Personalizing ASR for Dysarthric and Accented Speech with Limited Data
INTERSPEECH, pp. 784-788, 2019.
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
PPT (Upload PPT)