文献
J-GLOBAL ID:202002284007591682
整理番号:20A0813712
オンラインエンドツーエンド音声認識のための適応ダウンサンプリング符号化の学習【JST・京大機械翻訳】
Learning Adaptive Downsampling Encoding for Online End-to-End Speech Recognition
著者 (5件):
Na Rui
(National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China,Hefei,Anhui,China)
,
Hou Junfeng
(National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China,Hefei,Anhui,China)
,
Guo Wu
(National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China,Hefei,Anhui,China)
,
Song Yan
(National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China,Hefei,Anhui,China)
,
Dai Lirong
(National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China,Hefei,Anhui,China)
資料名:
IEEE Conference Proceedings
(IEEE Conference Proceedings)
巻:
2019
号:
APSIPA ASC
ページ:
850-854
発行年:
2019年
JST資料番号:
W2441A
資料種別:
会議録 (C)
記事区分:
原著論文
発行国:
アメリカ合衆国 (USA)
言語:
英語 (EN)