Google LLC
- Andrew M. Rosenberg
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Rare Word Recognition with LM-aware MWER Training
- Publication number 20230298570
- Publication date Sep 21, 2023
- Google LLC
- Weiran Wang
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Using Non-Parallel Voice Conversion for Speech Conversion Models
- Publication number 20230298565
- Publication date Sep 21, 2023
- Google LLC
- Andrew M. Rosenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
INSTANTANEOUS LEARNING IN TEXT-TO-SPEECH DURING DIALOG
- Publication number 20230274727
- Publication date Aug 31, 2023
- Google LLC
- Vijayaditya Peddinti
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Language-agnostic Multilingual Modeling Using Effective Script Norm...
- Publication number 20230223009
- Publication date Jul 13, 2023
- Google LLC
- Arindrima Datta
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Speech Recognition Using Unspoken Text and Speech Synthesis
- Publication number 20230197057
- Publication date Jun 22, 2023
- Google LLC
- Zhehuai Chen
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
MULTILINGUAL SPEECH SYNTHESIS AND CROSS-LANGUAGE VOICE CLONING
- Publication number 20230178068
- Publication date Jun 8, 2023
- Google LLC
- Yu Zhang
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Guided Data Selection for Masked Speech Modeling
- Publication number 20230103722
- Publication date Apr 6, 2023
- Google LLC
- Andrew Rosenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Improving Speech Recognition with Speech Synthesis-based Model Adap...
- Publication number 20230058447
- Publication date Feb 23, 2023
- Google LLC
- Andrew Rosenberg
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Advancing the Use of Text and Speech in ASR Pretraining With Consis...
- Publication number 20230013587
- Publication date Jan 19, 2023
- Google LLC
- Andrew Rosenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Injecting Text in Self-Supervised Speech Pre-training
- Publication number 20230017892
- Publication date Jan 19, 2023
- Google LLC
- Zhehuai Chen
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Training Speech Synthesis to Generate Distinct Speech Sounds
- Publication number 20230009613
- Publication date Jan 12, 2023
- Google LLC
- Andrew Rosenberg
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Self-Adaptive Distillation
- Publication number 20220309340
- Publication date Sep 29, 2022
- Google LLC
- Isabel Leal
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Regularizing Word Segmentation
- Publication number 20220310061
- Publication date Sep 29, 2022
- Google LLC
- Bhuvana Ramabhadran
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Mixture Model Attention for Flexible Streaming and Non-Streaming Au...
- Publication number 20220310074
- Publication date Sep 29, 2022
- Google LLC
- Kartik Audhkhasi
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Multilingual Re-Scoring Models for Automatic Speech Recognition
- Publication number 20220310081
- Publication date Sep 29, 2022
- Google LLC
- Neeraj Gaur
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Supervised and Unsupervised Training with Contrastive Loss Over Seq...
- Publication number 20220310065
- Publication date Sep 29, 2022
- Google LLC
- Andrew Rosenberg
- G06 - COMPUTING CALCULATING COUNTING
Information Patent Application
Mixture Model Attention for Flexible Streaming and Non-Streaming Au...
- Publication number 20220310073
- Publication date Sep 29, 2022
- Google LLC
- Kartik Audhkhasi
- G10 - MUSICAL INSTRUMENTS ACOUSTICS
Information Patent Application
Conformer-based Speech Conversion Model
- Publication number 20220310056
- Publication date Sep 29, 2022
- Google LLC
- Bhuvana Ramabhadran
- G10 - MUSICAL INSTRUMENTS ACOUSTICS

Bhuvana Ramabhadran

Person

Patents Grantslast 30 patents

Supervised and unsupervised training with contrastive loss over seq...

Using non-parallel voice conversion for speech conversion models

Injecting text in self-supervised speech pre-training

Mixture model attention for flexible streaming and non-streaming au...

Regularizing word segmentation

Training speech synthesis to generate distinct speech sounds

Multilingual speech synthesis and cross-language voice cloning

Multilingual re-scoring models for automatic speech recognition

Mixture model attention for flexible streaming and non-streaming au...

Using speech recognition to improve cross-language speech synthesis

Consistency prediction on streaming sequence models

Speech recognition using unspoken text and speech synthesis

Improving speech recognition with speech synthesis-based model adap...

Training of student neural network with teacher neural networks

Instantaneous learning in text-to-speech during dialog

Language-agnostic multilingual modeling using effective script norm...

Training of student neural network with switched teacher neural net...

Speech recognition using unspoken text and speech synthesis

Multilingual speech synthesis and cross-language voice cloning

Generating diverse and natural text-to-speech samples

Teacher and student learning for constructing mixed-domain model

Transliteration for speech recognition training and scoring

Soft label generation for knowledge distillation

Speech recognition using unspoken text and speech synthesis

Symbol sequence estimation in speech

Cognitive scheduler

Combining installed audio-visual sensors with ad-hoc mobile audio-v...

Priors adaptation for conservative training of acoustic model

Priors adaptation for conservative training of acoustic model

Sound identification utilizing periodic indications

Patents Applicationslast 30 patents

Mixture Model Attention for Flexible Streaming and Non-Streaming Au...

Multilingual Re-Scoring Models for Automatic Speech Recognition

MULTILINGUAL SPEECH SYNTHESIS AND CROSS-LANGUAGE VOICE CLONING

USING TEXT-INJECTION TO RECOGNIZE SPEECH WITHOUT TRANSCRIPTION

Self-Training With Oracle And Top-Ranked Hypotheses

MASK-CONFORMER AUGMENTING CONFORMER WITH MASK-PREDICT DECODER UNIFY...

USING SPEECH RECOGNITION TO IMPROVE CROSS-LANGUAGE SPEECH SYNTHESIS

Multilingual Re-Scoring Models for Automatic Speech Recognition

Modular Training for Flexible Attention Based End-to-End ASR

MASSIVE MULTILINGUAL SPEECH-TEXT JOINT SEMI-SUPERVISED LEARNING FOR...

Using Aligned Text and Speech Representations to Train Automatic Sp...

Alignment Prediction to Inject Text into Automatic Speech Recogniti...

Rare Word Recognition with LM-aware MWER Training

Using Non-Parallel Voice Conversion for Speech Conversion Models

INSTANTANEOUS LEARNING IN TEXT-TO-SPEECH DURING DIALOG

Language-agnostic Multilingual Modeling Using Effective Script Norm...

Speech Recognition Using Unspoken Text and Speech Synthesis

MULTILINGUAL SPEECH SYNTHESIS AND CROSS-LANGUAGE VOICE CLONING

Guided Data Selection for Masked Speech Modeling

Improving Speech Recognition with Speech Synthesis-based Model Adap...

Advancing the Use of Text and Speech in ASR Pretraining With Consis...

Injecting Text in Self-Supervised Speech Pre-training

Training Speech Synthesis to Generate Distinct Speech Sounds

Self-Adaptive Distillation

Regularizing Word Segmentation

Mixture Model Attention for Flexible Streaming and Non-Streaming Au...

Multilingual Re-Scoring Models for Automatic Speech Recognition

Supervised and Unsupervised Training with Contrastive Loss Over Seq...

Mixture Model Attention for Flexible Streaming and Non-Streaming Au...

Conformer-based Speech Conversion Model