FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1591002022> ?p ?o ?g. }

• W1591002022 abstract "In this paper, we investigate the relative noise robustness between dynamic and static spectral features, by using two speaker independent continuous digit databases in English (Aurora2) and Cantonese (CUDigit). It is found that the dynamic cepstrum is more robust to additive noise than its static counterpart. The results are consistent across different types of noise and under various SNRs. Optimal exponential weights for exploiting unequal noise robustness of the two features are discriminatively trained in a development set. When tested under various noise conditions, the optimal weights yielded relative word error rate reductions of 36.6% and 41.9% for Aurora2 and CUDigit, respectively. The proposed weighting is attractive for many ASR applications in noise because: (1) no noise estimation for feature compensation; (2) no adaptation of clean HMMs to a noisy environment; and (3) only a trivial change in the decoding process by weighting log likelihoods of static and dynamic components separately." @default.
• W1591002022 created "2016-06-24" @default.
• W1591002022 creator A5001795601 @default.
• W1591002022 creator A5054821225 @default.
• W1591002022 creator A5065394791 @default.
• W1591002022 date "2006-10-11" @default.
• W1591002022 modified "2023-09-26" @default.
• W1591002022 title "Static and Dynamic Spectral Features: Their Noise Robustness and Optimal Weights for ASR" @default.
• W1591002022 cites W1652807540 @default.
• W1591002022 cites W1829217008 @default.
• W1591002022 cites W1897037354 @default.
• W1591002022 cites W1994396704 @default.
• W1591002022 cites W1999686891 @default.
• W1591002022 cites W2000629566 @default.
• W1591002022 cites W2045036776 @default.
• W1591002022 cites W2050693797 @default.
• W1591002022 cites W2072563337 @default.
• W1591002022 cites W2103780312 @default.
• W1591002022 cites W2116251645 @default.
• W1591002022 cites W2126597753 @default.
• W1591002022 cites W2128653836 @default.
• W1591002022 cites W2137075158 @default.
• W1591002022 cites W2146871184 @default.
• W1591002022 cites W2150008717 @default.
• W1591002022 cites W2151129782 @default.
• W1591002022 cites W2151484683 @default.
• W1591002022 cites W2157821739 @default.
• W1591002022 cites W2158289097 @default.
• W1591002022 cites W2166730073 @default.
• W1591002022 cites W2522791656 @default.
• W1591002022 cites W29686801 @default.
• W1591002022 cites W48303286 @default.
• W1591002022 cites W68871563 @default.
• W1591002022 cites W71808162 @default.
• W1591002022 doi "https://doi.org/10.1109/icassp.2005.1415095" @default.
• W1591002022 hasPublicationYear "2006" @default.
• W1591002022 type Work @default.
• W1591002022 sameAs 1591002022 @default.
• W1591002022 citedByCount "11" @default.
• W1591002022 countsByYear W15910020222012 @default.
• W1591002022 countsByYear W15910020222014 @default.
• W1591002022 countsByYear W15910020222017 @default.
• W1591002022 countsByYear W15910020222018 @default.
• W1591002022 crossrefType "proceedings-article" @default.
• W1591002022 hasAuthorship W1591002022A5001795601 @default.
• W1591002022 hasAuthorship W1591002022A5054821225 @default.
• W1591002022 hasAuthorship W1591002022A5065394791 @default.
• W1591002022 hasConcept C104317684 @default.
• W1591002022 hasConcept C115961682 @default.
• W1591002022 hasConcept C121332964 @default.
• W1591002022 hasConcept C153180895 @default.
• W1591002022 hasConcept C154945302 @default.
• W1591002022 hasConcept C163294075 @default.
• W1591002022 hasConcept C183115368 @default.
• W1591002022 hasConcept C185592680 @default.
• W1591002022 hasConcept C24890656 @default.
• W1591002022 hasConcept C28490314 @default.
• W1591002022 hasConcept C29265498 @default.
• W1591002022 hasConcept C41008148 @default.
• W1591002022 hasConcept C55493867 @default.
• W1591002022 hasConcept C63479239 @default.
• W1591002022 hasConcept C88485024 @default.
• W1591002022 hasConcept C99498987 @default.
• W1591002022 hasConceptScore W1591002022C104317684 @default.
• W1591002022 hasConceptScore W1591002022C115961682 @default.
• W1591002022 hasConceptScore W1591002022C121332964 @default.
• W1591002022 hasConceptScore W1591002022C153180895 @default.
• W1591002022 hasConceptScore W1591002022C154945302 @default.
• W1591002022 hasConceptScore W1591002022C163294075 @default.
• W1591002022 hasConceptScore W1591002022C183115368 @default.
• W1591002022 hasConceptScore W1591002022C185592680 @default.
• W1591002022 hasConceptScore W1591002022C24890656 @default.
• W1591002022 hasConceptScore W1591002022C28490314 @default.
• W1591002022 hasConceptScore W1591002022C29265498 @default.
• W1591002022 hasConceptScore W1591002022C41008148 @default.
• W1591002022 hasConceptScore W1591002022C55493867 @default.
• W1591002022 hasConceptScore W1591002022C63479239 @default.
• W1591002022 hasConceptScore W1591002022C88485024 @default.
• W1591002022 hasConceptScore W1591002022C99498987 @default.
• W1591002022 hasLocation W15910020221 @default.
• W1591002022 hasOpenAccess W1591002022 @default.
• W1591002022 hasPrimaryLocation W15910020221 @default.
• W1591002022 hasRelatedWork W1492999943 @default.
• W1591002022 hasRelatedWork W1717575570 @default.
• W1591002022 hasRelatedWork W1805204942 @default.
• W1591002022 hasRelatedWork W2016077841 @default.
• W1591002022 hasRelatedWork W2075273120 @default.
• W1591002022 hasRelatedWork W2120837095 @default.
• W1591002022 hasRelatedWork W2151484683 @default.
• W1591002022 hasRelatedWork W2157852208 @default.
• W1591002022 hasRelatedWork W2285729352 @default.
• W1591002022 hasRelatedWork W2396843779 @default.
• W1591002022 hasRelatedWork W2403743561 @default.
• W1591002022 hasRelatedWork W2617522273 @default.
• W1591002022 hasRelatedWork W269674882 @default.
• W1591002022 hasRelatedWork W2745106881 @default.
• W1591002022 hasRelatedWork W2962914040 @default.
• W1591002022 hasRelatedWork W3139726962 @default.
• W1591002022 hasRelatedWork W3150290231 @default.
• W1591002022 hasRelatedWork W69241656 @default.

• next