Matches in SemOpenAlex for { <https://semopenalex.org/work/W2190506272> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2190506272 abstract "Recent studies have been revisiting whole words as the basic modelling unit in speech recognition and query applications, instead of phonetic units. Such whole-word segmental systems rely on a function that maps a variable-length speech segment to a vector in a fixed-dimensional space; the resulting acoustic word embeddings need to allow for accurate discrimination between different word types, directly in the embedding space. We compare several old and new approaches in a word discrimination task. Our best approach uses side information in the form of known word pairs to train a Siamese convolutional neural network (CNN): a pair of tied networks that take two speech segments as input and produce their embeddings, trained with a hinge loss that separates same-word pairs and different-word pairs by some margin. A word classifier CNN performs similarly, but requires much stronger supervision. Both types of CNNs yield large improvements over the best previously published results on the word discrimination task." @default.
- W2190506272 created "2016-06-24" @default.
- W2190506272 creator A5005239198 @default.
- W2190506272 creator A5015602781 @default.
- W2190506272 creator A5040305929 @default.
- W2190506272 date "2016-03-01" @default.
- W2190506272 modified "2023-10-14" @default.
- W2190506272 title "Deep convolutional acoustic word embeddings using word-pair side information" @default.
- W2190506272 cites W1496120315 @default.
- W2190506272 cites W1577418252 @default.
- W2190506272 cites W1967924372 @default.
- W2190506272 cites W2020607164 @default.
- W2190506272 cites W2052697931 @default.
- W2190506272 cites W2057007397 @default.
- W2190506272 cites W2059652594 @default.
- W2190506272 cites W2072054026 @default.
- W2190506272 cites W2097207027 @default.
- W2190506272 cites W2114347655 @default.
- W2190506272 cites W2126203737 @default.
- W2190506272 cites W2138621090 @default.
- W2190506272 cites W2159775472 @default.
- W2190506272 cites W2171590421 @default.
- W2190506272 doi "https://doi.org/10.1109/icassp.2016.7472619" @default.
- W2190506272 hasPublicationYear "2016" @default.
- W2190506272 type Work @default.
- W2190506272 sameAs 2190506272 @default.
- W2190506272 citedByCount "134" @default.
- W2190506272 countsByYear W21905062722016 @default.
- W2190506272 countsByYear W21905062722017 @default.
- W2190506272 countsByYear W21905062722018 @default.
- W2190506272 countsByYear W21905062722019 @default.
- W2190506272 countsByYear W21905062722020 @default.
- W2190506272 countsByYear W21905062722021 @default.
- W2190506272 countsByYear W21905062722022 @default.
- W2190506272 countsByYear W21905062722023 @default.
- W2190506272 crossrefType "proceedings-article" @default.
- W2190506272 hasAuthorship W2190506272A5005239198 @default.
- W2190506272 hasAuthorship W2190506272A5015602781 @default.
- W2190506272 hasAuthorship W2190506272A5040305929 @default.
- W2190506272 hasBestOaLocation W21905062722 @default.
- W2190506272 hasConcept C153180895 @default.
- W2190506272 hasConcept C154945302 @default.
- W2190506272 hasConcept C204321447 @default.
- W2190506272 hasConcept C2524010 @default.
- W2190506272 hasConcept C28490314 @default.
- W2190506272 hasConcept C33923547 @default.
- W2190506272 hasConcept C40969351 @default.
- W2190506272 hasConcept C41008148 @default.
- W2190506272 hasConcept C81363708 @default.
- W2190506272 hasConcept C90805587 @default.
- W2190506272 hasConcept C95623464 @default.
- W2190506272 hasConceptScore W2190506272C153180895 @default.
- W2190506272 hasConceptScore W2190506272C154945302 @default.
- W2190506272 hasConceptScore W2190506272C204321447 @default.
- W2190506272 hasConceptScore W2190506272C2524010 @default.
- W2190506272 hasConceptScore W2190506272C28490314 @default.
- W2190506272 hasConceptScore W2190506272C33923547 @default.
- W2190506272 hasConceptScore W2190506272C40969351 @default.
- W2190506272 hasConceptScore W2190506272C41008148 @default.
- W2190506272 hasConceptScore W2190506272C81363708 @default.
- W2190506272 hasConceptScore W2190506272C90805587 @default.
- W2190506272 hasConceptScore W2190506272C95623464 @default.
- W2190506272 hasLocation W21905062721 @default.
- W2190506272 hasLocation W21905062722 @default.
- W2190506272 hasOpenAccess W2190506272 @default.
- W2190506272 hasPrimaryLocation W21905062721 @default.
- W2190506272 hasRelatedWork W2019914509 @default.
- W2190506272 hasRelatedWork W2175746458 @default.
- W2190506272 hasRelatedWork W2732542196 @default.
- W2190506272 hasRelatedWork W2964383635 @default.
- W2190506272 hasRelatedWork W2995914718 @default.
- W2190506272 hasRelatedWork W3093612317 @default.
- W2190506272 hasRelatedWork W3107474891 @default.
- W2190506272 hasRelatedWork W4225852842 @default.
- W2190506272 hasRelatedWork W4304208073 @default.
- W2190506272 hasRelatedWork W564581980 @default.
- W2190506272 isParatext "false" @default.
- W2190506272 isRetracted "false" @default.
- W2190506272 magId "2190506272" @default.
- W2190506272 workType "article" @default.