Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Walter Andrews"'
Autor:
Mihai Surdeanu, John Hungerford, Yee Seng Chan, Jessica MacBride, Benjamin Gyori, Andrew Zupon, Zheng Tang, Haoling Qiu, Bonan Min, Yan Zverev, Caitlin Hilverman, Max Thomas, Walter Andrews, Keith Alcock, Zeyu Zhang, Michael Reynolds, Steven Bethard, Rebecca Sharp, Egoitz Laparra
Publikováno v:
Proceedings of the Second Workshop on Bridging Human--Computer Interaction and Natural Language Processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::61798b2a7a417a04e61e29827a5993c8
https://doi.org/10.18653/v1/2022.hcinlp-1.1
https://doi.org/10.18653/v1/2022.hcinlp-1.1
Publikováno v:
WACV
Deep Convolutional Neural Networks (CNN) enforces supervised information only at the output layer, and hidden layers are trained by back propagating the prediction error from the output layer without explicit supervision. We propose a supervised feat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4ad2c753eaf0867a7354c9819a55161c
https://doi.org/10.1109/wacv.2017.30
https://doi.org/10.1109/wacv.2017.30
Publikováno v:
BMVC
We conduct an in-depth exploration of different strategies for doing event detection in videos using convolutional neural networks (CNNs) trained for image classification. We study different ways of performing spatial and temporal pooling, feature no
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::901e3944e29d6c14ea6d49553d3d3072
https://doi.org/10.5244/c.29.60
https://doi.org/10.5244/c.29.60
Autor:
Walter Andrews, Ryan Leary
Publikováno v:
INTERSPEECH
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8b9d0248eb14449f98e33d1ae957745a
https://doi.org/10.21437/interspeech.2014-14
https://doi.org/10.21437/interspeech.2014-14
Publikováno v:
ICASSP (4)
Recent studies show that phonetic sequences from multiple languages can provide effective features for speaker recognition. So far, only pronunciation dynamics in the time dimension, i.e., n-gram modeling on each of the phone sequences, have been exa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::438bf26796e4ea4b997762ba723a9f22
https://doi.org/10.1109/icassp.2003.1202764
https://doi.org/10.1109/icassp.2003.1202764
Publikováno v:
ICASSP (4)
Recent work in phonetic speaker recognition has shown that modeling phone sequences using n-grams is a viable and effective approach to speaker recognition, primarily aiming at capturing speaker-dependent pronunciation and also word usage. The paper
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::95b4b023951072eaed417ad774f0a4f8
https://doi.org/10.1109/icassp.2003.1202763
https://doi.org/10.1109/icassp.2003.1202763
Autor:
Ernesto P, Molmenti, Robert H, Squires, David, Nagata, Jay S, Roden, Hebe, Molmenti, Carlos G, Fasola, Claude, Prestidge, Lisa, D'Amico, Donna, Casey, Edmund Q, Sanchez, Robert M, Goldstein, Marlon F, Levy, Margareta, Benser, Wanda, McPhail, Walter, Andrews, John A, Andersen, Goran B, Klintmalm
Publikováno v:
Pediatric transplantation. 7(2)
The most common hepatic complications of cystic fibrosis (CF) are steatosis, fibrosis, biliary cirrhosis, atretic gallbladder, cholelithiasis, and sclerosing cholangitis. Cholestatic liver disease is a slow progressive disorder, but will stabilize fo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=pmid________::2c09c828c698a2d79305ddfdd4314331
https://pubmed.ncbi.nlm.nih.gov/12654048
https://pubmed.ncbi.nlm.nih.gov/12654048
Publikováno v:
1997 IEEE Workshop on Speech Coding for Telecommunications Proceedings. Back to Basics: Attacking Fundamental Problems in Speech Coding.
Speech coders such as those based on multiband excitation (MBE) and STC models depend on having available an accurate representation of a discrete set of significant spectral amplitudes. Normal linear predictive (LP) spectrum representations model ad
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f98e9fb5caaf971880fb6caa82272def
https://doi.org/10.1109/scft.1997.623872
https://doi.org/10.1109/scft.1997.623872
Autor:
Keith A. Teague, Walter Andrews
Publikováno v:
Conference Record of the Thirty-First Asilomar Conference on Signals, Systems and Computers (Cat. No.97CB36136).
Low rate speech coders based on MBE or STC models require an accurate representation of a discrete set of significant spectral amplitudes for proper performance. Although compact and easy to code, classical linear predictive spectrum representations
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2b815f6a3d331ca564c7c2fa16f5b3fc
https://doi.org/10.1109/acssc.1997.679070
https://doi.org/10.1109/acssc.1997.679070
Autor:
Walter Andrews, Keith A. Teague
Publikováno v:
Conference Record of the Thirty-Fourth Asilomar Conference on Signals, Systems and Computers (Cat. No.00CH37154).
Federal Standard 1016 CELP is a widely adopted standard for speech coding at 4.8 kbps. In this paper we address the issue of improving the existing standard using techniques maintaining compatibility and interoperability. Two techniques are discussed
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::64b366e82fb4456541bc61d3aba4019b
https://doi.org/10.1109/acssc.2000.911231
https://doi.org/10.1109/acssc.2000.911231