Matches in SemOpenAlex for { <https://semopenalex.org/work/W2040243326> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2040243326 abstract "State-of-the-art phoneme sequence recognition systems are based on hybrid hidden Markov model/artificial neural networks (HMM/ANN) framework. In this framework, the local classifier, ANN, is typically trained using Viterbi expectation-maximization algorithm, which involves two separate steps: phoneme sequence segmentation and training of ANN. In this paper, we propose a CRF based phoneme sequence recognition approach that simultaneously infers the phoneme segmentation and classifies the phoneme sequence. More specifically, the phoneme sequence recognition system consists of a local classifier ANN followed by a conditional random field (CRF) whose parameters are trained jointly, using a cost function that discriminates the true phoneme sequence against all competing sequences. In order to efficiently train such a system we introduce a novel CRF based segmentation using acyclic graph. We study the viability of the proposed approach on TIMIT phoneme recognition task. Our studies show that the proposed approach is capable of achieving performance similar to standard hybrid HMM/ANN and ANN/CRF systems where the ANN is trained with manual segmentation." @default.
- W2040243326 created "2016-06-24" @default.
- W2040243326 creator A5053915453 @default.
- W2040243326 creator A5064459820 @default.
- W2040243326 creator A5064656096 @default.
- W2040243326 date "2014-12-01" @default.
- W2040243326 modified "2023-10-14" @default.
- W2040243326 title "Joint phoneme segmentation inference and classification using CRFs" @default.
- W2040243326 cites W1560013842 @default.
- W2040243326 cites W1634752325 @default.
- W2040243326 cites W169539560 @default.
- W2040243326 cites W1828163288 @default.
- W2040243326 cites W1902568950 @default.
- W2040243326 cites W1981678206 @default.
- W2040243326 cites W1993882792 @default.
- W2040243326 cites W2077804127 @default.
- W2040243326 cites W2107789863 @default.
- W2040243326 cites W2114016253 @default.
- W2040243326 cites W2131342762 @default.
- W2040243326 cites W2133924365 @default.
- W2040243326 cites W2137644731 @default.
- W2040243326 cites W2141778357 @default.
- W2040243326 cites W2142416747 @default.
- W2040243326 cites W2147880316 @default.
- W2040243326 cites W2148099973 @default.
- W2040243326 cites W2158899491 @default.
- W2040243326 cites W2160815625 @default.
- W2040243326 cites W2163605009 @default.
- W2040243326 cites W2394932179 @default.
- W2040243326 cites W2398337534 @default.
- W2040243326 cites W2399086392 @default.
- W2040243326 cites W2963175699 @default.
- W2040243326 cites W3028642772 @default.
- W2040243326 cites W753012316 @default.
- W2040243326 cites W88081813 @default.
- W2040243326 doi "https://doi.org/10.1109/globalsip.2014.7032185" @default.
- W2040243326 hasPublicationYear "2014" @default.
- W2040243326 type Work @default.
- W2040243326 sameAs 2040243326 @default.
- W2040243326 citedByCount "1" @default.
- W2040243326 countsByYear W20402433262016 @default.
- W2040243326 crossrefType "proceedings-article" @default.
- W2040243326 hasAuthorship W2040243326A5053915453 @default.
- W2040243326 hasAuthorship W2040243326A5064459820 @default.
- W2040243326 hasAuthorship W2040243326A5064656096 @default.
- W2040243326 hasBestOaLocation W20402433262 @default.
- W2040243326 hasConcept C152565575 @default.
- W2040243326 hasConcept C153180895 @default.
- W2040243326 hasConcept C154945302 @default.
- W2040243326 hasConcept C23224414 @default.
- W2040243326 hasConcept C2775953691 @default.
- W2040243326 hasConcept C2776214188 @default.
- W2040243326 hasConcept C2778724510 @default.
- W2040243326 hasConcept C28490314 @default.
- W2040243326 hasConcept C41008148 @default.
- W2040243326 hasConcept C50644808 @default.
- W2040243326 hasConcept C60582962 @default.
- W2040243326 hasConcept C89600930 @default.
- W2040243326 hasConcept C95623464 @default.
- W2040243326 hasConceptScore W2040243326C152565575 @default.
- W2040243326 hasConceptScore W2040243326C153180895 @default.
- W2040243326 hasConceptScore W2040243326C154945302 @default.
- W2040243326 hasConceptScore W2040243326C23224414 @default.
- W2040243326 hasConceptScore W2040243326C2775953691 @default.
- W2040243326 hasConceptScore W2040243326C2776214188 @default.
- W2040243326 hasConceptScore W2040243326C2778724510 @default.
- W2040243326 hasConceptScore W2040243326C28490314 @default.
- W2040243326 hasConceptScore W2040243326C41008148 @default.
- W2040243326 hasConceptScore W2040243326C50644808 @default.
- W2040243326 hasConceptScore W2040243326C60582962 @default.
- W2040243326 hasConceptScore W2040243326C89600930 @default.
- W2040243326 hasConceptScore W2040243326C95623464 @default.
- W2040243326 hasLocation W20402433261 @default.
- W2040243326 hasLocation W20402433262 @default.
- W2040243326 hasLocation W20402433263 @default.
- W2040243326 hasOpenAccess W2040243326 @default.
- W2040243326 hasPrimaryLocation W20402433261 @default.
- W2040243326 hasRelatedWork W2040243326 @default.
- W2040243326 hasRelatedWork W2087221270 @default.
- W2040243326 hasRelatedWork W2100982643 @default.
- W2040243326 hasRelatedWork W2122922410 @default.
- W2040243326 hasRelatedWork W2148632119 @default.
- W2040243326 hasRelatedWork W2150455364 @default.
- W2040243326 hasRelatedWork W2166866311 @default.
- W2040243326 hasRelatedWork W2248934801 @default.
- W2040243326 hasRelatedWork W2533715784 @default.
- W2040243326 hasRelatedWork W2950161128 @default.
- W2040243326 isParatext "false" @default.
- W2040243326 isRetracted "false" @default.
- W2040243326 magId "2040243326" @default.
- W2040243326 workType "article" @default.