排序方式: 共有2条查询结果,搜索用时 15 毫秒
1
1.
Béatrice Chevaillier Damien Mandry Jean-Luc Collette Michel Claudon Marie-Agnès Galloy Olivier Pietquin 《Neural Processing Letters》2011,34(1):71-85
In dynamic contrast-enhanced magnetic resonance imaging, segmentation of internal kidney structures like cortex, medulla and
cavities is essential for functional assessment. To avoid fastidious and time-consuming manual segmentation, semi-automatic
methods have been recently developed. Some of them use the differences between temporal contrast evolution in each anatomical
region to perform functional segmentation. We test two methods where pixels are classified according to their time–intensity
evolution. They both require a vector quantization stage with some unsupervised learning algorithm (K-means or Growing Neural Gas with targeting). Three or more classes are thus obtained. In the first case the method is completely
automatic. In the second case, a restricted intervention by an observer is required for merging. As no ground truth is available
for result evaluation, a manual anatomical segmentation is considered as a reference. Some discrepancy criteria like overlap,
extra pixels and similarity index are computed between this segmentation and a functional one. The same criteria are also
evaluated between the reference and another manual segmentation. Results are comparable for the two types of comparisons,
proving that anatomical segmentation can be performed using functional information. 相似文献
2.
Pietquin O. Dutoit T. 《IEEE transactions on audio, speech, and language processing》2006,14(2):589-599
The design of Spoken Dialog Systems cannot be considered as the simple combination of speech processing technologies. Indeed, speech-based interface design has been an expert job for a long time. It necessitates good skills in speech technologies and low-level programming. Moreover, rapid development and reusability of previously designed systems remains uneasy. This makes optimality and objective evaluation of design very difficult. The design process is therefore a cyclic process composed of prototype releases, user satisfaction surveys, bug reports and refinements. It is well known that human intervention for testing is time-consuming and above all very expensive. This is one of the reasons for the recent interest in dialog simulation for evaluation as well as for design automation and optimization. In this paper we expose a probabilistic framework for a realistic simulation of spoken dialogs in which the major components of a dialog system are modeled and parameterized thanks to independent data or expert knowledge. Especially, an Automatic Speech Recognition (ASR) system model and a User Model (UM) have been developed. The ASR model, based on articulatory similarities in language models, provides task-adaptive performance prediction and Confidence Level (CL) distribution estimation. The user model relies on the Bayesian Networks (BN) paradigm and is used both for user behavior modeling and Natural Language Understanding (NLU) modeling. The complete simulation framework has been used to train a reinforcement-learning agent on two different tasks. These experiments helped to point out several potentially problematic dialog scenarios. 相似文献
1