Sciweavers

104 search results - page 14 / 21
» Learning sound location from a single microphone
Sort
View
MLMI
2005
Springer
14 years 24 days ago
Improving the Performance of Acoustic Event Classification by Selecting and Combining Information Sources Using the Fuzzy Integr
Acoustic events produced in meeting-room-like environments may carry information useful for perceptually aware interfaces. In this paper, we focus on the problem of combining diffe...
Andrey Temko, Dusan Macho, Climent Nadeu
COST
2007
Springer
118views Multimedia» more  COST 2007»
14 years 1 months ago
The Organization of a Neurocomputational Control Model for Articulatory Speech Synthesis
The organization of a computational control model of articulatory speech synthesis is outlined in this paper. The model is based on general principles of neurophysiology and cognit...
Bernd J. Kröger, Anja Lowit, Ralph Schnitker
NIPS
2004
13 years 8 months ago
Joint MRI Bias Removal Using Entropy Minimization Across Images
The correction of bias in magnetic resonance images is an important problem in medical image processing. Most previous approaches have used a maximum likelihood method to increase...
Erik G. Learned-Miller, Parvez Ahammad
NN
2000
Springer
192views Neural Networks» more  NN 2000»
13 years 7 months ago
A new algorithm for learning in piecewise-linear neural networks
Piecewise-linear (PWL) neural networks are widely known for their amenability to digital implementation. This paper presents a new algorithm for learning in PWL networks consistin...
Emad Gad, Amir F. Atiya, Samir I. Shaheen, Ayman E...
ICPR
2006
IEEE
14 years 8 months ago
Phoneme segmentation of speech
In most approaches to speech recognition, the speech signals are segmented using constant-time segmentation, for example into 25 ms blocks. Constant segmentation risks losing info...
Bartosz Ziólko, Suresh Manandhar, Richard C...