Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Karl Ni"'
Publikováno v:
Applications of Machine Learning 2021.
Visual search and similarity can aid an e-commerce platform by providing appropriate recommendations where semantic labeling and associated metadata does not always exist. In this work, we detail the specifics of our system that powers visually simil
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::154a38a2d1f0bb8b895715830f6b0bad
https://doi.org/10.1117/12.2594924
https://doi.org/10.1117/12.2594924
Publikováno v:
Applications of Machine Learning 2021.
The performance of recommendation systems is highly dependent on candidate matching techniques for scoping users’ information needs. Existing candidate matching methods are based on text embedding and collaborative filtering, which base similarity
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8b184f8f4798f0606046487f5b788031
https://doi.org/10.1117/12.2595087
https://doi.org/10.1117/12.2595087
Publikováno v:
INTERSPEECH
We propose an algorithm to denoise speakers from a single microphone in the presence of non-stationary and dynamic noise. Our approach is inspired by the recent success of neural network models separating speakers from other speakers and singers from
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::537b6a8ba6cd5852998e5f9c1e01a8d9
http://arxiv.org/abs/1804.10669
http://arxiv.org/abs/1804.10669
Autor:
Cory Stephenson, M. A. Barrios, Paul Gamble, Chris Bartels, Mahesh Kumar Nandwana, Julien van Hout, J. Hetherly, Horacio Franco, Martin Graciarena, Colleen Richey, Zeb Armstrong, Karl Ni, Allen R. Stauffer, Aaron Lawson
Publikováno v:
INTERSPEECH
This paper introduces the Voices Obscured In Complex Environmental Settings (VOICES) corpus, a freely available dataset under Creative Commons BY 4.0. This dataset will promote speech and signal processing research of speech recorded by far-field mic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f37da0c0f8deb8b0d82030ecbc62cf9b
Publikováno v:
ACSSC
Academic work in identifying writers of handwritten documents has previously focused on clean benchmark datasets: plain white documents with uniform writing instruments. Solutions on this type of data have achieved hit-in-top-10 accuracy rates reachi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6c4b405b3e90f8bd070bfad35ed5349e
https://doi.org/10.1109/acssc.2017.8335714
https://doi.org/10.1109/acssc.2017.8335714
Publikováno v:
SiPS
We propose an algorithm to separate simultaneously speaking persons from each other, the “cocktail party problem”, using a single microphone. Our approach involves a deep recurrent neural networks regression to a vector space that is descriptive
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3b317512766a26d74d00308756c3f0c6
https://doi.org/10.1109/sips.2017.8110005
https://doi.org/10.1109/sips.2017.8110005
Publikováno v:
WACV
Identifying the writer of a handwritten document based on visual features is difficult, as evidenced by the limited number of subject matter experts proficient in forensic document analysis. Automating writer identification would be beneficial for su
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c2913da826ab816caa59074f2b7c4e05
https://doi.org/10.1109/wacv.2017.136
https://doi.org/10.1109/wacv.2017.136
Publikováno v:
ICIP
Image annotation, or prediction of multiple tags for an image, is a challenging task. Most current algorithms are based on large sets of handcrafted features. Deep convolutional neural networks have recently outperformed humans in image classificatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4db851320b2b460cd44cf466ea17d41d
https://doi.org/10.1109/icip.2016.7532762
https://doi.org/10.1109/icip.2016.7532762
Autor:
Zeb Armstrong, Paul Gamble, Colleen Richey, Karl Ni, Aaron Lawson, Cory Stephenson, J. Hetherly, Martin Graciarena, M. A. Barrios, Todd Stavish
Publikováno v:
The Journal of the Acoustical Society of America. 143:1869-1869
The speakers in the room (SITR) corpus is a collaboration between Lab41 and SRI International, designed to be a freely available data set for speech and acoustics research in noisy room conditions. The main focus of the corpus is on distant microphon
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f887a8f7ceef2812c8b88ec09636cb8b
https://doi.org/10.1121/1.5036132
https://doi.org/10.1121/1.5036132