Zobrazeno 1 - 10
of 50
pro vyhledávání: '"Umut Ozertem"'
Autor:
Ziad Al Bawab, Noha Alon, Ranjitha Gurunath Kulkarni, Umut Ozertem, Imed Zitouni, Ahmed El Kholy, Shuangyu Chang
Publikováno v:
ICASSP
Automatic speech recognition systems can benefit from cues in user voice such as hyperarticulation. Traditional approaches typically attempt to define and detect an absolute state of hyperarticulation, which is very difficult, especially on short voi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2688fc209e7504a50b9284bb88ef8966
https://doi.org/10.1109/icassp.2017.7953105
https://doi.org/10.1109/icassp.2017.7953105
Publikováno v:
WWW
Web search via voice is becoming increasingly popular, taking advantage of recent advances in automatic speech recognition. Speech recognition systems are trained using audio transcripts, which can be generated by a paid annotator listening to some a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d43f3c17be535935e5e3925ff153ec26
https://doi.org/10.1145/2872427.2882994
https://doi.org/10.1145/2872427.2882994
Autor:
Haibo He, Umut Ozertem, Ding Wang, Yoonsuck Choe, Ling Shao, Ali A. Minai, Brijesh Verma, Jochen J. Steil, Nitesh V. Chawla, Andries P. Engelbrecht, Jaya deva, Lyle N. Long, Feiping Nie, Barak A. Pearlmutter, Huanhuan Chen, Jennie Si
“Happy New Year!” At the beginning of 2016, I would like to take this opportunity to wish everyone a very happy, healthy, and prosperous new year! It is my great honor and privilege to serve as the Editor-in-Chief (EiC) of the IEEE TRANSACTIONS O
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9e2bba7a03156bbc59c7c161ca949893
https://pub.uni-bielefeld.de/record/2907683
https://pub.uni-bielefeld.de/record/2907683
Autor:
Umut Ozertem, Deniz Erdogmus
Publikováno v:
IEEE Transactions on Signal Processing. 57:2041-2049
Time warping finds use in many fields of time series analysis, and it has been effectively implemented in many different application areas. Rather than focusing on a particular application area we approach the general problem definition, and employ p
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f983ac84a0b6272c98ae999a60cb3dc5
https://doi.org/10.1109/tsp.2009.2016268
https://doi.org/10.1109/tsp.2009.2016268
Autor:
Umut Ozertem, Deniz Erdogmus
Publikováno v:
IEEE Signal Processing Letters. 16:18-21
System identification with noisy input-output measurements has been dominantly addressed through the optimization of the mean-squared-error criterion (MSE), especially in adaptive filtering. MSE is known to provide models that approximate the conditi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d5de3c13edad0a4db134252a426a1d09
https://doi.org/10.1109/lsp.2008.2008478
https://doi.org/10.1109/lsp.2008.2008478
Publikováno v:
IEEE Transactions on Neural Networks. 19:1978-1984
The insufficiency of using only second-order statistics and premise of exploiting higher order statistics of the data has been well understood, and more advanced objectives including higher order statistics, especially those stemming from information
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b28f1d466f78bad111e5cc7f29df415c
https://doi.org/10.1109/tnn.2008.2006167
https://doi.org/10.1109/tnn.2008.2006167
Publikováno v:
Pattern Recognition. 41:1924-1938
In recent years there has been a growing interest in clustering methods stemming from the spectral decomposition of the data affinity matrix, which are shown to present good results on a wide variety of situations. However, a complete theoretical und
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::baf00c517d701ba263c0a45b90acce5a
https://doi.org/10.1016/j.patcog.2007.09.009
https://doi.org/10.1016/j.patcog.2007.09.009
Recursive complex BSS via generalized eigendecomposition and application in image rejection for BPSK
Publikováno v:
Signal Processing. 88:1368-1381
Under the assumptions of non-Gaussian, non-stationary, or non-white independent sources, linear blind source separation can be formulated as generalized eigenvalue decomposition. Here we provide an elegant method of doing this on-line, instead of wai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d4c3fc6350b4478a538fe7c9371e5e7
https://doi.org/10.1016/j.sigpro.2007.12.001
https://doi.org/10.1016/j.sigpro.2007.12.001
Autor:
Umut Ozertem, Deniz Erdogmus
Publikováno v:
The Journal of VLSI Signal Processing Systems for Signal, Image, and Video Technology. 49:291-299
We propose the information regularization principle for fusing information from sets of identical sensors observing a target phenomenon. The principle basically proposes an importance-weighting scheme for each sensor measurement based on the mutual i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5ec8466702f9d92d5316ae9b78541a6e
https://doi.org/10.1007/s11265-007-0079-0
https://doi.org/10.1007/s11265-007-0079-0
Publikováno v:
CIKM
Voice interactions are becoming more prevalent as the usage of voice search and intelligent assistants gains more popularity. Users frequently reformulate their requests in hope of getting better results either because the system was unable to recogn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c80a35431c35a995efbf4f9d75d3b734
https://doi.org/10.1145/2806416.2806491
https://doi.org/10.1145/2806416.2806491