Matches in SemOpenAlex for { <https://semopenalex.org/work/W1676065412> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W1676065412 abstract "The aim of this work is to propose a refinement of the shift-MLLR (shift Maximum Likelihood Linear Regression) adaptation of an acoustics model in the case of limited amount of adaptation data, which can lead to ill-conditioned transformations matrices. We try to suppress the influence of badly estimated transformation parameters utilizing the Artificial Neural Network (ANN), especially Convolutional Neural Network (CNN) with bottleneck layer on the end. The badly estimated shift-MLLR transformation is propagated through an ANN (suitably trained beforehand), and the output of the net is used as the new refined transformation. To train the ANN the well and the badly conditioned shift-MLLR transformations are used as outputs and inputs of ANN, respectively." @default.
- W1676065412 created "2016-06-24" @default.
- W1676065412 creator A5017114383 @default.
- W1676065412 creator A5020627791 @default.
- W1676065412 creator A5042440003 @default.
- W1676065412 creator A5067707474 @default.
- W1676065412 date "2014-01-01" @default.
- W1676065412 modified "2023-10-15" @default.
- W1676065412 title "Convolutional Neural Network for Refinement of Speaker Adaptation Transformation" @default.
- W1676065412 cites W1485424219 @default.
- W1676065412 cites W1536929369 @default.
- W1676065412 cites W1538131130 @default.
- W1676065412 cites W1554663460 @default.
- W1676065412 cites W162588823 @default.
- W1676065412 cites W1968752651 @default.
- W1676065412 cites W197326900 @default.
- W1676065412 cites W2002342963 @default.
- W1676065412 cites W2019042707 @default.
- W1676065412 cites W202531933 @default.
- W1676065412 cites W2152417180 @default.
- W1676065412 cites W2171972033 @default.
- W1676065412 cites W2295000399 @default.
- W1676065412 cites W2309152904 @default.
- W1676065412 cites W2504410676 @default.
- W1676065412 cites W31925794 @default.
- W1676065412 cites W95870201 @default.
- W1676065412 doi "https://doi.org/10.1007/978-3-319-11581-8_20" @default.
- W1676065412 hasPublicationYear "2014" @default.
- W1676065412 type Work @default.
- W1676065412 sameAs 1676065412 @default.
- W1676065412 citedByCount "1" @default.
- W1676065412 countsByYear W16760654122016 @default.
- W1676065412 crossrefType "book-chapter" @default.
- W1676065412 hasAuthorship W1676065412A5017114383 @default.
- W1676065412 hasAuthorship W1676065412A5020627791 @default.
- W1676065412 hasAuthorship W1676065412A5042440003 @default.
- W1676065412 hasAuthorship W1676065412A5067707474 @default.
- W1676065412 hasConcept C104317684 @default.
- W1676065412 hasConcept C11413529 @default.
- W1676065412 hasConcept C120665830 @default.
- W1676065412 hasConcept C121332964 @default.
- W1676065412 hasConcept C139807058 @default.
- W1676065412 hasConcept C149635348 @default.
- W1676065412 hasConcept C153180895 @default.
- W1676065412 hasConcept C154945302 @default.
- W1676065412 hasConcept C185592680 @default.
- W1676065412 hasConcept C204241405 @default.
- W1676065412 hasConcept C2780513914 @default.
- W1676065412 hasConcept C28490314 @default.
- W1676065412 hasConcept C41008148 @default.
- W1676065412 hasConcept C50644808 @default.
- W1676065412 hasConcept C55493867 @default.
- W1676065412 hasConcept C81363708 @default.
- W1676065412 hasConceptScore W1676065412C104317684 @default.
- W1676065412 hasConceptScore W1676065412C11413529 @default.
- W1676065412 hasConceptScore W1676065412C120665830 @default.
- W1676065412 hasConceptScore W1676065412C121332964 @default.
- W1676065412 hasConceptScore W1676065412C139807058 @default.
- W1676065412 hasConceptScore W1676065412C149635348 @default.
- W1676065412 hasConceptScore W1676065412C153180895 @default.
- W1676065412 hasConceptScore W1676065412C154945302 @default.
- W1676065412 hasConceptScore W1676065412C185592680 @default.
- W1676065412 hasConceptScore W1676065412C204241405 @default.
- W1676065412 hasConceptScore W1676065412C2780513914 @default.
- W1676065412 hasConceptScore W1676065412C28490314 @default.
- W1676065412 hasConceptScore W1676065412C41008148 @default.
- W1676065412 hasConceptScore W1676065412C50644808 @default.
- W1676065412 hasConceptScore W1676065412C55493867 @default.
- W1676065412 hasConceptScore W1676065412C81363708 @default.
- W1676065412 hasLocation W16760654121 @default.
- W1676065412 hasOpenAccess W1676065412 @default.
- W1676065412 hasPrimaryLocation W16760654121 @default.
- W1676065412 hasRelatedWork W1891007208 @default.
- W1676065412 hasRelatedWork W1986044677 @default.
- W1676065412 hasRelatedWork W2010925413 @default.
- W1676065412 hasRelatedWork W2013875578 @default.
- W1676065412 hasRelatedWork W2088431855 @default.
- W1676065412 hasRelatedWork W2098115693 @default.
- W1676065412 hasRelatedWork W2147276126 @default.
- W1676065412 hasRelatedWork W2158474701 @default.
- W1676065412 hasRelatedWork W2386460253 @default.
- W1676065412 hasRelatedWork W2397868525 @default.
- W1676065412 hasRelatedWork W2537395343 @default.
- W1676065412 hasRelatedWork W2545631154 @default.
- W1676065412 hasRelatedWork W2588760122 @default.
- W1676065412 hasRelatedWork W2592193412 @default.
- W1676065412 hasRelatedWork W2695252763 @default.
- W1676065412 hasRelatedWork W2724392596 @default.
- W1676065412 hasRelatedWork W2735766064 @default.
- W1676065412 hasRelatedWork W2800423036 @default.
- W1676065412 hasRelatedWork W3003469253 @default.
- W1676065412 hasRelatedWork W3118973577 @default.
- W1676065412 isParatext "false" @default.
- W1676065412 isRetracted "false" @default.
- W1676065412 magId "1676065412" @default.
- W1676065412 workType "book-chapter" @default.