FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2902459807> ?p ?o ?g. }

• W2902459807 abstract "Supervised non-negative matrix factorization (NMF) is effective in speech enhancement through training spectral models of speech and noise signals. However, the enhancement quality reduces when the models are trained on data that is not highly relevant to a speech signal and a noise signal in a noisy observation. In this paper, we propose to train a classifier in order to overcome such poor characterization of the signals through the trained models. The main idea is to decompose the noisy observation into parts and the enhanced signal is reconstructed by combining the less-corrupted ones which are identified in the cepstral domain using the trained classifier. We apply unsupervised NMF followed by Wiener filtering for the decomposition, and use a support vector machine trained on the mel-frequency cepstral coefficients of the parts of training speech and noise signals for the classification. The results show the effectiveness of the proposed method compared with the supervised NMF." @default.
• W2902459807 created "2018-12-11" @default.
• W2902459807 creator A5007282822 @default.
• W2902459807 creator A5019002740 @default.
• W2902459807 creator A5026658144 @default.
• W2902459807 date "2018-09-01" @default.
• W2902459807 modified "2023-10-16" @default.
• W2902459807 title "Speech Enhancement by Classification of Noisy Signals Decomposed Using NMF and Wiener Filtering" @default.
• W2902459807 cites W1504438288 @default.
• W2902459807 cites W1552314771 @default.
• W2902459807 cites W165956390 @default.
• W2902459807 cites W1902027874 @default.
• W2902459807 cites W1980183422 @default.
• W2902459807 cites W2046233597 @default.
• W2902459807 cites W2048687561 @default.
• W2902459807 cites W2051428568 @default.
• W2902459807 cites W2115594062 @default.
• W2902459807 cites W2121894251 @default.
• W2902459807 cites W2140828385 @default.
• W2902459807 cites W2144561273 @default.
• W2902459807 cites W2235103357 @default.
• W2902459807 cites W2254223938 @default.
• W2902459807 cites W2404400936 @default.
• W2902459807 cites W2607108972 @default.
• W2902459807 cites W2748130992 @default.
• W2902459807 cites W2802812753 @default.
• W2902459807 cites W4239510810 @default.
• W2902459807 cites W4253928870 @default.
• W2902459807 doi "https://doi.org/10.23919/eusipco.2018.8553123" @default.
• W2902459807 hasPublicationYear "2018" @default.
• W2902459807 type Work @default.
• W2902459807 sameAs 2902459807 @default.
• W2902459807 citedByCount "7" @default.
• W2902459807 countsByYear W29024598072019 @default.
• W2902459807 countsByYear W29024598072020 @default.
• W2902459807 countsByYear W29024598072021 @default.
• W2902459807 countsByYear W29024598072023 @default.
• W2902459807 crossrefType "proceedings-article" @default.
• W2902459807 hasAuthorship W2902459807A5007282822 @default.
• W2902459807 hasAuthorship W2902459807A5019002740 @default.
• W2902459807 hasAuthorship W2902459807A5026658144 @default.
• W2902459807 hasBestOaLocation W29024598072 @default.
• W2902459807 hasConcept C111472728 @default.
• W2902459807 hasConcept C115961682 @default.
• W2902459807 hasConcept C121332964 @default.
• W2902459807 hasConcept C12267149 @default.
• W2902459807 hasConcept C138885662 @default.
• W2902459807 hasConcept C151989614 @default.
• W2902459807 hasConcept C152671427 @default.
• W2902459807 hasConcept C153180895 @default.
• W2902459807 hasConcept C154945302 @default.
• W2902459807 hasConcept C158693339 @default.
• W2902459807 hasConcept C163294075 @default.
• W2902459807 hasConcept C18537770 @default.
• W2902459807 hasConcept C2776182073 @default.
• W2902459807 hasConcept C28490314 @default.
• W2902459807 hasConcept C29265498 @default.
• W2902459807 hasConcept C41008148 @default.
• W2902459807 hasConcept C42355184 @default.
• W2902459807 hasConcept C52622490 @default.
• W2902459807 hasConcept C60048801 @default.
• W2902459807 hasConcept C62520636 @default.
• W2902459807 hasConcept C88485024 @default.
• W2902459807 hasConcept C95623464 @default.
• W2902459807 hasConcept C99498987 @default.
• W2902459807 hasConceptScore W2902459807C111472728 @default.
• W2902459807 hasConceptScore W2902459807C115961682 @default.
• W2902459807 hasConceptScore W2902459807C121332964 @default.
• W2902459807 hasConceptScore W2902459807C12267149 @default.
• W2902459807 hasConceptScore W2902459807C138885662 @default.
• W2902459807 hasConceptScore W2902459807C151989614 @default.
• W2902459807 hasConceptScore W2902459807C152671427 @default.
• W2902459807 hasConceptScore W2902459807C153180895 @default.
• W2902459807 hasConceptScore W2902459807C154945302 @default.
• W2902459807 hasConceptScore W2902459807C158693339 @default.
• W2902459807 hasConceptScore W2902459807C163294075 @default.
• W2902459807 hasConceptScore W2902459807C18537770 @default.
• W2902459807 hasConceptScore W2902459807C2776182073 @default.
• W2902459807 hasConceptScore W2902459807C28490314 @default.
• W2902459807 hasConceptScore W2902459807C29265498 @default.
• W2902459807 hasConceptScore W2902459807C41008148 @default.
• W2902459807 hasConceptScore W2902459807C42355184 @default.
• W2902459807 hasConceptScore W2902459807C52622490 @default.
• W2902459807 hasConceptScore W2902459807C60048801 @default.
• W2902459807 hasConceptScore W2902459807C62520636 @default.
• W2902459807 hasConceptScore W2902459807C88485024 @default.
• W2902459807 hasConceptScore W2902459807C95623464 @default.
• W2902459807 hasConceptScore W2902459807C99498987 @default.
• W2902459807 hasLocation W29024598071 @default.
• W2902459807 hasLocation W29024598072 @default.
• W2902459807 hasLocation W29024598073 @default.
• W2902459807 hasOpenAccess W2902459807 @default.
• W2902459807 hasPrimaryLocation W29024598071 @default.
• W2902459807 hasRelatedWork W2020571614 @default.
• W2902459807 hasRelatedWork W2117765945 @default.
• W2902459807 hasRelatedWork W2122333497 @default.
• W2902459807 hasRelatedWork W2146970321 @default.
• W2902459807 hasRelatedWork W2167342572 @default.
• W2902459807 hasRelatedWork W2407147558 @default.
• W2902459807 hasRelatedWork W2769260541 @default.

• next