Asia-Pacific Signal and Information Processing Association (APSIPA) - Deep neural network-based speech recognition with combination of speaker-class models

2015 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

Author(s): Tetsuo Kosaka ; Kazuki Konno ; Masaharu Kato
Publisher: Asia-Pacific Signal and Information Processing Association (APSIPA)
Publication Date: 1 December 2015
Conference Location: Hong Kong, China
Conference Date: 16 December 2015
Page(s): 1,203 - 1,206
ISBN (Electronic): 978-9-8814-7680-7
DOI: 10.1109/APSIPA.2015.7415464
Regular:

This paper proposes a new speech recognition method based on speaker-class (SC) models. In previous studies based on this approach, Gaussian-mixture-model-based hidden Markov models... View More

Advertisement