Sciweavers

1532 search results - page 210 / 307
» Tilings Robust to Errors
Sort
View
INTERSPEECH
2010
15 years 1 months ago
Learning a language model from continuous speech
This paper presents a new approach to language model construction, learning a language model not from text, but directly from continuous speech. A phoneme lattice is created using...
Graham Neubig, Masato Mimura, Shinsuke Mori, Tatsu...
INTERSPEECH
2010
15 years 1 months ago
Multimodal speaker diarization using oriented optical flow histograms
Speaker diarization is the task of partitioning an input stream into speaker homogeneous regions, or in other words, to determine "who spoke when." While approaches to t...
Mary Tai Knox, Gerald Friedland
NETWORK
2010
119views more  NETWORK 2010»
15 years 1 months ago
A multiple failure propagation model in GMPLS-based networks
In this article, a new model to simulate different failure propagation scenarios in GMPLS-based networks is proposed. Several types of failures and malfunctions may spread along t...
Eusebi Calle, J. Ripoll, J. Segovia, Pere Vil&agra...
TIP
2010
165views more  TIP 2010»
15 years 1 months ago
Physically Consistent and Efficient Variational Denoising of Image Fluid Flow Estimates
Imaging plays an important role in experimental fluid dynamics. It is equally important both for scientific research and a range of industrial applications. It is known, however, t...
Andrey Vlasenko, Christoph Schnörr
TNN
2010
216views Management» more  TNN 2010»
15 years 1 months ago
Simplifying mixture models through function approximation
Finite mixture model is a powerful tool in many statistical learning problems. In this paper, we propose a general, structure-preserving approach to reduce its model complexity, w...
Kai Zhang, James T. Kwok