%Aigaion2 BibTeX export from Idiap Publications
%Thursday 05 December 2024 03:08:56 PM

@INPROCEEDINGS{pinto:icassp-phnrecog:2008,
         author = {Pinto, Joel Praveen and Hermansky, Hynek and Yegnanarayana, B. and Magimai.-Doss, Mathew},
       projects = {Idiap},
          title = {Exploiting Contextual Information for Improved Phoneme Recognition},
      booktitle = {"{IEEE} Int. Conf. on Acoustics, Speech, and Signal Processing ({ICASSP})"},
           year = {2008},
           note = {IDIAP-RR 07-65},
       crossref = {pinto:rr07-65},
       abstract = {In this paper, we investigate the significance of contextual information in a phoneme recognition system using the hidden Markov model - artificial neural network paradigm. Contextual information is probed at the feature level as well as at the output of the multilayerd perceptron. At the feature level, we analyse and compare different methods to model sub-phonemic classes. To exploit the contextual information at the output of the multilayered perceptron, we propose the hierarchical estimation of phoneme posterior probabilities. The best phoneme (excluding silence) recognition accuracy of 73.4\\% on the TIMIT database is comparable to that of the state-of-the-art systems, but more emphasis is on analysis of the contextual information.},
            pdf = {https://publications.idiap.ch/attachments/papers/2008/pinto-icassp-phnrecog-2008.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/papers/2008/pinto-icassp-phnrecog-2008.ps.gz},
ipdmembership={speech},
}



crossreferenced publications: 
@TECHREPORT{pinto:rr07-65,
         author = {Pinto, Joel Praveen and Yegnanarayana, B. and Hermansky, Hynek and Magimai.-Doss, Mathew},
       projects = {Idiap},
          title = {Exploiting Contextual Information for Improved Phoneme Recognition},
           type = {Idiap-RR},
         number = {Idiap-RR-65-2007},
           year = {2007},
    institution = {IDIAP},
       abstract = {In this paper, we investigate the significance of contextual information in a phoneme recognition system using the hidden Markov model - artificial neural network paradigm. Contextual information is probed at the feature level as well as at the output of the multilayerd perceptron. At the feature level, we analyse and compare different methods to model sub-phonemic classes. To exploit the contextual information at the output of the multilayered perceptron, we propose the hierarchical estimation of phoneme posterior probabilities. The best phoneme (excluding silence) recognition accuracy of 73.4\\% on the TIMIT database is comparable to that of the state-of-the-art systems, but more emphasis is on analysis of the contextual information.},
            pdf = {https://publications.idiap.ch/attachments/reports/2007/pinto-idiap-rr-07-65.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2007/pinto-idiap-rr-07-65.ps.gz},
ipdmembership={speech},
}