Personalizing ASR for Dysarthric and Accented Speech with Limited Data

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

INTERSPEECH, pp. 784-788, 2019.

Cited by: 5|Bibtex|Views21|
EI

Abstract:

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 finetuning techniques to improve ASR for users with non-s...More

Code:

Data:

Your rating :
0

 

Tags
Comments