%Aigaion2 BibTeX export from Idiap Publications
%Sunday 23 June 2024 06:24:05 AM

@INPROCEEDINGS{pinto:IS:2008,
         author = {Pinto, Joel Praveen and Hermansky, Hynek},
       projects = {Idiap},
          title = {Combining Evidence from a Generative and a Discriminative Model in Phoneme Recognition},
      booktitle = {{P}roceedings of Interspeech},
           year = {2008},
           note = {IDIAP-RR 08-20},
       crossref = {pinto:rr08-20},
       abstract = {We investigate the use of the log-likelihood of the features obtained from a generative Gaussian mixture model, and the posterior probability of phonemes from a discriminative multilayered perceptron in multi-stream combination for recognition of phonemes. Multi-stream combination techniques, namely early integration and late integration are used to combine the evidence from these models. By using multi-stream combination, we obtain a phoneme recognition accuracy of 74\\% on the standard TIMIT database, an absolute improvement of 2.5\\% over the single best stream.},
            pdf = {https://publications.idiap.ch/attachments/papers/2008/pinto-IS-2008.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/papers/2008/pinto-IS-2008.ps.gz},
ipdmembership={speech},
}



crossreferenced publications: 
@TECHREPORT{pinto:rr08-20,
         author = {Pinto, Joel Praveen and Hermansky, Hynek},
       projects = {Idiap},
          title = {Combining Evidence from a Generative and a Discriminative Model in Phoneme Recognition},
           type = {Idiap-RR},
         number = {Idiap-RR-20-2008},
           year = {2008},
    institution = {IDIAP},
           note = {Submitted for publication},
       abstract = {We investigate the use of the log-likelihood of the features obtained from a generative Gaussian mixture model, and the posterior probability of phonemes from a discriminative multilayered perceptron in multi-stream combination for recognition of phonemes. Multi-stream combination techniques, namely early integration and late integration are used to combine the evidence from these models. By using multi-stream combination, we obtain a phoneme recognition accuracy of 74\\% on the standard TIMIT database, an absolute improvement of 2.5\\% over the single best stream.},
            pdf = {https://publications.idiap.ch/attachments/reports/2008/pinto-idiap-rr-08-20.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2008/pinto-idiap-rr-08-20.ps.gz},
ipdmembership={speech},
}