%Aigaion2 BibTeX export from Idiap Publications
%Tuesday 03 December 2024 03:41:33 PM

@PHDTHESIS{Luettin-thesis97,
         author = {Luettin, Juergen},
       projects = {Idiap},
          title = {{V}isual {S}peech and {S}peaker {R}ecognition},
           year = {1997},
         school = {University of Sheffield},
       abstract = {This thesis presents a learning based approach to speech recognition and person recognition from image sequences. An appearance based model of the articulators is learned from example images and is used to locate, track, and recover visual speech features. A major difficulty in model based approaches is to develop a scheme which is general enough to account for the large appearance variability of objects but which does not lack in specificity. The method described here decomposes the lip shape and the intensities in the mouth region into weighted sums of basis shapes and basis intensities, respectively, using a Karhunen-Lo{\'{e}}ve expansion. The intensities deform with the shape model to provide shape independent intensity information. This information is used in image search, which is based on a similarity measure between the model and the image. Visual speech features can be recovered from the tracking results and represent shape and intensity information. A speechreading (lip-reading) system is presented which models these features by Gaussian distributions and their temporal dependencies by hidden Markov models. The models are trained using the EM-algorithm and speech recognition is performed based on maximum posterior probability classification. It is shown that, besides speech information, the recovered model parameters also contain person dependent information and a novel method for person recognition is presented which is based on these features. Talking persons are represented by spatio-temporal models which describe the appearance of the articulators and their temporal changes during speech production. Two different topologies for speaker models are described: Gaussian mixture models and hidden Markov models. The proposed methods were evaluated for lip localisation, lip tracking, speech recognition, and speaker recognition on an isolated digit database of 12 subjects, and on a continuous digit database of 37 subjects. The techniques were found to achieve good performance for all tasks listed above. For an isolated digit recognition task, the speechreading system outperformed previously reported systems and performed slightly better than untrained human speechreaders.},
            pdf = {https://publications.idiap.ch/attachments/papers/1997/luettin_thesis.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/papers/vision/luettin_thesis.ps.gz},
ipdmembership={vision},
}