Matches in SemOpenAlex for { <https://semopenalex.org/work/W2016076298> ?p ?o ?g. }
- W2016076298 abstract "In this work, we propose a deep bottleneck feature architecture that is able to leverage data from multiple languages. We also show that tonal features are helpful for non-tonal languages. Evaluations are performed on a low-resource conversational telephone speech transcription task in Bengali, while additional data for DBNF training is provided in Assamese, Pashto, Tagalog, Turkish, and Vietnamese. We obtain relative reductions of up to 17.3% and 9.4% WER over mono-lingual GMMs and DBNFs, respectively." @default.
- W2016076298 created "2016-06-24" @default.
- W2016076298 creator A5001160212 @default.
- W2016076298 creator A5007526409 @default.
- W2016076298 creator A5037112305 @default.
- W2016076298 creator A5065183855 @default.
- W2016076298 creator A5069183549 @default.
- W2016076298 date "2014-05-01" @default.
- W2016076298 modified "2023-09-25" @default.
- W2016076298 title "Multilingual shifting deep bottleneck features for low-resource ASR" @default.
- W2016076298 cites W1501286448 @default.
- W2016076298 cites W1970088388 @default.
- W2016076298 cites W1970890968 @default.
- W2016076298 cites W1978660892 @default.
- W2016076298 cites W1994606281 @default.
- W2016076298 cites W2012897754 @default.
- W2016076298 cites W2033436836 @default.
- W2016076298 cites W2072349636 @default.
- W2016076298 cites W2087395764 @default.
- W2016076298 cites W2107553890 @default.
- W2016076298 cites W2112920470 @default.
- W2016076298 cites W2117671523 @default.
- W2016076298 cites W2120209245 @default.
- W2016076298 cites W2123237149 @default.
- W2016076298 cites W2129070077 @default.
- W2016076298 cites W2134756243 @default.
- W2016076298 cites W2139737683 @default.
- W2016076298 cites W2145094598 @default.
- W2016076298 cites W2394526247 @default.
- W2016076298 cites W319941341 @default.
- W2016076298 doi "https://doi.org/10.1109/icassp.2014.6854676" @default.
- W2016076298 hasPublicationYear "2014" @default.
- W2016076298 type Work @default.
- W2016076298 sameAs 2016076298 @default.
- W2016076298 citedByCount "17" @default.
- W2016076298 countsByYear W20160762982014 @default.
- W2016076298 countsByYear W20160762982015 @default.
- W2016076298 countsByYear W20160762982016 @default.
- W2016076298 countsByYear W20160762982017 @default.
- W2016076298 countsByYear W20160762982018 @default.
- W2016076298 countsByYear W20160762982019 @default.
- W2016076298 countsByYear W20160762982020 @default.
- W2016076298 countsByYear W20160762982021 @default.
- W2016076298 crossrefType "proceedings-article" @default.
- W2016076298 hasAuthorship W2016076298A5001160212 @default.
- W2016076298 hasAuthorship W2016076298A5007526409 @default.
- W2016076298 hasAuthorship W2016076298A5037112305 @default.
- W2016076298 hasAuthorship W2016076298A5065183855 @default.
- W2016076298 hasAuthorship W2016076298A5069183549 @default.
- W2016076298 hasConcept C103621254 @default.
- W2016076298 hasConcept C108583219 @default.
- W2016076298 hasConcept C138885662 @default.
- W2016076298 hasConcept C149635348 @default.
- W2016076298 hasConcept C153083717 @default.
- W2016076298 hasConcept C154945302 @default.
- W2016076298 hasConcept C19235068 @default.
- W2016076298 hasConcept C204321447 @default.
- W2016076298 hasConcept C2777834912 @default.
- W2016076298 hasConcept C2779388314 @default.
- W2016076298 hasConcept C2780513914 @default.
- W2016076298 hasConcept C28490314 @default.
- W2016076298 hasConcept C41008148 @default.
- W2016076298 hasConcept C41895202 @default.
- W2016076298 hasConceptScore W2016076298C103621254 @default.
- W2016076298 hasConceptScore W2016076298C108583219 @default.
- W2016076298 hasConceptScore W2016076298C138885662 @default.
- W2016076298 hasConceptScore W2016076298C149635348 @default.
- W2016076298 hasConceptScore W2016076298C153083717 @default.
- W2016076298 hasConceptScore W2016076298C154945302 @default.
- W2016076298 hasConceptScore W2016076298C19235068 @default.
- W2016076298 hasConceptScore W2016076298C204321447 @default.
- W2016076298 hasConceptScore W2016076298C2777834912 @default.
- W2016076298 hasConceptScore W2016076298C2779388314 @default.
- W2016076298 hasConceptScore W2016076298C2780513914 @default.
- W2016076298 hasConceptScore W2016076298C28490314 @default.
- W2016076298 hasConceptScore W2016076298C41008148 @default.
- W2016076298 hasConceptScore W2016076298C41895202 @default.
- W2016076298 hasLocation W20160762981 @default.
- W2016076298 hasOpenAccess W2016076298 @default.
- W2016076298 hasPrimaryLocation W20160762981 @default.
- W2016076298 hasRelatedWork W1501286448 @default.
- W2016076298 hasRelatedWork W1524956127 @default.
- W2016076298 hasRelatedWork W1549006430 @default.
- W2016076298 hasRelatedWork W1585767454 @default.
- W2016076298 hasRelatedWork W1970088388 @default.
- W2016076298 hasRelatedWork W1970890968 @default.
- W2016076298 hasRelatedWork W1975550806 @default.
- W2016076298 hasRelatedWork W2012897754 @default.
- W2016076298 hasRelatedWork W2021680342 @default.
- W2016076298 hasRelatedWork W2127643134 @default.
- W2016076298 hasRelatedWork W2171723947 @default.
- W2016076298 hasRelatedWork W2548715307 @default.
- W2016076298 hasRelatedWork W2591335418 @default.
- W2016076298 hasRelatedWork W2914026563 @default.
- W2016076298 hasRelatedWork W3010133132 @default.
- W2016076298 hasRelatedWork W3029166220 @default.
- W2016076298 hasRelatedWork W3081482757 @default.
- W2016076298 hasRelatedWork W3094261897 @default.
- W2016076298 hasRelatedWork W3153610483 @default.
- W2016076298 hasRelatedWork W3204314484 @default.