Sciweavers

457 search results - page 38 / 92
» Universal background model based speech recognition
Sort
View
CVPR
2007
IEEE
15 years 8 months ago
Partially Occluded Object-Specific Segmentation in View-Based Recognition
We present a novel object-specific segmentation method which can be used in view-based object recognition systems. Previous object segmentation approaches generate inexact results ...
Minsu Cho (Seoul National University), Kyoung Mu L...
ISMIR
2005
Springer
128views Music» more  ISMIR 2005»
15 years 3 months ago
A Hierarchical Approach for Audio Stream Segmentation and Classification
This paper describes a hierarchical approach for fast audio stream segmentation and classification. With this approach, the audio stream is firstly segmented into audio clips by M...
Wei Liang, Shuwu Zhang, Bo Xu
ICASSP
2009
IEEE
15 years 1 months ago
Neural network based language models for highly inflective languages
Speech recognition of inflectional and morphologically rich languages like Czech is currently quite a challenging task, because simple n-gram techniques are unable to capture impo...
Tomas Mikolov, Jirí Kopecký, Lukas B...
IUI
2009
ACM
15 years 6 months ago
Positive effects of redundant descriptions in an interactive semantic speech interface
Spoken language interfaces based on interactive semantic language models [16, 14] allow probabilities for hypothesized words to be conditioned on the semantic interpretation of th...
Lane Schwartz, Luan Nguyen, Andrew Exley, William ...
BXML
2004
14 years 11 months ago
Telephony Interface of the ExtraPlanT Multi-agent Production Planning System
: ExtraPlanT system is a multi-agent production planning system designed for small factories, which needs to react quickly on market changes. To deal with this requirement, ExtraPl...
Petr Becvár, Michal Pechoucek, Lubos Sm&iac...