Matches in SemOpenAlex for { <https://semopenalex.org/work/W4252357778> ?p ?o ?g. }
Showing items 1 to 64 of
64
with 100 items per page.
- W4252357778 endingPage "321" @default.
- W4252357778 startingPage "321" @default.
- W4252357778 abstract "In-car infotainment and navigation devices are typical examples where speech based interfaces are successfully applied. While classical applications are monolingual, such as voice commands or monolingual destination input, the trend goes towards multilingual applications. Examples are music player control or multilingual destination input. As soon as more languages are considered the training and decoding complexity of the speech recognizer increases. For large multilingual systems, some kind of parameter tying is needed to keep the decoding task feasible on embedded systems with limited resources. A traditional technique for this is to use a semi-continuous Hidden Markov Model as the acoustic model. The monolingual codebook on which such a system relies is not appropriate for multilingual recognition. We introduce Multilingual Weighted Codebooks that give good results with low decoding complexity. These codebooks depend on the actual language combination and increase the training complexity. Therefore an algorithm is needed that can reduce the training complexity. Our first proposal are mathematically motivated projections between Hidden Markov Models defined in Gaussian spaces. Although theoretically optimal, these projections were difficult to employ directly in speech decoders. We found approximated projections to be most effective for practical application, giving good performance without requiring major modifications to the common speech recognizer architecture. With a combination of the Multilingual Weighted Codebooks and Gaussian Mixture Model projections we create an efficient and scalable architecture for non-native speech recognition. Our new architecture offers a solution to the combinatoric problems of training and decoding for multiple languages. It builds new multilingual systems in only 0.002% of the time of a traditional HMM training, and achieves comparable performance on foreign languages." @default.
- W4252357778 created "2022-05-12" @default.
- W4252357778 date "1982-12-01" @default.
- W4252357778 modified "2023-09-30" @default.
- W4252357778 title "Computer peripherals for the home infotainment market" @default.
- W4252357778 doi "https://doi.org/10.1016/0140-3664(82)90079-2" @default.
- W4252357778 hasPublicationYear "1982" @default.
- W4252357778 type Work @default.
- W4252357778 citedByCount "0" @default.
- W4252357778 crossrefType "journal-article" @default.
- W4252357778 hasConcept C113775141 @default.
- W4252357778 hasConcept C11413529 @default.
- W4252357778 hasConcept C121332964 @default.
- W4252357778 hasConcept C123657996 @default.
- W4252357778 hasConcept C127759330 @default.
- W4252357778 hasConcept C137293760 @default.
- W4252357778 hasConcept C142362112 @default.
- W4252357778 hasConcept C153349607 @default.
- W4252357778 hasConcept C154945302 @default.
- W4252357778 hasConcept C163716315 @default.
- W4252357778 hasConcept C23224414 @default.
- W4252357778 hasConcept C28490314 @default.
- W4252357778 hasConcept C41008148 @default.
- W4252357778 hasConcept C48044578 @default.
- W4252357778 hasConcept C57273362 @default.
- W4252357778 hasConcept C62520636 @default.
- W4252357778 hasConcept C77088390 @default.
- W4252357778 hasConceptScore W4252357778C113775141 @default.
- W4252357778 hasConceptScore W4252357778C11413529 @default.
- W4252357778 hasConceptScore W4252357778C121332964 @default.
- W4252357778 hasConceptScore W4252357778C123657996 @default.
- W4252357778 hasConceptScore W4252357778C127759330 @default.
- W4252357778 hasConceptScore W4252357778C137293760 @default.
- W4252357778 hasConceptScore W4252357778C142362112 @default.
- W4252357778 hasConceptScore W4252357778C153349607 @default.
- W4252357778 hasConceptScore W4252357778C154945302 @default.
- W4252357778 hasConceptScore W4252357778C163716315 @default.
- W4252357778 hasConceptScore W4252357778C23224414 @default.
- W4252357778 hasConceptScore W4252357778C28490314 @default.
- W4252357778 hasConceptScore W4252357778C41008148 @default.
- W4252357778 hasConceptScore W4252357778C48044578 @default.
- W4252357778 hasConceptScore W4252357778C57273362 @default.
- W4252357778 hasConceptScore W4252357778C62520636 @default.
- W4252357778 hasConceptScore W4252357778C77088390 @default.
- W4252357778 hasIssue "6" @default.
- W4252357778 hasLocation W42523577781 @default.
- W4252357778 hasOpenAccess W4252357778 @default.
- W4252357778 hasPrimaryLocation W42523577781 @default.
- W4252357778 hasRelatedWork W2071913588 @default.
- W4252357778 hasRelatedWork W2121188849 @default.
- W4252357778 hasRelatedWork W2167131998 @default.
- W4252357778 hasRelatedWork W2350700696 @default.
- W4252357778 hasRelatedWork W2374918184 @default.
- W4252357778 hasRelatedWork W2382623646 @default.
- W4252357778 hasRelatedWork W2539416393 @default.
- W4252357778 hasRelatedWork W2996122240 @default.
- W4252357778 hasRelatedWork W3016053754 @default.
- W4252357778 hasRelatedWork W60887625 @default.
- W4252357778 hasVolume "5" @default.
- W4252357778 isParatext "false" @default.
- W4252357778 isRetracted "false" @default.
- W4252357778 workType "article" @default.