Matches in SemOpenAlex for { <https://semopenalex.org/work/W2037298640> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2037298640 abstract "We propose a method for improving the unconstrained segmentation of speech into phoneme-like units using deep neural networks. The proposed approach is not dependent on acoustic models or forced alignment, but operates using the acoustic features directly. Previous solutions of this type were plagued by the tendency to hypothesise additional incorrect phoneme boundaries near the phoneme transitions. We show that the application of deep neural networks is able to reduce this over-segmentation substantially, and achieve improved segmentation accuracies. Furthermore, we find that generative pre-training offers an additional benefit." @default.
- W2037298640 created "2016-06-24" @default.
- W2037298640 creator A5023332009 @default.
- W2037298640 creator A5030124410 @default.
- W2037298640 creator A5050849172 @default.
- W2037298640 date "2015-01-01" @default.
- W2037298640 modified "2023-10-14" @default.
- W2037298640 title "Unconstrained Speech Segmentation using Deep Neural Networks" @default.
- W2037298640 cites W130754613 @default.
- W2037298640 cites W1606268232 @default.
- W2037298640 cites W1663973292 @default.
- W2037298640 cites W1993882792 @default.
- W2037298640 cites W2072128103 @default.
- W2037298640 cites W2083904075 @default.
- W2037298640 cites W2098363562 @default.
- W2037298640 cites W2114259387 @default.
- W2037298640 cites W2116697043 @default.
- W2037298640 cites W2131026791 @default.
- W2037298640 cites W2134701267 @default.
- W2037298640 cites W2135665758 @default.
- W2037298640 cites W2136922672 @default.
- W2037298640 cites W2138857742 @default.
- W2037298640 cites W2148233665 @default.
- W2037298640 cites W2202505358 @default.
- W2037298640 cites W2204988020 @default.
- W2037298640 cites W2601260342 @default.
- W2037298640 cites W28591292 @default.
- W2037298640 cites W30596880 @default.
- W2037298640 cites W3118608800 @default.
- W2037298640 cites W36113703 @default.
- W2037298640 cites W98894605 @default.
- W2037298640 doi "https://doi.org/10.5220/0005201802480254" @default.
- W2037298640 hasPublicationYear "2015" @default.
- W2037298640 type Work @default.
- W2037298640 sameAs 2037298640 @default.
- W2037298640 citedByCount "2" @default.
- W2037298640 countsByYear W20372986402019 @default.
- W2037298640 crossrefType "proceedings-article" @default.
- W2037298640 hasAuthorship W2037298640A5023332009 @default.
- W2037298640 hasAuthorship W2037298640A5030124410 @default.
- W2037298640 hasAuthorship W2037298640A5050849172 @default.
- W2037298640 hasBestOaLocation W20372986401 @default.
- W2037298640 hasConcept C108583219 @default.
- W2037298640 hasConcept C153180895 @default.
- W2037298640 hasConcept C154945302 @default.
- W2037298640 hasConcept C28490314 @default.
- W2037298640 hasConcept C2984842247 @default.
- W2037298640 hasConcept C41008148 @default.
- W2037298640 hasConcept C50644808 @default.
- W2037298640 hasConcept C89600930 @default.
- W2037298640 hasConceptScore W2037298640C108583219 @default.
- W2037298640 hasConceptScore W2037298640C153180895 @default.
- W2037298640 hasConceptScore W2037298640C154945302 @default.
- W2037298640 hasConceptScore W2037298640C28490314 @default.
- W2037298640 hasConceptScore W2037298640C2984842247 @default.
- W2037298640 hasConceptScore W2037298640C41008148 @default.
- W2037298640 hasConceptScore W2037298640C50644808 @default.
- W2037298640 hasConceptScore W2037298640C89600930 @default.
- W2037298640 hasLocation W20372986401 @default.
- W2037298640 hasOpenAccess W2037298640 @default.
- W2037298640 hasPrimaryLocation W20372986401 @default.
- W2037298640 hasRelatedWork W2773120646 @default.
- W2037298640 hasRelatedWork W2774265021 @default.
- W2037298640 hasRelatedWork W2948658236 @default.
- W2037298640 hasRelatedWork W2960184797 @default.
- W2037298640 hasRelatedWork W2972093541 @default.
- W2037298640 hasRelatedWork W3082683741 @default.
- W2037298640 hasRelatedWork W3162157813 @default.
- W2037298640 hasRelatedWork W4220855245 @default.
- W2037298640 hasRelatedWork W4285827401 @default.
- W2037298640 hasRelatedWork W4293211451 @default.
- W2037298640 isParatext "false" @default.
- W2037298640 isRetracted "false" @default.
- W2037298640 magId "2037298640" @default.
- W2037298640 workType "article" @default.