Learnings from curating a trustworthy, well-annotated, and useful dataset of disordered English speech

no code implementations • 13 Sep 2024 • Pan-Pan Jiang, Jimmy Tobin, Katrin Tomanek, Robert L. MacDonald, Katie Seaver, Richard Cave, Marilyn Ladewig, Rus Heywood, Jordan R. Green

Project Euphonia, a Google initiative, is dedicated to improving automatic speech recognition (ASR) of disordered speech.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

An analysis of degenerating speech due to progressive dysarthria on ASR performance

no code implementations • 31 Oct 2022 • Katrin Tomanek, Katie Seaver, Pan-Pan Jiang, Richard Cave, Lauren Harrel, Jordan R. Green

Although personalized automatic speech recognition (ASR) models have recently been designed to recognize even severely impaired speech, model performance may degrade over time for persons with degenerating speech.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Assessing ASR Model Quality on Disordered Speech using BERTScore

no code implementations • 21 Sep 2022 • Jimmy Tobin, Qisheng Li, Subhashini Venugopalan, Katie Seaver, Richard Cave, Katrin Tomanek

BERTScore was found to be more correlated with human assessment of error type and assessment.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2