Inventor

GOEL VAIBHAVA

US43 patents

⚠️ This page may combine multiple inventors who share the name “GOEL VAIBHAVA”. Patents are grouped by organization below to help distinguish them — per-person disambiguation is on the roadmap.

GOEL VAIBHAVA

IBM

Data augmentation method based on stochastic feature mapping for automatic speech recognition

Combining installed audio-visual sensors with ad-hoc mobile audio-visual sensors for smart meeting rooms

Natural language system and method based on unisolated performance metric

Method for likelihood computation in multi-stream HMM based speech recognition

Adjusting a deep neural network acoustic model

System and method for management of call data using a vector based model and relational data structure

Annealed dropout training of neural networks

Adjusting a deep neural network acoustic model

Combining installed audio-visual sensors with ad-hoc mobile audio-visual sensors for smart meeting rooms

Annealed dropout training of neural networks

Deep scattering spectrum in acoustic modeling for speech recognition

Systems and methods for combining stochastic average gradient and hessian-free optimization for sequence training of deep neural networks

Systems and methods for combining stochastic average gradient and hessian-free optimization for sequence training of deep neural networks

Combining installed audio-visual sensors with ad-hoc mobile audio-visual sensors for smart meeting rooms

System and method for management of call data using a vector based model and relational data structure

Natural language interaction with large databases

Data augmentation method based on stochastic feature mapping for automatic speech recognition

Combining installed audio-visual sensors with ad-hoc mobile audio-visual sensors for smart meeting rooms

Compressing feature space transforms

Regularized feature space discrimination adaptation

NUANCE COMMUNICATIONS INC

Privacy-sensitive speech model creation via aggregation of multiple user models

Natural language system and method based on unisolated performance metric

Privacy-sensitive speech model creation via aggregation of multiple user models

Audio-visual speech recognition with scattering operators

Sparse maximum a posteriori (map) adaption

Audio-visual speech recognition with scattering operators

Order statistic techniques for neural networks

Methods and apparatus for speech recognition using visual information

PRYON INCORPORATED

Systems and methods for question-and-answer searching using a cache

Visual structure of documents in question answering

Question-answering system for answering relational questions by utilizing two paths where at least one path uses BERT model

Methods and systems for improved document processing and information retrieval

Document pre-processing for question-and-answer searching

Supervised summarization and structuring of unstructured documents

GOEL VAIBHAVA

Sparse maximum a posteriori (MAP) adaptation

Method and system for using a statistical language model and an action classifier in parallel with grammar for better handling of out-of-grammar utterances

DELIGNE SABINE

Natural language system and method based on unisolated performance metric

EIDE ELLEN MARIE

Method and system for prompt construction for selection from a list of acoustically confusable items in spoken dialog systems

CLAIBORN DAVID

Method and system having hypothesis type variable thresholds

SARIKAYA RUHI

Machine translation (MT) based spoken dialog systems customer/machine dialog

JIANG DAN NING

Forced/predictable adaptation for speech recognition

CHU STEPHEN MINGYU

System and method for likelihood computation in multi-stream HMM based speech recognition

DOGNIN PIERRE

Model restructuring for client and server based automatic speech recognition