%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 11:34:04 AM

@ARTICLE{luettin-cviu97,
         author = {Luettin, Juergen and Thacker, Neil A.},
       projects = {Idiap},
          title = {Speechreading using Probabilistic Models},
        journal = {Computer Vision and Image Understanding},
         volume = {65},
         number = {02},
           year = {1997},
      publisher = {Academic Press},
           note = {IDIAP-RR 97-12},
       crossref = {luettin-rr-97-12},
       abstract = {We describe a robust method for locating and tracking lips in gray-level image sequences. Our approach learns patterns of shape variability from a training set which constrains the model during image search to only deform in ways similar to the training examples. Image search is guided by a learned gray-level model which is used to describe the large appearance variability of lips. Such variability might be due to different individuals, illumination, mouth opening, specularity, or visibility of teeth and tongue. Visual speech features are recovered from the tracking results and represent both shape and intensity information. We describe a speechreading (lip-reading) system, where the extracted features are modeled by Gaussian distributions and their temporal dependencies by hidden Markov models. Experimental results are presented for locating lips, tracking lips, and speechreading. The database used consists of a broad variety of speakers and was recorded in a natural environment with no special lighting or lip markers used. For a speaker independent digit recognition task using visual information only, the system achieved and accuracy about equivalent to that of untrained humans.},
ipdinar={1996},
ipdmembership={vision},
}



crossreferenced publications: 
@TECHREPORT{luettin-RR-97-12,
         author = {Luettin, Juergen and Thacker, Neil A.},
       projects = {Idiap},
          title = {Speechreading using Probabilistic Models},
           type = {Idiap-RR},
         number = {Idiap-RR-12-1997},
           year = {1997},
    institution = {IDIAP},
           note = {Published in ``CVIU'', 65(2,',','),
 163-178, 1997},
       abstract = {We describe a robust method for locating and tracking lips in gray-level image sequences. Our approach learns patterns of shape variability from a training set which constrains the model during image search to only deform in ways similar to the training examples. Image search is guided by a learned gray-level model which is used to describe the large appearance variability of lips. Such variability might be due to different individuals, illumination, mouth opening, specularity, or visibility of teeth and tongue. Visual speech features are recovered from the tracking results and represent both shape and intensity information. We describe a speechreading (lip-reading) system, where the extracted features are modeled by Gaussian distributions and their temporal dependencies by hidden Markov models. Experimental results are presented for locating lips, tracking lips, and speechreading. The database used consists of a broad variety of speakers and was recorded in a natural environment with no special lighting or lip markers used. For a speaker independent digit recognition task using visual information only, the system achieved and accuracy about equivalent to that of untrained humans.},
            pdf = {https://publications.idiap.ch/attachments/reports/1997/rr97-12.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/1997/rr97-12.ps.gz},
ipdmembership={vision},
}