Matches in SemOpenAlex for { <https://semopenalex.org/work/W2018355109> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2018355109 endingPage "2492" @default.
- W2018355109 startingPage "2485" @default.
- W2018355109 abstract "In this paper we present our investigation into improving the performance of our computer-assisted language learning (CALL) system through exploiting the acoustic model and features within the speech recognition framework. First, to alleviate channel distortion, speaker-dependent cepstrum mean normalization (CMN) is adopted and the average correlation coefficient (average CC) between machine and expert scores is improved from 78.00% to 84.14%. Second, heteroscedastic linear discriminant analysis (HLDA) is adopted to enhance the discriminability of the acoustic model, which successfully increases the average CC from 84.14% to 84.62%. Additionally, HLDA causes the scoring accuracy to be more stable at various pronunciation proficiency levels, and thus leads to an increase in the speaker correct-rank rate from 85.59% to 90.99%. Finally, we use maximum a posteriori (MAP) estimation to tune the acoustic model to fit strongly accented test speech. As a result, the average CC is improved from 84.62% to 86.57%. These three novel techniques improve the accuracy of evaluating pronunciation quality." @default.
- W2018355109 created "2016-06-24" @default.
- W2018355109 creator A5018911822 @default.
- W2018355109 creator A5022890229 @default.
- W2018355109 creator A5031150833 @default.
- W2018355109 creator A5064347076 @default.
- W2018355109 creator A5066595006 @default.
- W2018355109 creator A5085211104 @default.
- W2018355109 date "2008-10-01" @default.
- W2018355109 modified "2023-09-25" @default.
- W2018355109 title "Effective Acoustic Modeling for Pronunciation Quality Scoring of Strongly Accented Mandarin Speech" @default.
- W2018355109 cites W1931766939 @default.
- W2018355109 cites W2070133242 @default.
- W2018355109 cites W2080400971 @default.
- W2018355109 cites W2091359957 @default.
- W2018355109 cites W2106554350 @default.
- W2018355109 cites W2139008940 @default.
- W2018355109 cites W2158513796 @default.
- W2018355109 cites W2164810574 @default.
- W2018355109 cites W21911835 @default.
- W2018355109 cites W66698146 @default.
- W2018355109 doi "https://doi.org/10.1093/ietisy/e91-d.10.2485" @default.
- W2018355109 hasPublicationYear "2008" @default.
- W2018355109 type Work @default.
- W2018355109 sameAs 2018355109 @default.
- W2018355109 citedByCount "2" @default.
- W2018355109 countsByYear W20183551092013 @default.
- W2018355109 countsByYear W20183551092017 @default.
- W2018355109 crossrefType "journal-article" @default.
- W2018355109 hasAuthorship W2018355109A5018911822 @default.
- W2018355109 hasAuthorship W2018355109A5022890229 @default.
- W2018355109 hasAuthorship W2018355109A5031150833 @default.
- W2018355109 hasAuthorship W2018355109A5064347076 @default.
- W2018355109 hasAuthorship W2018355109A5066595006 @default.
- W2018355109 hasAuthorship W2018355109A5085211104 @default.
- W2018355109 hasBestOaLocation W20183551091 @default.
- W2018355109 hasConcept C136886441 @default.
- W2018355109 hasConcept C138885662 @default.
- W2018355109 hasConcept C138954614 @default.
- W2018355109 hasConcept C144024400 @default.
- W2018355109 hasConcept C153180895 @default.
- W2018355109 hasConcept C154945302 @default.
- W2018355109 hasConcept C19165224 @default.
- W2018355109 hasConcept C2780844864 @default.
- W2018355109 hasConcept C28490314 @default.
- W2018355109 hasConcept C41008148 @default.
- W2018355109 hasConcept C41895202 @default.
- W2018355109 hasConcept C69738355 @default.
- W2018355109 hasConcept C88485024 @default.
- W2018355109 hasConceptScore W2018355109C136886441 @default.
- W2018355109 hasConceptScore W2018355109C138885662 @default.
- W2018355109 hasConceptScore W2018355109C138954614 @default.
- W2018355109 hasConceptScore W2018355109C144024400 @default.
- W2018355109 hasConceptScore W2018355109C153180895 @default.
- W2018355109 hasConceptScore W2018355109C154945302 @default.
- W2018355109 hasConceptScore W2018355109C19165224 @default.
- W2018355109 hasConceptScore W2018355109C2780844864 @default.
- W2018355109 hasConceptScore W2018355109C28490314 @default.
- W2018355109 hasConceptScore W2018355109C41008148 @default.
- W2018355109 hasConceptScore W2018355109C41895202 @default.
- W2018355109 hasConceptScore W2018355109C69738355 @default.
- W2018355109 hasConceptScore W2018355109C88485024 @default.
- W2018355109 hasIssue "10" @default.
- W2018355109 hasLocation W20183551091 @default.
- W2018355109 hasOpenAccess W2018355109 @default.
- W2018355109 hasPrimaryLocation W20183551091 @default.
- W2018355109 hasRelatedWork W2042455139 @default.
- W2018355109 hasRelatedWork W2171162065 @default.
- W2018355109 hasRelatedWork W2350941553 @default.
- W2018355109 hasRelatedWork W2483947148 @default.
- W2018355109 hasRelatedWork W2545656840 @default.
- W2018355109 hasRelatedWork W2547369883 @default.
- W2018355109 hasRelatedWork W2884370189 @default.
- W2018355109 hasRelatedWork W40124310 @default.
- W2018355109 hasRelatedWork W2185988117 @default.
- W2018355109 hasRelatedWork W2508457823 @default.
- W2018355109 hasVolume "E91-D" @default.
- W2018355109 isParatext "false" @default.
- W2018355109 isRetracted "false" @default.
- W2018355109 magId "2018355109" @default.
- W2018355109 workType "article" @default.