Matches in SemOpenAlex for { <https://semopenalex.org/work/W2319316830> ?p ?o ?g. }
- W2319316830 endingPage "1139" @default.
- W2319316830 startingPage "1129" @default.
- W2319316830 abstract "Short utterance speaker recognition (SUSR) is highly challenging due to the limited enrollment and/or test data. We argue that the difficulty can be largely attributed to the mismatched prior distributions of the speech data used to train the universal background model (UBM) and those for enrollment and test. This paper presents a novel solution that distributes speech signals into a multitude of acoustic subregions that are defined by speech units, and models speakers within the subregions. To avoid data sparsity, a data-driven approach is proposed to cluster speech units into speech unit classes, based on which robust subregion models can be constructed. Further more, we propose a model synthesis approach based on maximum likelihood linear regression (MLLR) to deal with no-data speech unit classes. The experiments were conducted on a publicly available database SUD12. The results demonstrated that on a text-independent speaker recognition task where the test utterances are no longer than 2 seconds and mostly shorter than 0.5 seconds, the proposed subregion modeling offered a 21.51% relative reduction in equal error rate (EER), compared with the standard GMM-UBM baseline. In addition, with the model synthesis approach, the performance can be greatly improved in scenarios where no enrollment data are available for some speech unit classes." @default.
- W2319316830 created "2016-06-24" @default.
- W2319316830 creator A5010082933 @default.
- W2319316830 creator A5046454314 @default.
- W2319316830 creator A5050701255 @default.
- W2319316830 creator A5084318285 @default.
- W2319316830 date "2016-06-01" @default.
- W2319316830 modified "2023-10-17" @default.
- W2319316830 title "Improving Short Utterance Speaker Recognition by Modeling Speech Unit Classes" @default.
- W2319316830 cites W102958777 @default.
- W2319316830 cites W1586405805 @default.
- W2319316830 cites W1985690171 @default.
- W2319316830 cites W1993482042 @default.
- W2319316830 cites W2002342963 @default.
- W2319316830 cites W2033436836 @default.
- W2319316830 cites W2039057510 @default.
- W2319316830 cites W2041823554 @default.
- W2319316830 cites W2064630946 @default.
- W2319316830 cites W2068562110 @default.
- W2319316830 cites W2069883713 @default.
- W2319316830 cites W2069976350 @default.
- W2319316830 cites W2100969003 @default.
- W2319316830 cites W2107638917 @default.
- W2319316830 cites W2119468495 @default.
- W2319316830 cites W2121750345 @default.
- W2319316830 cites W2121812409 @default.
- W2319316830 cites W2125636736 @default.
- W2319316830 cites W2129244720 @default.
- W2319316830 cites W2146871184 @default.
- W2319316830 cites W2150769028 @default.
- W2319316830 cites W2152402526 @default.
- W2319316830 cites W2154278880 @default.
- W2319316830 cites W2166111255 @default.
- W2319316830 cites W4205947740 @default.
- W2319316830 doi "https://doi.org/10.1109/taslp.2016.2544660" @default.
- W2319316830 hasPublicationYear "2016" @default.
- W2319316830 type Work @default.
- W2319316830 sameAs 2319316830 @default.
- W2319316830 citedByCount "39" @default.
- W2319316830 countsByYear W23193168302015 @default.
- W2319316830 countsByYear W23193168302016 @default.
- W2319316830 countsByYear W23193168302017 @default.
- W2319316830 countsByYear W23193168302018 @default.
- W2319316830 countsByYear W23193168302019 @default.
- W2319316830 countsByYear W23193168302020 @default.
- W2319316830 countsByYear W23193168302021 @default.
- W2319316830 countsByYear W23193168302022 @default.
- W2319316830 countsByYear W23193168302023 @default.
- W2319316830 crossrefType "journal-article" @default.
- W2319316830 hasAuthorship W2319316830A5010082933 @default.
- W2319316830 hasAuthorship W2319316830A5046454314 @default.
- W2319316830 hasAuthorship W2319316830A5050701255 @default.
- W2319316830 hasAuthorship W2319316830A5084318285 @default.
- W2319316830 hasConcept C153180895 @default.
- W2319316830 hasConcept C154945302 @default.
- W2319316830 hasConcept C155635449 @default.
- W2319316830 hasConcept C162324750 @default.
- W2319316830 hasConcept C16910744 @default.
- W2319316830 hasConcept C187736073 @default.
- W2319316830 hasConcept C199360897 @default.
- W2319316830 hasConcept C2775852435 @default.
- W2319316830 hasConcept C2780451532 @default.
- W2319316830 hasConcept C28490314 @default.
- W2319316830 hasConcept C40969351 @default.
- W2319316830 hasConcept C41008148 @default.
- W2319316830 hasConcept C61328038 @default.
- W2319316830 hasConceptScore W2319316830C153180895 @default.
- W2319316830 hasConceptScore W2319316830C154945302 @default.
- W2319316830 hasConceptScore W2319316830C155635449 @default.
- W2319316830 hasConceptScore W2319316830C162324750 @default.
- W2319316830 hasConceptScore W2319316830C16910744 @default.
- W2319316830 hasConceptScore W2319316830C187736073 @default.
- W2319316830 hasConceptScore W2319316830C199360897 @default.
- W2319316830 hasConceptScore W2319316830C2775852435 @default.
- W2319316830 hasConceptScore W2319316830C2780451532 @default.
- W2319316830 hasConceptScore W2319316830C28490314 @default.
- W2319316830 hasConceptScore W2319316830C40969351 @default.
- W2319316830 hasConceptScore W2319316830C41008148 @default.
- W2319316830 hasConceptScore W2319316830C61328038 @default.
- W2319316830 hasFunder F4320321001 @default.
- W2319316830 hasIssue "6" @default.
- W2319316830 hasLocation W23193168301 @default.
- W2319316830 hasOpenAccess W2319316830 @default.
- W2319316830 hasPrimaryLocation W23193168301 @default.
- W2319316830 hasRelatedWork W115323076 @default.
- W2319316830 hasRelatedWork W2008308193 @default.
- W2319316830 hasRelatedWork W2080458333 @default.
- W2319316830 hasRelatedWork W2110052520 @default.
- W2319316830 hasRelatedWork W2319316830 @default.
- W2319316830 hasRelatedWork W2399356099 @default.
- W2319316830 hasRelatedWork W2943934118 @default.
- W2319316830 hasRelatedWork W4239447739 @default.
- W2319316830 hasRelatedWork W4293054790 @default.
- W2319316830 hasRelatedWork W4307784074 @default.
- W2319316830 hasVolume "24" @default.
- W2319316830 isParatext "false" @default.
- W2319316830 isRetracted "false" @default.
- W2319316830 magId "2319316830" @default.