Sciweavers

1318 search results - page 160 / 264
» Aggregation-based model reduction of a Hidden Markov Model
Sort
View
ICASSP
2010
IEEE
15 years 2 months ago
Model-based dereverberation in the logmelspec domain for robust distant-talking speech recognition
The REMOS (REverberation MOdeling for Speech recognition) concept for reverberation-robust distant-talking speech recognition, introduced in [1] for melspectral features, is exten...
Armin Sehr, Roland Maas, Walter Kellermann
ICPR
2008
IEEE
15 years 11 months ago
Unsupervised writer style adaptation for handwritten word spotting
We propose a novel approach for writer adaptation in a word spotting task. The method exploits the fact that a semi-continuous hidden Markov model separates the word model paramet...
José A. Rodríguez, Florent Perronnin...
IROS
2008
IEEE
142views Robotics» more  IROS 2008»
15 years 10 months ago
Scaffolding on-line segmentation of full body human motion patterns
Abstract— This paper develops an approach for on-line segmentation of whole body human motion patterns during human motion observation and learning. A Hidden Markov Model is used...
Dana Kulic, Yoshihiko Nakamura
CORR
2000
Springer
129views Education» more  CORR 2000»
15 years 4 months ago
Prosody-Based Automatic Segmentation of Speech into Sentences and Topics
A crucial step in processing speech audio data for information extraction, topic detection, or browsing/playback is to segment the input into sentence and topic units. Speech segm...
Elizabeth Shriberg, Andreas Stolcke, Dilek Z. Hakk...
IJON
2008
105views more  IJON 2008»
15 years 2 months ago
Estimating the number of components in a mixture of multilayer perceptrons
BIC criterion is widely used by the neural-network community for model selection tasks, although its convergence properties are not always theoretically established. In this paper...
Madalina Olteanu, Joseph Rynkiewicz