FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2100768664> ?p ?o ?g. }

• W2100768664 endingPage "49" @default.
• W2100768664 startingPage "40" @default.
• W2100768664 abstract "We investigate the problem of acoustic modeling in which prior language-specific knowledge and transcribed data are unavailable. We present an unsupervised model that simultaneously segments the speech, discovers a proper set of sub-word units (e.g., phones) and learns a Hidden Markov Model (HMM) for each induced acoustic unit. Our approach is formulated as a Dirichlet process mixture model in which each mixture is an HMM that represents a sub-word unit. We apply our model to the TIMIT corpus, and the results demonstrate that our model discovers sub-word units that are highly correlated with English phones and also produces better segmentation than the state-of-the-art unsupervised baseline. We test the quality of the learned acoustic models on a spoken term detection task. Compared to the baselines, our model improves the relative precision of top hits by at least 22.1% and outperforms a language-mismatched acoustic model." @default.
• W2100768664 created "2016-06-24" @default.
• W2100768664 creator A5039081803 @default.
• W2100768664 creator A5047426349 @default.
• W2100768664 date "2012-07-08" @default.
• W2100768664 modified "2023-09-29" @default.
• W2100768664 title "A Nonparametric Bayesian Approach to Acoustic Model Discovery" @default.
• W2100768664 cites W1957665339 @default.
• W2100768664 cites W1990005915 @default.
• W2100768664 cites W2026858810 @default.
• W2100768664 cites W2045656233 @default.
• W2100768664 cites W2077804127 @default.
• W2100768664 cites W2080972498 @default.
• W2100768664 cites W2083904075 @default.
• W2100768664 cites W2099415988 @default.
• W2100768664 cites W2111732304 @default.
• W2100768664 cites W2117041980 @default.
• W2100768664 cites W2120636621 @default.
• W2100768664 cites W2121997342 @default.
• W2100768664 cites W2126203737 @default.
• W2100768664 cites W2126377586 @default.
• W2100768664 cites W2148154194 @default.
• W2100768664 cites W2154093685 @default.
• W2100768664 cites W2171752983 @default.
• W2100768664 cites W2401464865 @default.
• W2100768664 cites W2403642609 @default.
• W2100768664 cites W3104490327 @default.
• W2100768664 cites W3127686677 @default.
• W2100768664 cites W53570656 @default.
• W2100768664 hasPublicationYear "2012" @default.
• W2100768664 type Work @default.
• W2100768664 sameAs 2100768664 @default.
• W2100768664 citedByCount "127" @default.
• W2100768664 countsByYear W21007686642012 @default.
• W2100768664 countsByYear W21007686642013 @default.
• W2100768664 countsByYear W21007686642014 @default.
• W2100768664 countsByYear W21007686642015 @default.
• W2100768664 countsByYear W21007686642016 @default.
• W2100768664 countsByYear W21007686642017 @default.
• W2100768664 countsByYear W21007686642018 @default.
• W2100768664 countsByYear W21007686642019 @default.
• W2100768664 countsByYear W21007686642020 @default.
• W2100768664 countsByYear W21007686642021 @default.
• W2100768664 crossrefType "proceedings-article" @default.
• W2100768664 hasAuthorship W2100768664A5039081803 @default.
• W2100768664 hasAuthorship W2100768664A5047426349 @default.
• W2100768664 hasConcept C107673813 @default.
• W2100768664 hasConcept C137293760 @default.
• W2100768664 hasConcept C141318989 @default.
• W2100768664 hasConcept C153180895 @default.
• W2100768664 hasConcept C154945302 @default.
• W2100768664 hasConcept C155635449 @default.
• W2100768664 hasConcept C162324750 @default.
• W2100768664 hasConcept C171686336 @default.
• W2100768664 hasConcept C177264268 @default.
• W2100768664 hasConcept C187736073 @default.
• W2100768664 hasConcept C199360897 @default.
• W2100768664 hasConcept C204321447 @default.
• W2100768664 hasConcept C23224414 @default.
• W2100768664 hasConcept C2524010 @default.
• W2100768664 hasConcept C2778724510 @default.
• W2100768664 hasConcept C2780451532 @default.
• W2100768664 hasConcept C28490314 @default.
• W2100768664 hasConcept C33923547 @default.
• W2100768664 hasConcept C41008148 @default.
• W2100768664 hasConcept C500882744 @default.
• W2100768664 hasConcept C61224824 @default.
• W2100768664 hasConcept C61328038 @default.
• W2100768664 hasConcept C89600930 @default.
• W2100768664 hasConcept C90805587 @default.
• W2100768664 hasConceptScore W2100768664C107673813 @default.
• W2100768664 hasConceptScore W2100768664C137293760 @default.
• W2100768664 hasConceptScore W2100768664C141318989 @default.
• W2100768664 hasConceptScore W2100768664C153180895 @default.
• W2100768664 hasConceptScore W2100768664C154945302 @default.
• W2100768664 hasConceptScore W2100768664C155635449 @default.
• W2100768664 hasConceptScore W2100768664C162324750 @default.
• W2100768664 hasConceptScore W2100768664C171686336 @default.
• W2100768664 hasConceptScore W2100768664C177264268 @default.
• W2100768664 hasConceptScore W2100768664C187736073 @default.
• W2100768664 hasConceptScore W2100768664C199360897 @default.
• W2100768664 hasConceptScore W2100768664C204321447 @default.
• W2100768664 hasConceptScore W2100768664C23224414 @default.
• W2100768664 hasConceptScore W2100768664C2524010 @default.
• W2100768664 hasConceptScore W2100768664C2778724510 @default.
• W2100768664 hasConceptScore W2100768664C2780451532 @default.
• W2100768664 hasConceptScore W2100768664C28490314 @default.
• W2100768664 hasConceptScore W2100768664C33923547 @default.
• W2100768664 hasConceptScore W2100768664C41008148 @default.
• W2100768664 hasConceptScore W2100768664C500882744 @default.
• W2100768664 hasConceptScore W2100768664C61224824 @default.
• W2100768664 hasConceptScore W2100768664C61328038 @default.
• W2100768664 hasConceptScore W2100768664C89600930 @default.
• W2100768664 hasConceptScore W2100768664C90805587 @default.
• W2100768664 hasLocation W21007686641 @default.
• W2100768664 hasOpenAccess W2100768664 @default.
• W2100768664 hasPrimaryLocation W21007686641 @default.
• W2100768664 hasRelatedWork W1524333225 @default.

• next