Matches in SemOpenAlex for { <https://semopenalex.org/work/W2020144989> ?p ?o ?g. }
- W2020144989 endingPage "608" @default.
- W2020144989 startingPage "589" @default.
- W2020144989 abstract "Recently, discriminative training (DT) methods have achieved tremendous progress in automatic speech recognition (ASR). In this survey article, all mainstream DT methods in speech recognition are reviewed from both theoretical and practical perspectives. From the theoretical aspect, many effective discriminative learning criteria in ASR are first introduced and then a unifying view is presented to elucidate the relationship among these popular DT criteria originally proposed from different viewpoints. Next, some key optimization methods used to optimize these criteria are summarized and their convergence properties are discussed. Moreover, as some recent advances, a novel discriminative learning framework is introduced as a general scheme to formulate discriminative training of HMMs for ASR, from which a variety of new DT methods can be developed. In addition, some important implementation issues regarding how to conduct DT for large vocabulary ASR are also discussed from a more practical aspect, such as efficient implementation of discriminative training on word graphs and effective optimization of complex DT objective functions in high-dimensionality space, and so on. Finally, this paper is summarized and concluded with some possible future research directions for this area. As a technical survey, all DT techniques and ideas are reviewed and discussed in this paper from high level without involving too much technical detail and experimental result." @default.
- W2020144989 created "2016-06-24" @default.
- W2020144989 creator A5008456610 @default.
- W2020144989 date "2010-10-01" @default.
- W2020144989 modified "2023-10-17" @default.
- W2020144989 title "Discriminative training of HMMs for automatic speech recognition: A survey" @default.
- W2020144989 cites W100756984 @default.
- W2020144989 cites W144014225 @default.
- W2020144989 cites W1538748823 @default.
- W2020144989 cites W1549656520 @default.
- W2020144989 cites W160662550 @default.
- W2020144989 cites W171059195 @default.
- W2020144989 cites W1964903355 @default.
- W2020144989 cites W1975953721 @default.
- W2020144989 cites W1979136262 @default.
- W2020144989 cites W2003123121 @default.
- W2020144989 cites W2027086767 @default.
- W2020144989 cites W2032005922 @default.
- W2020144989 cites W2063541597 @default.
- W2020144989 cites W2077574412 @default.
- W2020144989 cites W2086699924 @default.
- W2020144989 cites W2098601596 @default.
- W2020144989 cites W2102804087 @default.
- W2020144989 cites W2108672476 @default.
- W2020144989 cites W2110467295 @default.
- W2020144989 cites W2111479622 @default.
- W2020144989 cites W2111581792 @default.
- W2020144989 cites W2112182520 @default.
- W2020144989 cites W2116658213 @default.
- W2020144989 cites W2126033156 @default.
- W2020144989 cites W2129989249 @default.
- W2020144989 cites W2130768248 @default.
- W2020144989 cites W2131385129 @default.
- W2020144989 cites W2134659216 @default.
- W2020144989 cites W2136743277 @default.
- W2020144989 cites W2141969549 @default.
- W2020144989 cites W2146744574 @default.
- W2020144989 cites W2150907703 @default.
- W2020144989 cites W2153307830 @default.
- W2020144989 cites W2158289097 @default.
- W2020144989 cites W2158339352 @default.
- W2020144989 cites W2158808283 @default.
- W2020144989 cites W2161877964 @default.
- W2020144989 cites W2162965424 @default.
- W2020144989 cites W2167307239 @default.
- W2020144989 cites W4235499294 @default.
- W2020144989 doi "https://doi.org/10.1016/j.csl.2009.08.002" @default.
- W2020144989 hasPublicationYear "2010" @default.
- W2020144989 type Work @default.
- W2020144989 sameAs 2020144989 @default.
- W2020144989 citedByCount "76" @default.
- W2020144989 countsByYear W20201449892012 @default.
- W2020144989 countsByYear W20201449892013 @default.
- W2020144989 countsByYear W20201449892014 @default.
- W2020144989 countsByYear W20201449892015 @default.
- W2020144989 countsByYear W20201449892016 @default.
- W2020144989 countsByYear W20201449892017 @default.
- W2020144989 countsByYear W20201449892018 @default.
- W2020144989 countsByYear W20201449892019 @default.
- W2020144989 countsByYear W20201449892020 @default.
- W2020144989 countsByYear W20201449892021 @default.
- W2020144989 countsByYear W20201449892022 @default.
- W2020144989 crossrefType "journal-article" @default.
- W2020144989 hasAuthorship W2020144989A5008456610 @default.
- W2020144989 hasConcept C111030470 @default.
- W2020144989 hasConcept C119857082 @default.
- W2020144989 hasConcept C136197465 @default.
- W2020144989 hasConcept C138885662 @default.
- W2020144989 hasConcept C142362112 @default.
- W2020144989 hasConcept C153349607 @default.
- W2020144989 hasConcept C154945302 @default.
- W2020144989 hasConcept C22019652 @default.
- W2020144989 hasConcept C26517878 @default.
- W2020144989 hasConcept C2776035091 @default.
- W2020144989 hasConcept C2777601683 @default.
- W2020144989 hasConcept C28490314 @default.
- W2020144989 hasConcept C38652104 @default.
- W2020144989 hasConcept C41008148 @default.
- W2020144989 hasConcept C41895202 @default.
- W2020144989 hasConcept C50644808 @default.
- W2020144989 hasConcept C97931131 @default.
- W2020144989 hasConceptScore W2020144989C111030470 @default.
- W2020144989 hasConceptScore W2020144989C119857082 @default.
- W2020144989 hasConceptScore W2020144989C136197465 @default.
- W2020144989 hasConceptScore W2020144989C138885662 @default.
- W2020144989 hasConceptScore W2020144989C142362112 @default.
- W2020144989 hasConceptScore W2020144989C153349607 @default.
- W2020144989 hasConceptScore W2020144989C154945302 @default.
- W2020144989 hasConceptScore W2020144989C22019652 @default.
- W2020144989 hasConceptScore W2020144989C26517878 @default.
- W2020144989 hasConceptScore W2020144989C2776035091 @default.
- W2020144989 hasConceptScore W2020144989C2777601683 @default.
- W2020144989 hasConceptScore W2020144989C28490314 @default.
- W2020144989 hasConceptScore W2020144989C38652104 @default.
- W2020144989 hasConceptScore W2020144989C41008148 @default.
- W2020144989 hasConceptScore W2020144989C41895202 @default.
- W2020144989 hasConceptScore W2020144989C50644808 @default.
- W2020144989 hasConceptScore W2020144989C97931131 @default.