%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 11:57:20 AM

@INPROCEEDINGS{aradilla:icassp:2007,
         author = {Aradilla, Guillermo and Vepa, Jithendra and Bourlard, Herv{\'{e}}},
       projects = {Idiap},
          title = {An Acoustic Model Based on Kullback-Leibler Divergence for Posterior Features},
      booktitle = {{IEEE} Int. Conf. on Acoustics, Speech, and Signal Processing ({ICASSP})},
           year = {2007},
           note = {IDIAP-RR 06-60},
       crossref = {aradilla:rr06-60},
       abstract = {This paper investigates the use of features based on posterior probabilities of subword units such as phonemes. These features are typically transformed when used as inputs for a hidden Markov model with mixture of Gaussians as emission distribution (HMM/GMM). In this work, we introduce a novel acoustic model that avoids the Gaussian assumption and directly uses posterior features without any transformation. This model is described by a finite state machine where each state is characterized by a target distribution and the cost function associated to each state is given by the Kullback-Leibler (KL) divergence between its target distribution and the posterior features. Furthermore, hybrid HMM/ANN system can be seen as a particular case of this KL-based model where state target distributions are predefined. A training method is also presented that minimizes the KL-divergence between the state target distributions and the posteriors features.},
            pdf = {https://publications.idiap.ch/attachments/papers/2007/aradilla-icassp-2007.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/papers/2007/aradilla-icassp-2007.ps.gz},
ipdmembership={speech},
}



crossreferenced publications: 
@TECHREPORT{aradilla:rr06-60,
         author = {Aradilla, Guillermo and Vepa, Jithendra and Bourlard, Herv{\'{e}}},
       projects = {Idiap},
          title = {An Acoustic Model Based on Kullback-Leibler Divergence for Posterior Features},
           type = {Idiap-RR},
         number = {Idiap-RR-60-2006},
           year = {2006},
    institution = {IDIAP},
       abstract = {This paper investigates the use of features based on posterior probabilities of subword units such as phonemes. These features are typically transformed when used as inputs for a hidden Markov model with mixture of Gaussians as emission distribution (HMM/GMM). In this work, we introduce a novel acoustic model that avoids the Gaussian assumption and directly uses posterior features without any transformation. This model is described by a finite state machine where each state is characterized by a target distribution and the cost function associated to each state is given by the Kullback-Leibler (KL) divergence between its target distribution and the posterior features. Furthermore, hybrid HMM/ANN system can be seen as a particular case of this KL-based model where state target distributions are predefined. A training method is also presented that minimizes the KL-divergence between the state target distributions and the posteriors features.},
            pdf = {https://publications.idiap.ch/attachments/reports/2006/aradilla-idiap-rr-06-60.pdf},
     postscript = {ftp://ftp.idiap.ch/pub/reports/2006/aradilla-idiap-rr-06-60.ps.gz},
ipdmembership={speech},
}