Euphonia publications

With your help, we have gathered more than 1 million utterances (1400 hours of data) from more than a thousand speakers. This data has enabled us to refine our speech algorithms to better understand different types of speech. Here is a complete list of all the blog posts and papers we have published related to these research efforts.

Blog posts and announcements

Pie graph showing breakdowns of ethology, and severity, from our data collection program

Research

Personalized ASR Models from a Large and Diverse Disordered Speech Dataset (2021)

Speech impairments affect millions of people, with underlying causes ranging from neurological or genetic conditions to physical impairment, brain damage or hearing loss. Similarly, the resulting speech patterns are diverse, including stuttering, dysarthria, apraxia, etc., and can have a detrimental impact on self-expression, participation in society and access to voice-enabled technologies.

Read more

Recent papers

EMNLP 2021

Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech

Katrin Tomanek, Vicky Zayats, Dirk Padfield, Kara Vaillancourt, Fadi Biadsy

Interspeech 2021

Disordered Speech Data Collection: Lessons Learned at 1 Million Utterances from Project Euphonia

Robert L. MacDonald, Pan-Pan Jiang, Julie Cattiau, Rus Heywood, Richard Cave, Katie Seaver, Marilyn A. Ladewig, Jimmy Tobin, Michael P. Brenner, Philip C. Nelson, Jordan R. Green, Katrin Tomanek

Interspeech 2021

Automatic Speech Recognition of Disordered Speech: Personalized models outperforming human listeners on short phrases

Jordan R. Green, Robert L. MacDonald, Pan-Pan Jiang, Julie Cattiau, Rus Heywood, Richard Cave, Katie Seaver, Marilyn A. Ladewig, Jimmy Tobin, Michael P. Brenner, Philip C. Nelson, Katrin Tomanek

Interspeech 2021

Comparing Supervised Models And Learned Speech Representations For Classifying Intelligibility Of Disordered Speech On Selected Phrases

Subhashini Venugopalan, Joel Shor, Manoj Plakal, Jimmy Tobin, Katrin Tomanek, Jordan R. Green, Michael P. Brenner

Interspeech 2021

A Voice-Activated Switch for Persons with Motor and Speech Impairments: Isolated-Vowel Spotting Using Neural Networks

Shanqing Cai, Lisie Lillianfeld, Katie Seaver, Jordan R. Green, Michael Brenner, Philip Q Nelson, D. Sculley

Interspeech 2019

Personalizing ASR for Dysarthric and Accented Speech with Limited Data

Joel Shor, Dotan Emanuel, Oran Lang, Omry Tuval, Michael Brenner, Julie Cattiau, Fernando Vieira, Maeve McNally, Taylor Charbonneau, Melissa Nollstadt, Avinatan Hassidim, Yossi Matias