Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Vishal Thanvantri Vasudevan"'
Autor:
Vishal Thanvantri Vasudevan, Kellen Gillespie, Ioannis C. Konstantakopoulos, Abhinav Sethy, Xingzhi Guo
Publikováno v:
ICASSP
User interactions with personal assistants like Alexa, Google Home and Siri are typically initiated by a wake term or wakeword. Several personal assistants feature "follow-up" modes that allow users to make additional interactions without the need of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3e3246aebd5963b21bb25638d997a9ec
http://arxiv.org/abs/2010.01949
http://arxiv.org/abs/2010.01949
Autor:
Srividhya Swaminathan, Srinidhi Sridharan, Sri Karlapati, Swathika Rengasamy, Vishal Thanvantri Vasudevan
Publikováno v:
CSI Transactions on ICT. 4:165-171
Computer vision can be deemed as an emerging field which processes real world images in order to display a variety of numerical information about them. To improve the quality of the lifestyle that the visually impaired possess, we propose an assistiv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d1be1bb4058090bf75d85cc3bcb1ce0a
https://doi.org/10.1007/s40012-016-0111-2
https://doi.org/10.1007/s40012-016-0111-2
Publikováno v:
ICASSP
In this work we focus on confidence modeling for neural network based text classification and sequence to sequence models in the context of Natural Language Understanding (NLU) tasks. For most applications, the confidence of a neural network model in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::32609568bc45288ffccc545fa075c03b
https://doi.org/10.1109/icassp.2019.8683359
https://doi.org/10.1109/icassp.2019.8683359