Inventor

THOMAS SAMUEL

US44 patents

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

THOMAS SAMUEL

IBM

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

Using recurrent neural network for partitioning of audio data into segments that each correspond to a speech feature cluster identifier

Annealed dropout training of neural networks

Using long short-term memory recurrent neural network for speaker diarization segmentation

Acoustic model training

Acoustic model training

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

Soft label generation for knowledge distillation

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

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

Using closed captions as parallel training data for customization of closed captioning systems

Detecting and recovering out-of-vocabulary words in voice-to-text transcription systems

Denoising a signal

Denoising a signal

Annealed dropout training of neural networks

Denoising a signal

Training of student neural network with switched teacher neural networks

Teacher and student learning for constructing mixed-domain model

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

Multi-modal lung capacity measurement for respiratory illness prediction

Training teacher machine learning models using lossless and lossy branches

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

Leveraging unpaired text data for training end-to-end spoken language understanding systems

Denoising a signal

Using recurrent neural network for partitioning of audio data into segments that each correspond to a speech feature cluster identifier

Acoustic model training

Constructing, evaluating, and improving a search string for retrieving images indicating item use

Textual knowledge transfer for improved speech recognition and understanding

Training of student neural network with teacher neural networks

Multilingual intent recognition

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

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

Multi-pass speech activity detection strategy to improve automatic speech recognition

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

Constructing, evaluating, and improving a search string for retrieving images indicating item use

Constructing, evaluating, and improving a search string for retrieving images indicating item use

Constructing, evaluating, and improving a search string for retrieving images indicating item use

REFLODX LLC

Array sonography for esophageal characterization

MOSCA FREDERIC

Acoustic wave transducer and sonar antenna with improved directivity

THOMAS SAMUEL

Combined toothbrush case holder and bracket

SCHAEFFLER TECHNOLOGIES GMBH & CO KG

Linear guide rail inlay installation tool

TUFTS COLLEGE

Two-layer photo-responsive membranes