Matches in SemOpenAlex for { <https://semopenalex.org/work/W2791647162> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2791647162 abstract "How can we effectively develop speech technology for languages where no transcribed data is available? Many existing approaches use no annotated resources at all, yet it makes sense to leverage information from large annotated corpora in other languages, for example in the form of multilingual bottleneck features (BNFs) obtained from a supervised speech recognition system. In this work, we evaluate the benefits of BNFs for subword modeling (feature extraction) in six unseen languages on a word discrimination task. First we establish a strong unsupervised baseline by combining two existing methods: vocal tract length normalisation (VTLN) and the correspondence autoencoder (cAE). We then show that BNFs trained on a single language already beat this baseline; including up to 10 languages results in additional improvements which cannot be matched by just adding more data from a single language. Finally, we show that the cAE can improve further on the BNFs if high-quality same-word pairs are available." @default.
- W2791647162 created "2018-03-29" @default.
- W2791647162 creator A5042970143 @default.
- W2791647162 creator A5075564798 @default.
- W2791647162 date "2018-09-02" @default.
- W2791647162 modified "2023-09-25" @default.
- W2791647162 title "Multilingual Bottleneck Features for Subword Modeling in Zero-resource Languages" @default.
- W2791647162 cites W1545920196 @default.
- W2791647162 cites W1796128977 @default.
- W2791647162 cites W1967924372 @default.
- W2791647162 cites W2038810952 @default.
- W2791647162 cites W2127982613 @default.
- W2791647162 cites W2291975472 @default.
- W2791647162 cites W2402146185 @default.
- W2791647162 cites W2407151108 @default.
- W2791647162 cites W2511733680 @default.
- W2791647162 cites W2533125211 @default.
- W2791647162 cites W2614542633 @default.
- W2791647162 cites W2785415724 @default.
- W2791647162 cites W319941341 @default.
- W2791647162 doi "https://doi.org/10.21437/interspeech.2018-2334" @default.
- W2791647162 hasPublicationYear "2018" @default.
- W2791647162 type Work @default.
- W2791647162 sameAs 2791647162 @default.
- W2791647162 citedByCount "20" @default.
- W2791647162 countsByYear W27916471622018 @default.
- W2791647162 countsByYear W27916471622019 @default.
- W2791647162 countsByYear W27916471622020 @default.
- W2791647162 countsByYear W27916471622021 @default.
- W2791647162 countsByYear W27916471622022 @default.
- W2791647162 crossrefType "proceedings-article" @default.
- W2791647162 hasAuthorship W2791647162A5042970143 @default.
- W2791647162 hasAuthorship W2791647162A5075564798 @default.
- W2791647162 hasBestOaLocation W27916471622 @default.
- W2791647162 hasConcept C101738243 @default.
- W2791647162 hasConcept C108583219 @default.
- W2791647162 hasConcept C111368507 @default.
- W2791647162 hasConcept C12725497 @default.
- W2791647162 hasConcept C127313418 @default.
- W2791647162 hasConcept C137293760 @default.
- W2791647162 hasConcept C138885662 @default.
- W2791647162 hasConcept C149635348 @default.
- W2791647162 hasConcept C153083717 @default.
- W2791647162 hasConcept C154945302 @default.
- W2791647162 hasConcept C162324750 @default.
- W2791647162 hasConcept C187736073 @default.
- W2791647162 hasConcept C204321447 @default.
- W2791647162 hasConcept C2780451532 @default.
- W2791647162 hasConcept C2780513914 @default.
- W2791647162 hasConcept C28490314 @default.
- W2791647162 hasConcept C41008148 @default.
- W2791647162 hasConcept C41895202 @default.
- W2791647162 hasConcept C90805587 @default.
- W2791647162 hasConceptScore W2791647162C101738243 @default.
- W2791647162 hasConceptScore W2791647162C108583219 @default.
- W2791647162 hasConceptScore W2791647162C111368507 @default.
- W2791647162 hasConceptScore W2791647162C12725497 @default.
- W2791647162 hasConceptScore W2791647162C127313418 @default.
- W2791647162 hasConceptScore W2791647162C137293760 @default.
- W2791647162 hasConceptScore W2791647162C138885662 @default.
- W2791647162 hasConceptScore W2791647162C149635348 @default.
- W2791647162 hasConceptScore W2791647162C153083717 @default.
- W2791647162 hasConceptScore W2791647162C154945302 @default.
- W2791647162 hasConceptScore W2791647162C162324750 @default.
- W2791647162 hasConceptScore W2791647162C187736073 @default.
- W2791647162 hasConceptScore W2791647162C204321447 @default.
- W2791647162 hasConceptScore W2791647162C2780451532 @default.
- W2791647162 hasConceptScore W2791647162C2780513914 @default.
- W2791647162 hasConceptScore W2791647162C28490314 @default.
- W2791647162 hasConceptScore W2791647162C41008148 @default.
- W2791647162 hasConceptScore W2791647162C41895202 @default.
- W2791647162 hasConceptScore W2791647162C90805587 @default.
- W2791647162 hasLocation W27916471621 @default.
- W2791647162 hasLocation W27916471622 @default.
- W2791647162 hasLocation W27916471623 @default.
- W2791647162 hasOpenAccess W2791647162 @default.
- W2791647162 hasPrimaryLocation W27916471621 @default.
- W2791647162 hasRelatedWork W1782560969 @default.
- W2791647162 hasRelatedWork W2035959783 @default.
- W2791647162 hasRelatedWork W2081647779 @default.
- W2791647162 hasRelatedWork W2767433836 @default.
- W2791647162 hasRelatedWork W2883550961 @default.
- W2791647162 hasRelatedWork W3094861110 @default.
- W2791647162 hasRelatedWork W3120762062 @default.
- W2791647162 hasRelatedWork W3185852197 @default.
- W2791647162 hasRelatedWork W4304109176 @default.
- W2791647162 hasRelatedWork W4311725991 @default.
- W2791647162 isParatext "false" @default.
- W2791647162 isRetracted "false" @default.
- W2791647162 magId "2791647162" @default.
- W2791647162 workType "article" @default.