Personalizing ASR for Dysarthric and Accented Speech with Limited Data

Automatic speech recognition (ASR) systems have dramatically improved over the last few years. ASR systems are most often trained from 'typical' speech, which means that underrepresented groups don't experience the same level of improvement. In this paper, we present and evaluate fine...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2019-07
Hauptverfasser:	Shor, Joel, Dotan Emanuel, Lang, Oran, Omry Tuval, Brenner, Michael, Cattiau, Julie, Vieira, Fernando, McNally, Maeve, Charbonneau, Taylor, Nollstadt, Melissa, Hassidim, Avinatan, Matias, Yossi
Format:	Artikel
Sprache:	eng
Schlagworte:	Amyotrophic lateral sclerosis Automatic speech recognition Computer Science - Computation and Language Computer Science - Learning Computer Science - Sound Speech disorders
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!