Matches in SemOpenAlex for { <https://semopenalex.org/work/W2122699724> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2122699724 abstract "We recently proposed a new algorithm to perform acoustic model adaptation to noisy environments called Linear Spline Interpolation (LSI). In this method, the nonlinear relationship between clean and noisy speech features is modeled using linear spline regression. Linear spline parameters that minimize the error the between the predicted noisy features and the actual noisy features are learned from training data. A variance associated with each spline segment captures the uncertainty in the assumed model. In this work, we extend the LSI algorithm in two ways. First, the adaptation scheme is extended to compensate for the presence of linear channel distortion. Second, we show how the noise and channel parameters can be updated during decoding in an unsupervised manner within the LSI framework. Using LSI, we obtain an average relative improvement in word error rate of 10.8% over VTS adaptation on the Aurora 2 task with improvements of 15-18% at SNRs between 10 and 15 dB." @default.
- W2122699724 created "2016-06-24" @default.
- W2122699724 creator A5008449971 @default.
- W2122699724 creator A5041313589 @default.
- W2122699724 creator A5078631486 @default.
- W2122699724 date "2010-01-01" @default.
- W2122699724 modified "2023-10-14" @default.
- W2122699724 title "Acoustic model adaptation via Linear Spline Interpolation for robust speech recognition" @default.
- W2122699724 cites W1983360901 @default.
- W2122699724 cites W2045036776 @default.
- W2122699724 cites W2106714211 @default.
- W2122699724 cites W2136489317 @default.
- W2122699724 doi "https://doi.org/10.1109/icassp.2010.5495581" @default.
- W2122699724 hasPublicationYear "2010" @default.
- W2122699724 type Work @default.
- W2122699724 sameAs 2122699724 @default.
- W2122699724 citedByCount "19" @default.
- W2122699724 countsByYear W21226997242012 @default.
- W2122699724 countsByYear W21226997242013 @default.
- W2122699724 countsByYear W21226997242015 @default.
- W2122699724 countsByYear W21226997242016 @default.
- W2122699724 countsByYear W21226997242018 @default.
- W2122699724 countsByYear W21226997242020 @default.
- W2122699724 countsByYear W21226997242021 @default.
- W2122699724 crossrefType "proceedings-article" @default.
- W2122699724 hasAuthorship W2122699724A5008449971 @default.
- W2122699724 hasAuthorship W2122699724A5041313589 @default.
- W2122699724 hasAuthorship W2122699724A5078631486 @default.
- W2122699724 hasConcept C10390562 @default.
- W2122699724 hasConcept C104114177 @default.
- W2122699724 hasConcept C11413529 @default.
- W2122699724 hasConcept C115961682 @default.
- W2122699724 hasConcept C127162648 @default.
- W2122699724 hasConcept C127413603 @default.
- W2122699724 hasConcept C137800194 @default.
- W2122699724 hasConcept C153180895 @default.
- W2122699724 hasConcept C154945302 @default.
- W2122699724 hasConcept C171836373 @default.
- W2122699724 hasConcept C205203396 @default.
- W2122699724 hasConcept C23224414 @default.
- W2122699724 hasConcept C28490314 @default.
- W2122699724 hasConcept C31258907 @default.
- W2122699724 hasConcept C31447003 @default.
- W2122699724 hasConcept C31972630 @default.
- W2122699724 hasConcept C41008148 @default.
- W2122699724 hasConcept C57273362 @default.
- W2122699724 hasConcept C66938386 @default.
- W2122699724 hasConcept C99498987 @default.
- W2122699724 hasConceptScore W2122699724C10390562 @default.
- W2122699724 hasConceptScore W2122699724C104114177 @default.
- W2122699724 hasConceptScore W2122699724C11413529 @default.
- W2122699724 hasConceptScore W2122699724C115961682 @default.
- W2122699724 hasConceptScore W2122699724C127162648 @default.
- W2122699724 hasConceptScore W2122699724C127413603 @default.
- W2122699724 hasConceptScore W2122699724C137800194 @default.
- W2122699724 hasConceptScore W2122699724C153180895 @default.
- W2122699724 hasConceptScore W2122699724C154945302 @default.
- W2122699724 hasConceptScore W2122699724C171836373 @default.
- W2122699724 hasConceptScore W2122699724C205203396 @default.
- W2122699724 hasConceptScore W2122699724C23224414 @default.
- W2122699724 hasConceptScore W2122699724C28490314 @default.
- W2122699724 hasConceptScore W2122699724C31258907 @default.
- W2122699724 hasConceptScore W2122699724C31447003 @default.
- W2122699724 hasConceptScore W2122699724C31972630 @default.
- W2122699724 hasConceptScore W2122699724C41008148 @default.
- W2122699724 hasConceptScore W2122699724C57273362 @default.
- W2122699724 hasConceptScore W2122699724C66938386 @default.
- W2122699724 hasConceptScore W2122699724C99498987 @default.
- W2122699724 hasLocation W21226997241 @default.
- W2122699724 hasOpenAccess W2122699724 @default.
- W2122699724 hasPrimaryLocation W21226997241 @default.
- W2122699724 hasRelatedWork W2005346028 @default.
- W2122699724 hasRelatedWork W2009136130 @default.
- W2122699724 hasRelatedWork W2061482616 @default.
- W2122699724 hasRelatedWork W2129112923 @default.
- W2122699724 hasRelatedWork W2341600665 @default.
- W2122699724 hasRelatedWork W2349715036 @default.
- W2122699724 hasRelatedWork W2365148738 @default.
- W2122699724 hasRelatedWork W2370429033 @default.
- W2122699724 hasRelatedWork W2379507827 @default.
- W2122699724 hasRelatedWork W2384462540 @default.
- W2122699724 isParatext "false" @default.
- W2122699724 isRetracted "false" @default.
- W2122699724 magId "2122699724" @default.
- W2122699724 workType "article" @default.