Asia-Pacific Signal and Information Processing Association (APSIPA) - A discriminative training method incorporating pronunciation variations for dysarthric automatic speech recognition

2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

Author(s): Woo Kyeong Seong ; Nam Kyun Kim ; Hun Kyu Ha ; Hong Kook Kim
Publisher: Asia-Pacific Signal and Information Processing Association (APSIPA)
Publication Date: 1 December 2016
Conference Location: Jeju, South Korea
Conference Date: 13 December 2016
Page(s): 1 - 5
ISBN (Electronic): 978-9-8814-7682-1
DOI: 10.1109/APSIPA.2016.7820840
Regular:

While dysarthric speech recognition can be a convenient interface for dysarthric speakers, it is hard to collect enough speech data to overcome the underestimation problem of acoustic models. In... View More

Advertisement