Zobrazeno 1 - 10
of 13
pro vyhledávání: '"U. Bodenhausen"'
Autor:
U. Bodenhausen
Publikováno v:
ELIV-MarketPlace 2022 ISBN: 9783181024058
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ee1c5a62be2e95d0d878047924ff6731
https://doi.org/10.51202/9783181024058-265
https://doi.org/10.51202/9783181024058-265
Autor:
U. Bodenhausen
Publikováno v:
ELIV 2021
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8adcd533147b047262d4f5d48eef211f
https://doi.org/10.51202/9783181023846-151
https://doi.org/10.51202/9783181023846-151
Kniha
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
U. Bodenhausen, Alex Waibel
Publikováno v:
ICNN
Highly structured artificial neural networks can be optimized in many ways, and must be optimized for optimal performance. A highly structured approach is the multistate time delay neural network (MSTDNN) which uses shifted input windows and allows t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7bcf9b8370ae306b680c8ec0c69e6315
https://doi.org/10.1109/icnn.1993.298800
https://doi.org/10.1109/icnn.1993.298800
Autor:
U. Bodenhausen, S. Manke
Publikováno v:
ICASSP (2)
Shows how the multi-state time delay neural network (MS-TDNN), which is already used successfully in continuous speech recognition tasks, can be applied both to online single character and cursive (continuous) handwriting recognition. The MS-TDNN int
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f3ff80bf4fc3c49e9b4c2818de811344
Autor:
U. Bodenhausen, H. Hild
Publikováno v:
ICASSP
The successful application of speech recognition systems to new domains greatly depends on the tuning of the architecture to the new task, especially if the amount of training data is small. For example, the application of multi-layer perceptrons (ML
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e34907d25a38ff5426fb838235978e93
https://publikationen.bibliothek.kit.edu/280495
https://publikationen.bibliothek.kit.edu/280495
Autor:
U. Bodenhausen, S. Manke
Publikováno v:
ICANN ’93 ISBN: 9783540198390
Highly structured neural networks like the Time-Delay Neural Network (TDNN) can achieve very high recognition accuracies in real world applications like on-line handwritten character and speech recognition systems. Achieving the best possible perform
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0b4395d9db4c92df77e239d86bc5a03f
https://doi.org/10.1007/978-1-4471-2063-6_283
https://doi.org/10.1007/978-1-4471-2063-6_283
Autor:
U. Bodenhausen, S. Manke
Publikováno v:
ICASSP (1)
The authors applied an automatic structure optimization (ASO) algorithm to the optimization of multistate time-delay neural networks (MSTDNNs), an extension of the TDNN. These networks allow the recognition of sequences of ordered events that have to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::251bc098a282ef5ba97e32e9163b0c9c
https://doi.org/10.1109/icassp.1993.319196
https://doi.org/10.1109/icassp.1993.319196
Autor:
U. Bodenhausen, Alex Waibel
Publikováno v:
ICASSP
Results are presented that suggest that it is possible to learn the architecture of neural networks for speech recognition systems. The Tempo 2 algorithm is proposed. It is a training algorithm for neural networks that trains the temporal parameters
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::181936fcc71f7978ebb926f8af53130a
https://doi.org/10.1109/icassp.1991.150292
https://doi.org/10.1109/icassp.1991.150292