Matches in SemOpenAlex for { <https://semopenalex.org/work/W1479881569> ?p ?o ?g. }
Showing items 1 to 53 of
53
with 100 items per page.
- W1479881569 abstract "Classification and regression trees (CART) are convenient for low complexity speaker recognition on embedded devices. However, former attempts at using trees performed quite poorly compared to state of the art results with Gaussian Mixture Models (GMM). In this article, we introduce some solutions to improve the efficiency of the tree-based approach. First, we propose to use at the tree construction level different types of information from the GMM used in state of the art techniques. Then, we model the score function within each leaf of the tree by a linear score function. Considering a baseline state of the art system with an equal error rate (EER) of 8.6% on the NIST 2003 evaluation, a previous CART method provides typical EER ranging between 16% and 18% while the proposed improvements decrease the EER to 11.5%, with a computational cost suitable for embedded devices." @default.
- W1479881569 created "2016-06-24" @default.
- W1479881569 creator A5041230403 @default.
- W1479881569 creator A5047641213 @default.
- W1479881569 creator A5084799922 @default.
- W1479881569 date "2005-09-04" @default.
- W1479881569 modified "2023-10-16" @default.
- W1479881569 title "Decision trees with improved efficiency for fast speaker verification" @default.
- W1479881569 cites W1515620500 @default.
- W1479881569 cites W1594031697 @default.
- W1479881569 cites W2041823554 @default.
- W1479881569 cites W2168020168 @default.
- W1479881569 doi "https://doi.org/10.21437/interspeech.2005-660" @default.
- W1479881569 hasPublicationYear "2005" @default.
- W1479881569 type Work @default.
- W1479881569 sameAs 1479881569 @default.
- W1479881569 citedByCount "1" @default.
- W1479881569 crossrefType "proceedings-article" @default.
- W1479881569 hasAuthorship W1479881569A5041230403 @default.
- W1479881569 hasAuthorship W1479881569A5047641213 @default.
- W1479881569 hasAuthorship W1479881569A5084799922 @default.
- W1479881569 hasBestOaLocation W14798815692 @default.
- W1479881569 hasConcept C133892786 @default.
- W1479881569 hasConcept C154945302 @default.
- W1479881569 hasConcept C28490314 @default.
- W1479881569 hasConcept C2982762665 @default.
- W1479881569 hasConcept C41008148 @default.
- W1479881569 hasConcept C84525736 @default.
- W1479881569 hasConceptScore W1479881569C133892786 @default.
- W1479881569 hasConceptScore W1479881569C154945302 @default.
- W1479881569 hasConceptScore W1479881569C28490314 @default.
- W1479881569 hasConceptScore W1479881569C2982762665 @default.
- W1479881569 hasConceptScore W1479881569C41008148 @default.
- W1479881569 hasConceptScore W1479881569C84525736 @default.
- W1479881569 hasLocation W14798815691 @default.
- W1479881569 hasLocation W14798815692 @default.
- W1479881569 hasLocation W14798815693 @default.
- W1479881569 hasOpenAccess W1479881569 @default.
- W1479881569 hasPrimaryLocation W14798815691 @default.
- W1479881569 hasRelatedWork W1994867670 @default.
- W1479881569 hasRelatedWork W2064050250 @default.
- W1479881569 hasRelatedWork W2260330803 @default.
- W1479881569 hasRelatedWork W2368779261 @default.
- W1479881569 hasRelatedWork W2381020483 @default.
- W1479881569 hasRelatedWork W2738707637 @default.
- W1479881569 hasRelatedWork W2746471976 @default.
- W1479881569 hasRelatedWork W2794438528 @default.
- W1479881569 hasRelatedWork W2893763841 @default.
- W1479881569 hasRelatedWork W3107474891 @default.
- W1479881569 isParatext "false" @default.
- W1479881569 isRetracted "false" @default.
- W1479881569 magId "1479881569" @default.
- W1479881569 workType "article" @default.