%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 01:18:45 PM

@INPROCEEDINGS{Keshet_INTERSPEECH_2006,
         author = {Keshet, Joseph and Shalev-Shwartz, Shai and Singer, Yoram and Bengio, Samy and Chazan, Dan},
       projects = {Idiap},
          title = {Discriminative Kernel-Based Phoneme Sequence Recognition},
      booktitle = {The 9th International Conference on Spoken Language Processing (INTERSPEECH)},
           year = {2006},
       location = {Pittsburgh, PA},
       crossref = {keshet:rr06-14},
       abstract = {We describe a new method for phoneme sequence recognition given a 
  speech utterance, which is not based on the HMM. In contrast to HMM-based 
  approaches, our method uses a discriminative kernel-based training procedure in which the
  learning process is tailored to the goal of minimizing the
  Levenshtein distance between the predicted phoneme sequence and the
  correct sequence. The phoneme sequence predictor is devised by mapping the
  speech utterance along with a proposed phoneme sequence to a
  vector-space endowed with an inner-product that is realized by a
  Mercer kernel. Building on large margin techniques for predicting
  whole sequences, we are able to devise a learning algorithm which
  distills to separating the correct phoneme sequence from
  all other sequences.  We describe an iterative algorithm
  for learning the phoneme sequence recognizer and further describe an
  efficient implementation of it.  We present initial
  encouraging experimental results with the TIMIT and compare
  the proposed method to an HMM-based approach.},
            pdf = {https://publications.idiap.ch/attachments/papers/2008/Keshet_INTERSPEECH_2006.pdf}
}



crossreferenced publications: 
@TECHREPORT{keshet:rr06-14,
         author = {Keshet, Joseph and Bengio, Samy and Chazan, Dan and Shalev-Shwartz, Shai and Singer, Yoram},
       projects = {Idiap},
          title = {Discriminative Kernel-Based Phoneme Sequence Recognition},
           type = {Idiap-RR},
         number = {Idiap-RR-14-2006},
           year = {2006},
    institution = {IDIAP},
       abstract = {We describe a new method for phoneme sequence recognition given a speech utterance. In contrast to HMM-based approaches, our method uses a kernel-based discriminative training procedure in which the learning process is tailored to the goal of minimizing the Levenshtein distance between the predicted phoneme sequence and the correct sequence. The phoneme sequence predictor is devised by mapping the speech utterance along with a proposed phoneme sequence to a vector-space endowed with an inner-product that is realized by a Mercer kernel. Building on large margin techniques for predicting whole sequences, we are able to devise a learning algorithm which distills to separating the correct phoneme sequence from all other sequences. We describe an iterative algorithm for learning the phoneme sequence recognizer and further describe an efficient implementation of it. We present initial encouraging experimental results with the TIMIT and compare the proposed method to an HMM-based approach.},
            pdf = {https://publications.idiap.ch/attachments/reports/2006/keshet-idiap-rr-06-14.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2006/keshet-idiap-rr-06-14.ps.gz},
ipdmembership={learning},
}