Matches in SemOpenAlex for { <https://semopenalex.org/work/W3162133351> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3162133351 abstract "Binaural speech enhancement has often suffered from the trade-off between noise reduction and spatial cue preservation. The common-gain filtering of noisy speech under minimum mean-square error (MMSE) turned out as a viable approach, which resembles the format of Wiener-filtering spectral enhancement. Those techniques critically require the estimation of the local time-varying a-priori SNR. In single-channel approaches, it has been recently shown that local a-priori SNR can be marginalized in a Bayesian sense with an MMSE approach. In this paper, we translate the single-channel approach into a binaural Bayesian SNR marginalization, based on a binaural a-priori SNR definition and a related hyperprior. The overall MMSE solution then turns into a posterior expectation of an informed cue-preserving Wiener filter function, the computation of which is governed by binaural a-posteriori SNR and global SNR (i.e., the hyper-prior mean). The resulting MMSE solution is thus easy to implement and performance consistently stands at the top of our evaluation by segmental SNR, PESQ, and STOI computational metrics." @default.
- W3162133351 created "2021-05-24" @default.
- W3162133351 creator A5077936911 @default.
- W3162133351 creator A5088433449 @default.
- W3162133351 date "2021-06-06" @default.
- W3162133351 modified "2023-09-27" @default.
- W3162133351 title "Cue-Preserving MMSE Filter with Bayesian SNR Marginalization for Binaural Speech Enhancement" @default.
- W3162133351 cites W1614886494 @default.
- W3162133351 cites W1969838670 @default.
- W3162133351 cites W2024960421 @default.
- W3162133351 cites W2034082908 @default.
- W3162133351 cites W2045956438 @default.
- W3162133351 cites W2051428568 @default.
- W3162133351 cites W2100399221 @default.
- W3162133351 cites W2107557537 @default.
- W3162133351 cites W2121973264 @default.
- W3162133351 cites W2122171611 @default.
- W3162133351 cites W2131309056 @default.
- W3162133351 cites W2136682440 @default.
- W3162133351 cites W2141998673 @default.
- W3162133351 cites W2143156057 @default.
- W3162133351 cites W2158336491 @default.
- W3162133351 cites W2289898380 @default.
- W3162133351 cites W2310962060 @default.
- W3162133351 cites W2735973601 @default.
- W3162133351 cites W2888169925 @default.
- W3162133351 cites W3147539069 @default.
- W3162133351 cites W4214498238 @default.
- W3162133351 cites W2077947506 @default.
- W3162133351 doi "https://doi.org/10.1109/icassp39728.2021.9414956" @default.
- W3162133351 hasPublicationYear "2021" @default.
- W3162133351 type Work @default.
- W3162133351 sameAs 3162133351 @default.
- W3162133351 citedByCount "0" @default.
- W3162133351 crossrefType "proceedings-article" @default.
- W3162133351 hasAuthorship W3162133351A5077936911 @default.
- W3162133351 hasAuthorship W3162133351A5088433449 @default.
- W3162133351 hasConcept C103734657 @default.
- W3162133351 hasConcept C105795698 @default.
- W3162133351 hasConcept C106131492 @default.
- W3162133351 hasConcept C107673813 @default.
- W3162133351 hasConcept C111472728 @default.
- W3162133351 hasConcept C11413529 @default.
- W3162133351 hasConcept C138885662 @default.
- W3162133351 hasConcept C154945302 @default.
- W3162133351 hasConcept C163294075 @default.
- W3162133351 hasConcept C18537770 @default.
- W3162133351 hasConcept C185429906 @default.
- W3162133351 hasConcept C201247586 @default.
- W3162133351 hasConcept C2776182073 @default.
- W3162133351 hasConcept C28490314 @default.
- W3162133351 hasConcept C31972630 @default.
- W3162133351 hasConcept C33923547 @default.
- W3162133351 hasConcept C41008148 @default.
- W3162133351 hasConcept C49781872 @default.
- W3162133351 hasConcept C75553542 @default.
- W3162133351 hasConcept C90652560 @default.
- W3162133351 hasConcept C9810830 @default.
- W3162133351 hasConceptScore W3162133351C103734657 @default.
- W3162133351 hasConceptScore W3162133351C105795698 @default.
- W3162133351 hasConceptScore W3162133351C106131492 @default.
- W3162133351 hasConceptScore W3162133351C107673813 @default.
- W3162133351 hasConceptScore W3162133351C111472728 @default.
- W3162133351 hasConceptScore W3162133351C11413529 @default.
- W3162133351 hasConceptScore W3162133351C138885662 @default.
- W3162133351 hasConceptScore W3162133351C154945302 @default.
- W3162133351 hasConceptScore W3162133351C163294075 @default.
- W3162133351 hasConceptScore W3162133351C18537770 @default.
- W3162133351 hasConceptScore W3162133351C185429906 @default.
- W3162133351 hasConceptScore W3162133351C201247586 @default.
- W3162133351 hasConceptScore W3162133351C2776182073 @default.
- W3162133351 hasConceptScore W3162133351C28490314 @default.
- W3162133351 hasConceptScore W3162133351C31972630 @default.
- W3162133351 hasConceptScore W3162133351C33923547 @default.
- W3162133351 hasConceptScore W3162133351C41008148 @default.
- W3162133351 hasConceptScore W3162133351C49781872 @default.
- W3162133351 hasConceptScore W3162133351C75553542 @default.
- W3162133351 hasConceptScore W3162133351C90652560 @default.
- W3162133351 hasConceptScore W3162133351C9810830 @default.
- W3162133351 hasLocation W31621333511 @default.
- W3162133351 hasOpenAccess W3162133351 @default.
- W3162133351 hasPrimaryLocation W31621333511 @default.
- W3162133351 hasRelatedWork W1964509438 @default.
- W3162133351 hasRelatedWork W2053588309 @default.
- W3162133351 hasRelatedWork W2106793170 @default.
- W3162133351 hasRelatedWork W2127601328 @default.
- W3162133351 hasRelatedWork W2405774341 @default.
- W3162133351 hasRelatedWork W2533598077 @default.
- W3162133351 hasRelatedWork W26845451 @default.
- W3162133351 hasRelatedWork W2787650696 @default.
- W3162133351 hasRelatedWork W3162133351 @default.
- W3162133351 hasRelatedWork W3203814202 @default.
- W3162133351 isParatext "false" @default.
- W3162133351 isRetracted "false" @default.
- W3162133351 magId "3162133351" @default.
- W3162133351 workType "article" @default.