Matches in SemOpenAlex for { <https://semopenalex.org/work/W2407420912> ?p ?o ?g. }
- W2407420912 abstract "We describe the use of text data scraped from the web to augment language models for Automatic Speech Recognition and Keyword Search for Low Resource Languages. We scrape text from multiple genres including blogs, online news, translated TED talks, and subtitles. Using linearly interpolated language models, we find that blogs and movie subtitles are more relevant for language modeling of conversational telephone speech and obtain large reductions in out-of-vocabulary keywords. Furthermore, we show that the web data can improve Term Error Rate Performance by 3.8% absolute and Maximum Term-Weighted Value in Keyword Search by 0.0076-0.1059 absolute points. Much of the gain comes from the reduction of out-of-vocabulary items." @default.
- W2407420912 created "2016-06-24" @default.
- W2407420912 creator A5024283093 @default.
- W2407420912 creator A5032046290 @default.
- W2407420912 creator A5041419426 @default.
- W2407420912 creator A5045037642 @default.
- W2407420912 creator A5050766679 @default.
- W2407420912 creator A5055138015 @default.
- W2407420912 creator A5068567260 @default.
- W2407420912 creator A5082349516 @default.
- W2407420912 date "2015-09-06" @default.
- W2407420912 modified "2023-10-16" @default.
- W2407420912 title "Improving speech recognition and keyword search for low resource languages using web data" @default.
- W2407420912 cites W1506752962 @default.
- W2407420912 cites W1524333225 @default.
- W2407420912 cites W161909597 @default.
- W2407420912 cites W1631260214 @default.
- W2407420912 cites W1733633583 @default.
- W2407420912 cites W1975550806 @default.
- W2407420912 cites W2005232502 @default.
- W2407420912 cites W2028956843 @default.
- W2407420912 cites W2040070072 @default.
- W2407420912 cites W2042655742 @default.
- W2407420912 cites W2080401855 @default.
- W2407420912 cites W2094971681 @default.
- W2407420912 cites W2096140469 @default.
- W2407420912 cites W2105830342 @default.
- W2407420912 cites W2117257534 @default.
- W2407420912 cites W2121764873 @default.
- W2407420912 cites W2136780519 @default.
- W2407420912 cites W2155388323 @default.
- W2407420912 cites W2164666834 @default.
- W2407420912 cites W2277634955 @default.
- W2407420912 cites W2398775317 @default.
- W2407420912 cites W2759478409 @default.
- W2407420912 cites W626798658 @default.
- W2407420912 cites W630532510 @default.
- W2407420912 doi "https://doi.org/10.21437/interspeech.2015-260" @default.
- W2407420912 hasPublicationYear "2015" @default.
- W2407420912 type Work @default.
- W2407420912 sameAs 2407420912 @default.
- W2407420912 citedByCount "22" @default.
- W2407420912 countsByYear W24074209122015 @default.
- W2407420912 countsByYear W24074209122016 @default.
- W2407420912 countsByYear W24074209122017 @default.
- W2407420912 countsByYear W24074209122018 @default.
- W2407420912 countsByYear W24074209122019 @default.
- W2407420912 countsByYear W24074209122020 @default.
- W2407420912 countsByYear W24074209122021 @default.
- W2407420912 countsByYear W24074209122022 @default.
- W2407420912 crossrefType "proceedings-article" @default.
- W2407420912 hasAuthorship W2407420912A5024283093 @default.
- W2407420912 hasAuthorship W2407420912A5032046290 @default.
- W2407420912 hasAuthorship W2407420912A5041419426 @default.
- W2407420912 hasAuthorship W2407420912A5045037642 @default.
- W2407420912 hasAuthorship W2407420912A5050766679 @default.
- W2407420912 hasAuthorship W2407420912A5055138015 @default.
- W2407420912 hasAuthorship W2407420912A5068567260 @default.
- W2407420912 hasAuthorship W2407420912A5082349516 @default.
- W2407420912 hasBestOaLocation W24074209122 @default.
- W2407420912 hasConcept C121332964 @default.
- W2407420912 hasConcept C137293760 @default.
- W2407420912 hasConcept C138885662 @default.
- W2407420912 hasConcept C154945302 @default.
- W2407420912 hasConcept C204321447 @default.
- W2407420912 hasConcept C206345919 @default.
- W2407420912 hasConcept C23123220 @default.
- W2407420912 hasConcept C2777601683 @default.
- W2407420912 hasConcept C28490314 @default.
- W2407420912 hasConcept C31258907 @default.
- W2407420912 hasConcept C40969351 @default.
- W2407420912 hasConcept C41008148 @default.
- W2407420912 hasConcept C41895202 @default.
- W2407420912 hasConcept C61797465 @default.
- W2407420912 hasConcept C62520636 @default.
- W2407420912 hasConceptScore W2407420912C121332964 @default.
- W2407420912 hasConceptScore W2407420912C137293760 @default.
- W2407420912 hasConceptScore W2407420912C138885662 @default.
- W2407420912 hasConceptScore W2407420912C154945302 @default.
- W2407420912 hasConceptScore W2407420912C204321447 @default.
- W2407420912 hasConceptScore W2407420912C206345919 @default.
- W2407420912 hasConceptScore W2407420912C23123220 @default.
- W2407420912 hasConceptScore W2407420912C2777601683 @default.
- W2407420912 hasConceptScore W2407420912C28490314 @default.
- W2407420912 hasConceptScore W2407420912C31258907 @default.
- W2407420912 hasConceptScore W2407420912C40969351 @default.
- W2407420912 hasConceptScore W2407420912C41008148 @default.
- W2407420912 hasConceptScore W2407420912C41895202 @default.
- W2407420912 hasConceptScore W2407420912C61797465 @default.
- W2407420912 hasConceptScore W2407420912C62520636 @default.
- W2407420912 hasLocation W24074209121 @default.
- W2407420912 hasLocation W24074209122 @default.
- W2407420912 hasOpenAccess W2407420912 @default.
- W2407420912 hasPrimaryLocation W24074209121 @default.
- W2407420912 hasRelatedWork W1607797725 @default.
- W2407420912 hasRelatedWork W1667554445 @default.
- W2407420912 hasRelatedWork W188567224 @default.
- W2407420912 hasRelatedWork W2038770598 @default.
- W2407420912 hasRelatedWork W2101955803 @default.
- W2407420912 hasRelatedWork W2294172805 @default.