Inventor

ROSENBERG ANDREW

US17 patents

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

ROSENBERG ANDREW

GOOGLE LLC

Advancing the use of text and speech in ASR pretraining with consistency and contrastive losses

Consistency prediction on streaming sequence models

Instantaneous learning in text-to-speech during dialog

Synthesized data augmentation using voice conversion and speech recognition models

Using speech recognition to improve cross-language speech synthesis

Improving speech recognition with speech synthesis-based model adapation

Instantaneous learning in text-to-speech during dialog

Training speech synthesis to generate distinct speech sounds

Generating diverse and natural text-to-speech samples

Using aligned text and speech representations to train automatic speech recognition models without transcribed speech data

Supervised and unsupervised training with contrastive loss over sequences

Guided data selection for masked speech modeling based on an average score assigned to encoded representations of an utterance

MASIAKOS PETER T

Apparatus and method for preserving a tissue margin

BUNDY CORP

Quick connector with secondary latch

BINKOWSKI EDWARD S

Computer system and method for de-identification of patient and/or individual health and/or medical related information, such as patient micro-data

MEDCO HEALTH SOLUTIONS INC

Computer system and method for de-identification of patient and/or individual health and/or medical related information, such as patient micro-data

IBM

Voice-transformation based data augmentation for prosodic classification