Y Shahar - Journal of Experimental & Theoretical Artificial …, 1999 - Taylor & Francis
Temporal interpolation is the task of bridging gaps between time-oriented concepts in a context-sensitive manner. It is a subtask important for solving the temporal-abstraction task …
TA Stephenson, H Bourlard, S Bengio… - … on Spoken Language …, 2000 - infoscience.epfl.ch
Current technology for automatic speech recognition (ASR) uses hidden Markov models (HMMs) that recognize spoken speech using the acoustic signal. However, no use is made …
This dissertation describes a reasoning framework for knowledge-based systems, specific to the task of abstracting higher-level, interval-based concepts from time-stamped data, but …
In this paper, we show a new approach for reasoning about time and probability that combines a formal declarative language with a graph representation of systems of random …
Z Qin, CR Shelton - IEEE Transactions on Image Processing, 2017 - ieeexplore.ieee.org
We propose a novel approach toward event detection in real-world continuous video sequences. The method: 1) is able to model arbitrary-order non-Markovian dependences in …
V Lytvynenko, O Naumov, M Voronenko… - … “Intellectual Systems of …, 2020 - Springer
In this paper, we propose a methodology for using dynamic Bayesian networks (DBN) in the tasks of assessing the success of an investment project. The methods of constructing DBN …
This paper describes the application of Bayesian networks to automatic speech recognition (ASR). Bayesian networks enable the construction of probabilistic models in which an …
Many real world applications depend on modeling the temporal dynamics of streams of diverse events, many of which are rare. We introduce a novel model class, Conjoint …