CONF icslp2000/IDIAP A neural network for classification with incomplete data: application to robust ASR Morris, Andrew Josifovski, Ljubomir Bourlard, Hervé Cooke, Martin Green, Phil missing features neural networks robust recognition EXTERNAL https://publications.idiap.ch/attachments/reports/2000/morris-2000-icslp.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/morris-rr-00-23 Related documents Proc. ICSLP 2000 Beijing, China If the data vector for input to an automatic classifier is incomplete, the optimal estimate for each class probability must be calculated as the expected value of the classifier output. We identify a form of RBF classifier whose expected outputs can easily be evaluated in terms of the original function parameters. We then describe two ways in which this classifier can be applied to robust automatic speech recognition, depending on whether or not the position of missing data is known REPORT morris-RR-00-23/IDIAP A neural network for classification with incomplete data Morris, Andrew missing features neural networks robust recognition EXTERNAL https://publications.idiap.ch/attachments/reports/2000/rr00-23.pdf PUBLIC Idiap-RR-23-2000 2000 IDIAP If the data vector for input to an automatic classifier is incomplete, the optimal estimate for each class probability must be calculated as the expected value of the classifier output. We identify a form of Radial Basis Function (RBF) classifier whose expected outputs can easily be evaluated in terms of the original function parameters. Two ways are described in which this classifier can be applied to robust automatic speech recognition, depending on whether or not the position of missing data is known.