Asia-Pacific Signal and Information Processing Association (APSIPA) - Deep neural network based acoustic model using speaker-class information for short time utterance

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

Author(s): Hiroshi Seki ; Kazumasa Yamamoto ; Seiichi Nakagawa
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): 1,222 - 1,225
ISBN (Electronic): 978-9-8814-7680-7
DOI: 10.1109/APSIPA.2015.7415467
Regular:

In speech recognition, it is preferable not to hypothesize the details, e.g., specific age and gender, of a target user. However, speaker independence is one of the things that degrades ASR... View More

Advertisement