Matches in SemOpenAlex for { <https://semopenalex.org/work/W2024539680> ?p ?o ?g. }
- W2024539680 endingPage "36" @default.
- W2024539680 startingPage "14" @default.
- W2024539680 abstract "In this article, we studied the objective functions of MMI, MCE, and MPE/MWE for discriminative learning in sequential pattern recognition. We presented an approach that unifies the objective functions of MMI, MCE, and MPE/MWE in a common rational-function form of (25). The exact structure of the rational-function form for each discriminative criterion was derived and studied. While the rational-function form of MMI has been known in the past, we provided the theoretical proof that the similar rational-function form exists for the objective functions of MCE and MPE/MWE. Moreover, we showed that the rational function forms for objective functions of MMI, MCE, and MPE/MWE differ in the constant weighting factors CDT (s1 . . . sR) and these weighting factors depend only on the labeled sequence s1 . . . sR, and are independent of the parameter set - to be optimized. The derived rational-function form for MMI, MCE, and MPE/MWE allows the GT/EBW-based parameter optimization framework to be applied directly in discriminative learning. In the past, lack of the appropriate rational-function form was a difficulty for MCE and MPE/MWE, because without this form, the GT/EBW-based parameter optimization framework cannot be directly applied. Based on the unified rational-function form, in a tutorial style, we derived the GT/EBW-based parameter optimization formulas for both discrete HMMs and CDHMMs in discriminative learning using MMI, MCE, and MPE/MWE criteria. The unifying review provided in this article has been based upon a large number of earlier contributions that have been cited and discussed throughout the article. Here we provide a brief summary of such background work. Extension to large-scale speech recognition tasks was accomplished in the work of [59] and [60]. The dissertation of [47] further improved the MMI criterion to that of MPE/MWE. In a parallel vein, the work of [20] provided an alternative approach to that of [41], with an attempt to more rigorously provide a CDHMM model re-estimation formula that gives positive growth of the MMI objective function. A crucial error of this attempt was corrected in [2] for establishing an existence proof of such positive growth. The main goal of this article is to provide an underlying foundation for MMI, MCE, and MPE/MWE at the objective function level to facilitate the development of new parameter optimization techniques and to incorporate other pattern recognition concepts, e.g., discriminative margins [66], into the current discriminative learning paradigm." @default.
- W2024539680 created "2016-06-24" @default.
- W2024539680 creator A5035017068 @default.
- W2024539680 creator A5048159038 @default.
- W2024539680 creator A5078167951 @default.
- W2024539680 date "2008-09-01" @default.
- W2024539680 modified "2023-10-18" @default.
- W2024539680 title "Discriminative learning in sequential pattern recognition" @default.
- W2024539680 cites W1269046860 @default.
- W2024539680 cites W1538748823 @default.
- W2024539680 cites W1604608981 @default.
- W2024539680 cites W1975953721 @default.
- W2024539680 cites W1979136262 @default.
- W2024539680 cites W1982073070 @default.
- W2024539680 cites W2003123121 @default.
- W2024539680 cites W2006544565 @default.
- W2024539680 cites W2010581677 @default.
- W2024539680 cites W2021700397 @default.
- W2024539680 cites W2022768064 @default.
- W2024539680 cites W2032005922 @default.
- W2024539680 cites W2033565080 @default.
- W2024539680 cites W2063541597 @default.
- W2024539680 cites W2075036386 @default.
- W2024539680 cites W2077574412 @default.
- W2024539680 cites W2097427452 @default.
- W2024539680 cites W2098601596 @default.
- W2024539680 cites W2102804087 @default.
- W2024539680 cites W2106404689 @default.
- W2024539680 cites W2113034831 @default.
- W2024539680 cites W2115439799 @default.
- W2024539680 cites W2115877992 @default.
- W2024539680 cites W2117109565 @default.
- W2024539680 cites W2117489663 @default.
- W2024539680 cites W2124216369 @default.
- W2024539680 cites W2129989249 @default.
- W2024539680 cites W2131702393 @default.
- W2024539680 cites W2133828439 @default.
- W2024539680 cites W2143908786 @default.
- W2024539680 cites W2146574666 @default.
- W2024539680 cites W2156615793 @default.
- W2024539680 cites W2158289097 @default.
- W2024539680 cites W2158339352 @default.
- W2024539680 cites W2158808283 @default.
- W2024539680 cites W2162965424 @default.
- W2024539680 cites W2168283124 @default.
- W2024539680 cites W3149335959 @default.
- W2024539680 cites W4245668478 @default.
- W2024539680 cites W198744843 @default.
- W2024539680 doi "https://doi.org/10.1109/msp.2008.926652" @default.
- W2024539680 hasPublicationYear "2008" @default.
- W2024539680 type Work @default.
- W2024539680 sameAs 2024539680 @default.
- W2024539680 citedByCount "124" @default.
- W2024539680 countsByYear W20245396802012 @default.
- W2024539680 countsByYear W20245396802013 @default.
- W2024539680 countsByYear W20245396802014 @default.
- W2024539680 countsByYear W20245396802015 @default.
- W2024539680 countsByYear W20245396802016 @default.
- W2024539680 countsByYear W20245396802017 @default.
- W2024539680 countsByYear W20245396802018 @default.
- W2024539680 countsByYear W20245396802019 @default.
- W2024539680 countsByYear W20245396802020 @default.
- W2024539680 countsByYear W20245396802021 @default.
- W2024539680 countsByYear W20245396802022 @default.
- W2024539680 countsByYear W20245396802023 @default.
- W2024539680 crossrefType "journal-article" @default.
- W2024539680 hasAuthorship W2024539680A5035017068 @default.
- W2024539680 hasAuthorship W2024539680A5048159038 @default.
- W2024539680 hasAuthorship W2024539680A5078167951 @default.
- W2024539680 hasConcept C119857082 @default.
- W2024539680 hasConcept C153180895 @default.
- W2024539680 hasConcept C154945302 @default.
- W2024539680 hasConcept C28490314 @default.
- W2024539680 hasConcept C41008148 @default.
- W2024539680 hasConcept C97931131 @default.
- W2024539680 hasConceptScore W2024539680C119857082 @default.
- W2024539680 hasConceptScore W2024539680C153180895 @default.
- W2024539680 hasConceptScore W2024539680C154945302 @default.
- W2024539680 hasConceptScore W2024539680C28490314 @default.
- W2024539680 hasConceptScore W2024539680C41008148 @default.
- W2024539680 hasConceptScore W2024539680C97931131 @default.
- W2024539680 hasIssue "5" @default.
- W2024539680 hasLocation W20245396801 @default.
- W2024539680 hasOpenAccess W2024539680 @default.
- W2024539680 hasPrimaryLocation W20245396801 @default.
- W2024539680 hasRelatedWork W1652783584 @default.
- W2024539680 hasRelatedWork W1990254706 @default.
- W2024539680 hasRelatedWork W2024160000 @default.
- W2024539680 hasRelatedWork W2026121273 @default.
- W2024539680 hasRelatedWork W2404514746 @default.
- W2024539680 hasRelatedWork W2490266937 @default.
- W2024539680 hasRelatedWork W2743258233 @default.
- W2024539680 hasRelatedWork W2773500201 @default.
- W2024539680 hasRelatedWork W2998168123 @default.
- W2024539680 hasRelatedWork W4287995534 @default.
- W2024539680 hasVolume "25" @default.
- W2024539680 isParatext "false" @default.
- W2024539680 isRetracted "false" @default.