Matches in SemOpenAlex for { <https://semopenalex.org/work/W2018466475> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2018466475 endingPage "30" @default.
- W2018466475 startingPage "21" @default.
- W2018466475 abstract "This paper presents three different methods for developing multilingual phone models for flexible speech recognition tasks. The main goal of our investigations is to find multilingual speech units that work equally well in many languages. With such a universal set it is possible to build speech recognition systems for a variety of languages. One advantage of this approach is that acoustic–phonetic parameters in a HMM-based speech recognition system can then be shared. The multilingual approach starts with the phone sets of six languages, a total of 232 language-dependent and context-independent phone models. Then, we develop three different methods to map the language-dependent models to a multilingual phone set. The first method is a direct mapping to the phone set of the International Phonetic Association (IPA). In the second approach we apply an automatic clustering algorithm for the phone models. The third method exploits the similarities of single mixture components of the language-dependent models. Like the first method the language-specific models are mapped to the IPA inventory. In the second step an agglomerative clustering is performed on the density level to find regions of similarity between the phone models of different languages. The experiments carried out with the SpeechDat(M) database, show that the third method yields almost the same recognition rate as language-dependent models. However, using this method we achieve a huge reduction of the number of densities in the multilingual system." @default.
- W2018466475 created "2016-06-24" @default.
- W2018466475 creator A5044903955 @default.
- W2018466475 date "2001-08-01" @default.
- W2018466475 modified "2023-10-16" @default.
- W2018466475 title "Multilingual phone models for vocabulary-independent speech recognition tasks" @default.
- W2018466475 cites W137286837 @default.
- W2018466475 cites W148334237 @default.
- W2018466475 cites W1512513334 @default.
- W2018466475 cites W154262204 @default.
- W2018466475 cites W185189022 @default.
- W2018466475 cites W185215740 @default.
- W2018466475 cites W1936316808 @default.
- W2018466475 cites W2019116789 @default.
- W2018466475 cites W2102836199 @default.
- W2018466475 cites W2110403070 @default.
- W2018466475 cites W2132534451 @default.
- W2018466475 cites W2167771929 @default.
- W2018466475 cites W2587033535 @default.
- W2018466475 cites W4243964575 @default.
- W2018466475 cites W73572011 @default.
- W2018466475 doi "https://doi.org/10.1016/s0167-6393(00)00093-5" @default.
- W2018466475 hasPublicationYear "2001" @default.
- W2018466475 type Work @default.
- W2018466475 sameAs 2018466475 @default.
- W2018466475 citedByCount "50" @default.
- W2018466475 countsByYear W20184664752012 @default.
- W2018466475 countsByYear W20184664752013 @default.
- W2018466475 countsByYear W20184664752014 @default.
- W2018466475 countsByYear W20184664752015 @default.
- W2018466475 countsByYear W20184664752016 @default.
- W2018466475 countsByYear W20184664752017 @default.
- W2018466475 countsByYear W20184664752019 @default.
- W2018466475 countsByYear W20184664752021 @default.
- W2018466475 countsByYear W20184664752023 @default.
- W2018466475 crossrefType "journal-article" @default.
- W2018466475 hasAuthorship W2018466475A5044903955 @default.
- W2018466475 hasConcept C103278499 @default.
- W2018466475 hasConcept C115961682 @default.
- W2018466475 hasConcept C137293760 @default.
- W2018466475 hasConcept C138885662 @default.
- W2018466475 hasConcept C151730666 @default.
- W2018466475 hasConcept C154945302 @default.
- W2018466475 hasConcept C177264268 @default.
- W2018466475 hasConcept C199360897 @default.
- W2018466475 hasConcept C204321447 @default.
- W2018466475 hasConcept C23224414 @default.
- W2018466475 hasConcept C2777601683 @default.
- W2018466475 hasConcept C2778707766 @default.
- W2018466475 hasConcept C2779343474 @default.
- W2018466475 hasConcept C28490314 @default.
- W2018466475 hasConcept C41008148 @default.
- W2018466475 hasConcept C41895202 @default.
- W2018466475 hasConcept C61328038 @default.
- W2018466475 hasConcept C73555534 @default.
- W2018466475 hasConcept C86803240 @default.
- W2018466475 hasConceptScore W2018466475C103278499 @default.
- W2018466475 hasConceptScore W2018466475C115961682 @default.
- W2018466475 hasConceptScore W2018466475C137293760 @default.
- W2018466475 hasConceptScore W2018466475C138885662 @default.
- W2018466475 hasConceptScore W2018466475C151730666 @default.
- W2018466475 hasConceptScore W2018466475C154945302 @default.
- W2018466475 hasConceptScore W2018466475C177264268 @default.
- W2018466475 hasConceptScore W2018466475C199360897 @default.
- W2018466475 hasConceptScore W2018466475C204321447 @default.
- W2018466475 hasConceptScore W2018466475C23224414 @default.
- W2018466475 hasConceptScore W2018466475C2777601683 @default.
- W2018466475 hasConceptScore W2018466475C2778707766 @default.
- W2018466475 hasConceptScore W2018466475C2779343474 @default.
- W2018466475 hasConceptScore W2018466475C28490314 @default.
- W2018466475 hasConceptScore W2018466475C41008148 @default.
- W2018466475 hasConceptScore W2018466475C41895202 @default.
- W2018466475 hasConceptScore W2018466475C61328038 @default.
- W2018466475 hasConceptScore W2018466475C73555534 @default.
- W2018466475 hasConceptScore W2018466475C86803240 @default.
- W2018466475 hasIssue "1-2" @default.
- W2018466475 hasLocation W20184664751 @default.
- W2018466475 hasOpenAccess W2018466475 @default.
- W2018466475 hasPrimaryLocation W20184664751 @default.
- W2018466475 hasRelatedWork W2012156628 @default.
- W2018466475 hasRelatedWork W2029924358 @default.
- W2018466475 hasRelatedWork W2038107365 @default.
- W2018466475 hasRelatedWork W2102687237 @default.
- W2018466475 hasRelatedWork W2131226854 @default.
- W2018466475 hasRelatedWork W2143620265 @default.
- W2018466475 hasRelatedWork W2159208002 @default.
- W2018466475 hasRelatedWork W2162248568 @default.
- W2018466475 hasRelatedWork W2167118415 @default.
- W2018466475 hasRelatedWork W2911335828 @default.
- W2018466475 hasVolume "35" @default.
- W2018466475 isParatext "false" @default.
- W2018466475 isRetracted "false" @default.
- W2018466475 magId "2018466475" @default.
- W2018466475 workType "article" @default.