Inventor

KINGSBURY BRIAN E D

US28 patents

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

KINGSBURY BRIAN E D

IBM

Training deep neural network acoustic models using distributed hessian-free optimization

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

Systems and methods for accelerating hessian-free optimization for deep neural networks by implicit preconditioning and sampling

Classifier-based system combination for spoken term detection

Integrating dialog history into end-to-end spoken language understanding systems

Training end-to-end spoken language understanding systems with unordered entities

End-to-end spoken language understanding without full transcripts

Low-rank matrix factorization for deep belief network training with high-dimensional output targets

Integrating text inputs for training and adapting neural network transducer ASR models

Method and system for order-free spoken term detection

Deep scattering spectrum in acoustic modeling for speech recognition

Method and system for efficient spoken term detection using confusion networks

Speech label accelerators and techniques for using same

Length perturbation techniques for improving generalization of deep neural network acoustic models

Multi-speaker data augmentation for improved end-to-end automatic speech recognition

Customization of recurrent neural network transducers for speech recognition

Soft-forgetting for connectionist temporal classification based automatic speech recognition

Textual knowledge transfer for improved speech recognition and understanding

Systems and methods for accelerating hessian-free optimization for deep neural networks by implicit preconditioning and sampling

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

Transliteration based data augmentation for training multilingual ASR acoustic models in low resource settings

Method and system for order-free spoken term detection

Reducing exposure bias in machine learning training of sequence-to-sequence transducers

Method and system for efficient spoken term detection using confusion networks

End-to-end integration of dialog history for spoken language understanding

Input encoding for classifier generalization

INTERNAT COMP SCIENCE INST

Feature extraction for automatic speech recognition

NUANCE COMMUNICATIONS INC

Learning front-end speech recognition parameters within neural network training