FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2017608047> ?p ?o ?g. }

• W2017608047 endingPage "2002" @default.
• W2017608047 startingPage "1993" @default.
• W2017608047 abstract "Speech separation can be formulated as a classification problem. In classification-based speech separation, supervised learning is employed to classify time-frequency units as either speech-dominant or noise-dominant. In very low signal-to-noise ratio (SNR) conditions, acoustic features extracted from a mixture are crucial for correct classification. In this study, we systematically evaluate a range of promising features for classification-based separation using six nonstationary noises at the low SNR level of -5 dB, which is chosen with the goal of improving human speech intelligibility in mind. In addition, we propose a new feature called multi-resolution cochleagram (MRCG). The new feature is constructed by combining four cochleagrams at different spectrotemporal resolutions in order to capture both the local and contextual information. Experimental results show that MRCG gives the best classification results among all evaluated features. In addition, our results indicate that auto-regressive moving average (ARMA) filtering, a post-processing technique for improving automatic speech recognition features, also improves many acoustic features for speech separation." @default.
• W2017608047 created "2016-06-24" @default.
• W2017608047 creator A5035742417 @default.
• W2017608047 creator A5046063537 @default.
• W2017608047 creator A5051837453 @default.
• W2017608047 date "2014-12-01" @default.
• W2017608047 modified "2023-10-17" @default.
• W2017608047 title "A Feature Study for Classification-Based Speech Separation at Low Signal-to-Noise Ratios" @default.
• W2017608047 cites W118588063 @default.
• W2017608047 cites W1493299544 @default.
• W2017608047 cites W160800111 @default.
• W2017608047 cites W1963970749 @default.
• W2017608047 cites W1974387177 @default.
• W2017608047 cites W1979099822 @default.
• W2017608047 cites W1989364685 @default.
• W2017608047 cites W1990934990 @default.
• W2017608047 cites W2013312573 @default.
• W2017608047 cites W2020438552 @default.
• W2017608047 cites W2027701650 @default.
• W2017608047 cites W2027804983 @default.
• W2017608047 cites W2030680983 @default.
• W2017608047 cites W2052667477 @default.
• W2017608047 cites W2055516313 @default.
• W2017608047 cites W2057200980 @default.
• W2017608047 cites W2057889776 @default.
• W2017608047 cites W2061140267 @default.
• W2017608047 cites W2070707809 @default.
• W2017608047 cites W2073612610 @default.
• W2017608047 cites W2085191029 @default.
• W2017608047 cites W2088137865 @default.
• W2017608047 cites W2090861223 @default.
• W2017608047 cites W2106398669 @default.
• W2017608047 cites W2114719288 @default.
• W2017608047 cites W2123157731 @default.
• W2017608047 cites W2137075158 @default.
• W2017608047 cites W2153119843 @default.
• W2017608047 cites W2158483598 @default.
• W2017608047 cites W2159202424 @default.
• W2017608047 cites W2166243357 @default.
• W2017608047 cites W2168379380 @default.
• W2017608047 cites W4231807801 @default.
• W2017608047 cites W4243882841 @default.
• W2017608047 cites W67398352 @default.
• W2017608047 doi "https://doi.org/10.1109/taslp.2014.2359159" @default.
• W2017608047 hasPublicationYear "2014" @default.
• W2017608047 type Work @default.
• W2017608047 sameAs 2017608047 @default.
• W2017608047 citedByCount "121" @default.
• W2017608047 countsByYear W20176080472015 @default.
• W2017608047 countsByYear W20176080472016 @default.
• W2017608047 countsByYear W20176080472017 @default.
• W2017608047 countsByYear W20176080472018 @default.
• W2017608047 countsByYear W20176080472019 @default.
• W2017608047 countsByYear W20176080472020 @default.
• W2017608047 countsByYear W20176080472021 @default.
• W2017608047 countsByYear W20176080472022 @default.
• W2017608047 countsByYear W20176080472023 @default.
• W2017608047 crossrefType "journal-article" @default.
• W2017608047 hasAuthorship W2017608047A5035742417 @default.
• W2017608047 hasAuthorship W2017608047A5046063537 @default.
• W2017608047 hasAuthorship W2017608047A5051837453 @default.
• W2017608047 hasConcept C115961682 @default.
• W2017608047 hasConcept C121332964 @default.
• W2017608047 hasConcept C138885662 @default.
• W2017608047 hasConcept C153180895 @default.
• W2017608047 hasConcept C154945302 @default.
• W2017608047 hasConcept C199360897 @default.
• W2017608047 hasConcept C24890656 @default.
• W2017608047 hasConcept C2776401178 @default.
• W2017608047 hasConcept C2779843651 @default.
• W2017608047 hasConcept C28490314 @default.
• W2017608047 hasConcept C41008148 @default.
• W2017608047 hasConcept C41895202 @default.
• W2017608047 hasConcept C99498987 @default.
• W2017608047 hasConceptScore W2017608047C115961682 @default.
• W2017608047 hasConceptScore W2017608047C121332964 @default.
• W2017608047 hasConceptScore W2017608047C138885662 @default.
• W2017608047 hasConceptScore W2017608047C153180895 @default.
• W2017608047 hasConceptScore W2017608047C154945302 @default.
• W2017608047 hasConceptScore W2017608047C199360897 @default.
• W2017608047 hasConceptScore W2017608047C24890656 @default.
• W2017608047 hasConceptScore W2017608047C2776401178 @default.
• W2017608047 hasConceptScore W2017608047C2779843651 @default.
• W2017608047 hasConceptScore W2017608047C28490314 @default.
• W2017608047 hasConceptScore W2017608047C41008148 @default.
• W2017608047 hasConceptScore W2017608047C41895202 @default.
• W2017608047 hasConceptScore W2017608047C99498987 @default.
• W2017608047 hasIssue "12" @default.
• W2017608047 hasLocation W20176080471 @default.
• W2017608047 hasOpenAccess W2017608047 @default.
• W2017608047 hasPrimaryLocation W20176080471 @default.
• W2017608047 hasRelatedWork W2016461833 @default.
• W2017608047 hasRelatedWork W2052253960 @default.
• W2017608047 hasRelatedWork W2147802381 @default.
• W2017608047 hasRelatedWork W2382607599 @default.
• W2017608047 hasRelatedWork W2489255581 @default.
• W2017608047 hasRelatedWork W2760085659 @default.
• W2017608047 hasRelatedWork W2970216048 @default.

• next