Zobrazeno 1 - 10
of 11
pro vyhledávání: '"Yoonhyung Lee"'
There are two types of methods for non-autoregressive text-to-speech models to learn the one-to-many relationship between text and speech effectively. The first one is to use an advanced generative framework such as normalizing flow (NF). The second
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::33f5aa637dbd5bf669da9148731e828c
Autor:
Youan Kwon, Yoonhyung Lee
Publikováno v:
The Journal of Linguistics Science. 98:31-50
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d9aae85bdb9f12e2136b49a2aeda417d
https://doi.org/10.21296/jls.2021.9.98.31
https://doi.org/10.21296/jls.2021.9.98.31
Publikováno v:
INTERSPEECH
In this paper, we propose a novel speech emotion recognition model called Cross Attention Network (CAN) that uses aligned audio and text signals as inputs. It is inspired by the fact that humans recognize speech as a combination of simultaneously pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1b3aadfc6f62d4a5f5cc8983b10d6c54
Towards Dynamically Reconfigurable IoT Camera Virtualization for Video Analytics Edge Cloud Services
Publikováno v:
IEEE Internet Computing. 23:10-17
Video analytics edge computing exploiting IoT cameras has gained high attention. Running such tasks on the network edge is very challenging since video and image processing are bandwidth-hungry and computationally intensive. IoT cameras are heavily d
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::290a2ab6049fd7140589be835b00ddf1
https://doi.org/10.1109/mic.2019.2893872
https://doi.org/10.1109/mic.2019.2893872
Publikováno v:
The Journal of Linguistics Science. 88:251-280
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bf2a69992d12cbc4e7ec6ccfad7422c4
https://doi.org/10.21296/jls.2019.3.88.251
https://doi.org/10.21296/jls.2019.3.88.251
Publikováno v:
ACL
Even though BERT achieves successful performance improvements in various supervised learning tasks, applying BERT for unsupervised tasks still holds a limitation that it requires repetitive inference for computing contextual language representations.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::35790a4be073fda862eb147a8acec818
http://arxiv.org/abs/2004.08097
http://arxiv.org/abs/2004.08097
Publikováno v:
SemEval@NAACL-HLT
This paper describes our system for SemEval-2019 Task 3: EmoContext, which aims to predict the emotion of the third utterance considering two preceding utterances in a dialogue. To address this challenge of predicting the emotion considering its cont
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7ccb148b7769a2ab75e0c27e9fd7fc1a
https://doi.org/10.18653/v1/s19-2043
https://doi.org/10.18653/v1/s19-2043
Publikováno v:
SEC
Video analytics edge computing exploiting IoT cameras has gained high attention. Running such tasks on the network edge is very challenging since video and image processing are both bandwidth-hungry and computationally intensive. Unlike traditional c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7f2f806b51f07f8b922560df4f6e95a5
https://doi.org/10.1109/sec.2018.00017
https://doi.org/10.1109/sec.2018.00017
Publikováno v:
CFI
We explore issues and challenges for application-aware virtualization in edge Internet-of-Things (IoT) clouds. Since a large number of IoT devices reside in network edges, it is necessary for a current edge computing technology to virtualize them not
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e21022bfb13af0956f2c4c7d5118d0fc
https://doi.org/10.1145/3226052.3226059
https://doi.org/10.1145/3226052.3226059
Autor:
Anthony Kanai, Naoki Yoshimura, Takahisa Suzuki, Joonbeom Kwon, Eiichiro Takaoka, Nobutaka Shimizu, Yoonhyung Lee
Publikováno v:
Journal of Urology. 199
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::620408da4d6d5b5d84ca8d0f713c44d0
https://doi.org/10.1016/j.juro.2018.02.330
https://doi.org/10.1016/j.juro.2018.02.330