Matches in SemOpenAlex for { <https://semopenalex.org/work/W3094871513> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3094871513 abstract "Transformer models have become to state-of-the-art in natural language understanding, their use for language modeling in Automatic Speech Recognition (ASR) is also promising. Albeit Transformer based language models were shown to improve ASR performance, their computational complexity makes their application in real-time systems quite challenging. It has been also shown that the knowledge of such language models can be transferred to traditional n-gram models, suitable for real-time decoding. This paper investigates the adaptation of this transfer approach to morphologically rich languages, and in a real time scenario. We propose a new method for subword-based neural text augmentation with a Transformer language model, which consists in retokenizing the training corpus into subwords, based on a statistical data-driven approach. We demonstrate that ASR performance can be augmented by yet reducing the vocabulary size and alleviating memory consumption." @default.
- W3094871513 created "2020-11-09" @default.
- W3094871513 creator A5014608650 @default.
- W3094871513 creator A5020514527 @default.
- W3094871513 creator A5043901293 @default.
- W3094871513 creator A5075146981 @default.
- W3094871513 date "2020-09-23" @default.
- W3094871513 modified "2023-10-16" @default.
- W3094871513 title "Improving Real-time Recognition of Morphologically Rich Speech with Transformer Language Model" @default.
- W3094871513 cites W1425721496 @default.
- W3094871513 cites W179875071 @default.
- W3094871513 cites W1971415293 @default.
- W3094871513 cites W1979625042 @default.
- W3094871513 cites W2110415041 @default.
- W3094871513 cites W2117621558 @default.
- W3094871513 cites W2121299803 @default.
- W3094871513 cites W2158195707 @default.
- W3094871513 cites W2295078202 @default.
- W3094871513 cites W2402268235 @default.
- W3094871513 cites W2532751415 @default.
- W3094871513 cites W2714176837 @default.
- W3094871513 cites W2888867175 @default.
- W3094871513 cites W2939021222 @default.
- W3094871513 cites W2943845043 @default.
- W3094871513 cites W2962784628 @default.
- W3094871513 cites W2972551035 @default.
- W3094871513 cites W4293569503 @default.
- W3094871513 doi "https://doi.org/10.1109/coginfocom50765.2020.9237817" @default.
- W3094871513 hasPublicationYear "2020" @default.
- W3094871513 type Work @default.
- W3094871513 sameAs 3094871513 @default.
- W3094871513 citedByCount "0" @default.
- W3094871513 crossrefType "proceedings-article" @default.
- W3094871513 hasAuthorship W3094871513A5014608650 @default.
- W3094871513 hasAuthorship W3094871513A5020514527 @default.
- W3094871513 hasAuthorship W3094871513A5043901293 @default.
- W3094871513 hasAuthorship W3094871513A5075146981 @default.
- W3094871513 hasConcept C119599485 @default.
- W3094871513 hasConcept C127413603 @default.
- W3094871513 hasConcept C129353971 @default.
- W3094871513 hasConcept C137293760 @default.
- W3094871513 hasConcept C138885662 @default.
- W3094871513 hasConcept C154945302 @default.
- W3094871513 hasConcept C165801399 @default.
- W3094871513 hasConcept C195324797 @default.
- W3094871513 hasConcept C204321447 @default.
- W3094871513 hasConcept C23224414 @default.
- W3094871513 hasConcept C2777601683 @default.
- W3094871513 hasConcept C28490314 @default.
- W3094871513 hasConcept C39608478 @default.
- W3094871513 hasConcept C41008148 @default.
- W3094871513 hasConcept C41895202 @default.
- W3094871513 hasConcept C57273362 @default.
- W3094871513 hasConcept C66322947 @default.
- W3094871513 hasConcept C76155785 @default.
- W3094871513 hasConcept C83479923 @default.
- W3094871513 hasConceptScore W3094871513C119599485 @default.
- W3094871513 hasConceptScore W3094871513C127413603 @default.
- W3094871513 hasConceptScore W3094871513C129353971 @default.
- W3094871513 hasConceptScore W3094871513C137293760 @default.
- W3094871513 hasConceptScore W3094871513C138885662 @default.
- W3094871513 hasConceptScore W3094871513C154945302 @default.
- W3094871513 hasConceptScore W3094871513C165801399 @default.
- W3094871513 hasConceptScore W3094871513C195324797 @default.
- W3094871513 hasConceptScore W3094871513C204321447 @default.
- W3094871513 hasConceptScore W3094871513C23224414 @default.
- W3094871513 hasConceptScore W3094871513C2777601683 @default.
- W3094871513 hasConceptScore W3094871513C28490314 @default.
- W3094871513 hasConceptScore W3094871513C39608478 @default.
- W3094871513 hasConceptScore W3094871513C41008148 @default.
- W3094871513 hasConceptScore W3094871513C41895202 @default.
- W3094871513 hasConceptScore W3094871513C57273362 @default.
- W3094871513 hasConceptScore W3094871513C66322947 @default.
- W3094871513 hasConceptScore W3094871513C76155785 @default.
- W3094871513 hasConceptScore W3094871513C83479923 @default.
- W3094871513 hasLocation W30948715131 @default.
- W3094871513 hasOpenAccess W3094871513 @default.
- W3094871513 hasPrimaryLocation W30948715131 @default.
- W3094871513 hasRelatedWork W1481468666 @default.
- W3094871513 hasRelatedWork W1812060171 @default.
- W3094871513 hasRelatedWork W2059764863 @default.
- W3094871513 hasRelatedWork W2113094193 @default.
- W3094871513 hasRelatedWork W2120010607 @default.
- W3094871513 hasRelatedWork W2161306565 @default.
- W3094871513 hasRelatedWork W2374918184 @default.
- W3094871513 hasRelatedWork W2963899393 @default.
- W3094871513 hasRelatedWork W3107474891 @default.
- W3094871513 hasRelatedWork W2472867216 @default.
- W3094871513 isParatext "false" @default.
- W3094871513 isRetracted "false" @default.
- W3094871513 magId "3094871513" @default.
- W3094871513 workType "article" @default.