%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 01:11:04 PM

@INPROCEEDINGS{icslp2000,
         author = {Morris, Andrew and Josifovski, Ljubomir and Bourlard, Herv{\'{e}} and Cooke, Martin and Green, Phil},
       keywords = {missing features, neural networks, robust recognition},
       projects = {Idiap},
          title = {A neural network for classification with incomplete data: application to robust ASR},
      booktitle = {Proc. ICSLP},
           year = {2000},
        address = {Beijing, China},
       crossref = {morris-rr-00-23},
       abstract = {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},
            pdf = {https://publications.idiap.ch/attachments/reports/2000/morris-2000-icslp.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2000/morris-2000-icslp.ps.gz},
ipdmembership={speech},
}



crossreferenced publications: 
@TECHREPORT{morris-RR-00-23,
         author = {Morris, Andrew},
       keywords = {missing features, neural networks, robust recognition},
       projects = {Idiap},
          title = {A neural network for classification with incomplete data},
           type = {Idiap-RR},
         number = {Idiap-RR-23-2000},
           year = {2000},
    institution = {IDIAP},
       abstract = {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.},
            pdf = {https://publications.idiap.ch/attachments/reports/2000/rr00-23.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2000/rr00-23.ps.gz},
ipdmembership={speech},
}