Show simple item record

dc.contributor.authorNogueiras Rodríguez, Albino
dc.contributor.authorMariño Acebal, José Bernardo
dc.contributor.authorMonte Moreno, Enrique
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2012-03-27T17:00:22Z
dc.date.available2012-03-27T17:00:22Z
dc.date.created1998
dc.date.issued1998
dc.identifier.citationNogueiras, A.; Mariño, J.; Monte, E. An adaptive gradient-search based algorithm for discriminative training of hmm's. A: 5th International Conference on spoken language processing (ICSLP'98). "ICSLP'98 Proceedings". Sidney: Robert H. Mannel and Jordi Robert-Ribes, 1998, p. 2979-2982.
dc.identifier.isbn1 876346 17 5
dc.identifier.urihttp://hdl.handle.net/2117/15675
dc.description.abstractAlthough having revealed to be a very powerful tool in acoustic modelling, discriminative training presents a major drawback: the lack of a formulation guaranteeing convergence in no matter which initial conditions, such as the Baum-Welch algorithm in maximum likelihood training. For this reason, a gradient descent search is usually used in this kind of problem. Unfortunately, standard gradient descent algorithms rely heavily on the election of the learning rates. This dependence is specially cumbersome because it represents that, at each run of the discriminative training procedure, a search should be carried out over the parameters ruling the algorithm. In this paper we describe an adaptive procedure for determining the optimal value of the step size at each iteration. While the calculus and memory overhead of the algorithm is negligible, results show less dependence on the initial learning rate than standard gradient descent and, using the same idea in order to apply self-scaling, it clearly outperforms it.
dc.format.extent4 p.
dc.language.isoeng
dc.publisherRobert H. Mannel and Jordi Robert-Ribes
dc.subjectÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Llenguatge natural
dc.subject.lcshNatural language processing (Computer science)
dc.titleAn adaptive gradient-search based algorithm for discriminative training of hmm's
dc.typeConference lecture
dc.subject.lemacProcessament en llenguatge natural (Informàtica)
dc.contributor.groupUniversitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://nlp.lsi.upc.edu/papers/nogueiras98.pdf
dc.rights.accessRestricted access - publisher's policy
drac.iddocument2376889
dc.description.versionPostprint (published version)
upcommons.citation.authorNogueiras, A.; Mariño, J.; Monte, E.
upcommons.citation.contributor5th International Conference on spoken language processing (ICSLP'98)
upcommons.citation.pubplaceSidney
upcommons.citation.publishedtrue
upcommons.citation.publicationNameICSLP'98 Proceedings
upcommons.citation.startingPage2979
upcommons.citation.endingPage2982


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

All rights reserved. This work is protected by the corresponding intellectual and industrial property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public communication or transformation of this work are prohibited without permission of the copyright holder