Matches in SemOpenAlex for { <https://semopenalex.org/work/W2963189033> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W2963189033 abstract "In recent years, deep networks have led to dramatic improvements in speech enhancement by framing it as a data-driven pattern recognition problem. In many modern enhancement systems, large amounts of data are used to train a deep network to estimate masks for complex-valued short-time Fourier transforms (STFTs) to suppress noise and preserve speech. However, current masking approaches often neglect two important constraints: STFT consistency and mixture consistency. Without STFT consistency, the system’s output is not necessarily the STFT of a time-domain signal, and without mixture consistency, the sum of the estimated sources does not necessarily equal the input mixture. Furthermore, the only previous approaches that apply mixture consistency use real-valued masks; mixture consistency has been ignored for complex-valued masks." @default.
- W2963189033 created "2019-07-30" @default.
- W2963189033 creator A5001338678 @default.
- W2963189033 creator A5013234773 @default.
- W2963189033 creator A5016309279 @default.
- W2963189033 creator A5026650852 @default.
- W2963189033 creator A5053447215 @default.
- W2963189033 creator A5082524152 @default.
- W2963189033 creator A5087313939 @default.
- W2963189033 date "2019-05-01" @default.
- W2963189033 modified "2023-09-23" @default.
- W2963189033 title "Differentiable Consistency Constraints for Improved Deep Speech Enhancement" @default.
- W2963189033 cites W1482149378 @default.
- W2963189033 cites W1494198834 @default.
- W2963189033 cites W1574170747 @default.
- W2963189033 cites W1817284079 @default.
- W2963189033 cites W2013419672 @default.
- W2963189033 cites W2126762974 @default.
- W2963189033 cites W2141411743 @default.
- W2963189033 cites W2156379660 @default.
- W2963189033 cites W2406737436 @default.
- W2963189033 cites W2775265115 @default.
- W2963189033 cites W2808920027 @default.
- W2963189033 cites W2889286744 @default.
- W2963189033 cites W2962715207 @default.
- W2963189033 cites W2962905190 @default.
- W2963189033 doi "https://doi.org/10.1109/icassp.2019.8682783" @default.
- W2963189033 hasPublicationYear "2019" @default.
- W2963189033 type Work @default.
- W2963189033 sameAs 2963189033 @default.
- W2963189033 citedByCount "86" @default.
- W2963189033 countsByYear W29631890332019 @default.
- W2963189033 countsByYear W29631890332020 @default.
- W2963189033 countsByYear W29631890332021 @default.
- W2963189033 countsByYear W29631890332022 @default.
- W2963189033 countsByYear W29631890332023 @default.
- W2963189033 crossrefType "proceedings-article" @default.
- W2963189033 hasAuthorship W2963189033A5001338678 @default.
- W2963189033 hasAuthorship W2963189033A5013234773 @default.
- W2963189033 hasAuthorship W2963189033A5016309279 @default.
- W2963189033 hasAuthorship W2963189033A5026650852 @default.
- W2963189033 hasAuthorship W2963189033A5053447215 @default.
- W2963189033 hasAuthorship W2963189033A5082524152 @default.
- W2963189033 hasAuthorship W2963189033A5087313939 @default.
- W2963189033 hasBestOaLocation W29631890332 @default.
- W2963189033 hasConcept C134306372 @default.
- W2963189033 hasConcept C154945302 @default.
- W2963189033 hasConcept C163294075 @default.
- W2963189033 hasConcept C202615002 @default.
- W2963189033 hasConcept C2776182073 @default.
- W2963189033 hasConcept C2776436953 @default.
- W2963189033 hasConcept C28490314 @default.
- W2963189033 hasConcept C33923547 @default.
- W2963189033 hasConcept C41008148 @default.
- W2963189033 hasConceptScore W2963189033C134306372 @default.
- W2963189033 hasConceptScore W2963189033C154945302 @default.
- W2963189033 hasConceptScore W2963189033C163294075 @default.
- W2963189033 hasConceptScore W2963189033C202615002 @default.
- W2963189033 hasConceptScore W2963189033C2776182073 @default.
- W2963189033 hasConceptScore W2963189033C2776436953 @default.
- W2963189033 hasConceptScore W2963189033C28490314 @default.
- W2963189033 hasConceptScore W2963189033C33923547 @default.
- W2963189033 hasConceptScore W2963189033C41008148 @default.
- W2963189033 hasLocation W29631890331 @default.
- W2963189033 hasLocation W29631890332 @default.
- W2963189033 hasOpenAccess W2963189033 @default.
- W2963189033 hasPrimaryLocation W29631890331 @default.
- W2963189033 hasRelatedWork W1600259599 @default.
- W2963189033 hasRelatedWork W2166831097 @default.
- W2963189033 hasRelatedWork W2350879319 @default.
- W2963189033 hasRelatedWork W2353865532 @default.
- W2963189033 hasRelatedWork W2368779261 @default.
- W2963189033 hasRelatedWork W2653598178 @default.
- W2963189033 hasRelatedWork W2747006289 @default.
- W2963189033 hasRelatedWork W2778699561 @default.
- W2963189033 hasRelatedWork W2794438528 @default.
- W2963189033 hasRelatedWork W2901917862 @default.
- W2963189033 isParatext "false" @default.
- W2963189033 isRetracted "false" @default.
- W2963189033 magId "2963189033" @default.
- W2963189033 workType "article" @default.