Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Oguz H. Elibol"'
Autor:
Ting Gong, Tyler Lee, Cory Stephenson, Venkata Renduchintala, Suchismita Padhy, Anthony Ndirango, Gokce Keskin, Oguz H. Elibol
Publikováno v:
IEEE Access, Vol 7, Pp 141627-141632 (2019)
With the success of deep learning in a wide variety of areas, many deep multi-task learning (MTL) models have been proposed claiming improvements in performance obtained by sharing the learned structure across several related tasks. However, the dyna
Externí odkaz:
https://doaj.org/article/d0b7dc367767469291058e22e4b47415
Publikováno v:
IEEE Access, Vol 3, Pp 1477-1479 (2015)
The five senses of sight, sound, smell, touch, and taste define the world for us. Sensing technologies augment these primary sensing capabilities: Mechanical sensors broaden our perception of the world by being sensitive to objects that we cannot ‘
Externí odkaz:
https://doaj.org/article/9cf98649a6934afdaf7aade217e5f47b
Publikováno v:
IEEE Communications Letters. 25:489-493
As the density of cellular networks grows, it becomes exceedingly difficult to provide traditional fiber backhaul access to each cell site. Millimeter wave communication coupled with beamforming can be used to provide high-speed wireless backhaul to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bc5e561e3ea81ec22165b46fb549aef6
https://doi.org/10.1109/lcomm.2020.3029513
https://doi.org/10.1109/lcomm.2020.3029513
Autor:
Oguz H. Elibol, Jasha Droppo
Publikováno v:
Interspeech 2021.
There is a recent trend in machine learning to increase model quality by growing models to sizes previously thought to be unreasonable. Recent work has shown that autoregressive generative models with cross-entropy objective functions exhibit smooth
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::99e60dcafdd99c301a68a9a749b57ce7
https://doi.org/10.21437/interspeech.2021-1644
https://doi.org/10.21437/interspeech.2021-1644
Publikováno v:
Interspeech 2021.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::91d5965c4da9a94bcc08795cb5aa60f9
https://doi.org/10.21437/interspeech.2021-1935
https://doi.org/10.21437/interspeech.2021-1935
Autor:
Oguz H. Elibol, Ting Gong, Suchismita Padhy, Gokce Keskin, Venkata Renduchintala, Tyler Lee, Anthony Ndirango, Cory Stephenson
Publikováno v:
IEEE Access, Vol 7, Pp 141627-141632 (2019)
With the success of deep learning in a wide variety of areas, many deep multi-task learning (MTL) models have been proposed claiming improvements in performance obtained by sharing the learned structure across several related tasks. However, the dyna
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1c88d36cd29a2934375ff9f6ac13171a
https://doi.org/10.1109/access.2019.2943604
https://doi.org/10.1109/access.2019.2943604
By implicitly recognizing a user based on his/her speech input, speaker identification enables many downstream applications, such as personalized system behavior and expedited shopping checkouts. Based on whether the speech content is constrained or
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b0cc126dad041f7b5dbd8030356f510a
Autor:
Drew A. Hall, Madoo Varma, Jonathan S. Daniels, Noureddine Tayebi, David J. Liu, Handong Li, Oguz H. Elibol, Grace M. Credo, Xing Su, Kai Wu
Publikováno v:
ACS Sensors. 3:1773-1781
Clinical diagnostic assays that monitor redox enzyme activity are widely used in small, low-cost readout devices for point-of-care monitoring (e.g., a glucometer); however, monitoring non-redox enzymes in real-time using compact electronic devices re
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0ec2d45dbd43ce35f76a778e2fd99115
https://doi.org/10.1021/acssensors.8b00500
https://doi.org/10.1021/acssensors.8b00500
Publikováno v:
INTERSPEECH
In this work we introduce a semi-supervised approach to the voice conversion problem, in which speech from a source speaker is converted into speech of a target speaker. The proposed method makes use of both parallel and non-parallel utterances from
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6f4b0edef46c55506e84ce76d34b0b37
http://arxiv.org/abs/1910.00067
http://arxiv.org/abs/1910.00067
Publikováno v:
ICASSP
We present a method for converting the voices between a set of speakers. Our method is based on training multiple autoencoder paths, where there is a single speaker-independent encoder and multiple speaker-dependent decoders. The autoencoders are tra
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::51773e2433a99fc51311bb7f550d7693
http://arxiv.org/abs/1905.03864
http://arxiv.org/abs/1905.03864