Matches in SemOpenAlex for { <https://semopenalex.org/work/W4375869056> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4375869056 abstract "Acoustic feedback arises from the leakage of sound from the loudspeaker back to the microphone and is a common problem in hearing aids and public address systems. One popular solution to this problem is adaptive feedback cancellation (AFC) which utilizes an adaptive filter (AF) to estimate and subsequently subtract the feedback component from the microphone. Due to the closed-loop system the loudspeaker signal and the incoming signal exhibit a high correlation. However, model-based and more recently learning-based AF methods typically neglect this correlation in their derivation, leading to sub-optimal performance in closed-loop scenarios. In this paper, we propose Neural-AFC, a recurrent neural network (RNN) designed for AFC step-size control optimization, that addresses this problem by including not only the adaptive filter but also the acoustic feedback path and the system gain in the recurrence model. Our experiment results show that when trained within this closed-loop model, Neural-AFC improves the steady-state performance and (re)convergence rate compared to conventional and open-loop RNN-based AF in both hearing aid and public address system applications." @default.
- W4375869056 created "2023-05-10" @default.
- W4375869056 creator A5013093821 @default.
- W4375869056 creator A5026205150 @default.
- W4375869056 creator A5083953535 @default.
- W4375869056 date "2023-06-04" @default.
- W4375869056 modified "2023-09-27" @default.
- W4375869056 title "Neural-AFC: Learning-Based Step-Size Control for Adaptive Feedback Cancellation with Closed-Loop Model Training" @default.
- W4375869056 cites W1491843047 @default.
- W4375869056 cites W1494198834 @default.
- W4375869056 cites W1654142233 @default.
- W4375869056 cites W1965795117 @default.
- W4375869056 cites W1977144816 @default.
- W4375869056 cites W1994510259 @default.
- W4375869056 cites W2004031438 @default.
- W4375869056 cites W2027282255 @default.
- W4375869056 cites W2032676419 @default.
- W4375869056 cites W2036512040 @default.
- W4375869056 cites W2097095546 @default.
- W4375869056 cites W2136682440 @default.
- W4375869056 cites W2150355110 @default.
- W4375869056 cites W2156367112 @default.
- W4375869056 cites W2158760189 @default.
- W4375869056 cites W2397974105 @default.
- W4375869056 cites W2544921883 @default.
- W4375869056 cites W2626210771 @default.
- W4375869056 cites W2718043749 @default.
- W4375869056 cites W2784003631 @default.
- W4375869056 cites W2794331672 @default.
- W4375869056 cites W2900161807 @default.
- W4375869056 cites W2911058322 @default.
- W4375869056 cites W4226134299 @default.
- W4375869056 doi "https://doi.org/10.1109/icassp49357.2023.10094841" @default.
- W4375869056 hasPublicationYear "2023" @default.
- W4375869056 type Work @default.
- W4375869056 citedByCount "0" @default.
- W4375869056 crossrefType "proceedings-article" @default.
- W4375869056 hasAuthorship W4375869056A5013093821 @default.
- W4375869056 hasAuthorship W4375869056A5026205150 @default.
- W4375869056 hasAuthorship W4375869056A5083953535 @default.
- W4375869056 hasBestOaLocation W43758690561 @default.
- W4375869056 hasConcept C102248274 @default.
- W4375869056 hasConcept C11413529 @default.
- W4375869056 hasConcept C119599485 @default.
- W4375869056 hasConcept C127413603 @default.
- W4375869056 hasConcept C147168706 @default.
- W4375869056 hasConcept C154945302 @default.
- W4375869056 hasConcept C157138929 @default.
- W4375869056 hasConcept C186886427 @default.
- W4375869056 hasConcept C2775924081 @default.
- W4375869056 hasConcept C2778263558 @default.
- W4375869056 hasConcept C28490314 @default.
- W4375869056 hasConcept C38652104 @default.
- W4375869056 hasConcept C38956757 @default.
- W4375869056 hasConcept C41008148 @default.
- W4375869056 hasConcept C47446073 @default.
- W4375869056 hasConcept C50644808 @default.
- W4375869056 hasConceptScore W4375869056C102248274 @default.
- W4375869056 hasConceptScore W4375869056C11413529 @default.
- W4375869056 hasConceptScore W4375869056C119599485 @default.
- W4375869056 hasConceptScore W4375869056C127413603 @default.
- W4375869056 hasConceptScore W4375869056C147168706 @default.
- W4375869056 hasConceptScore W4375869056C154945302 @default.
- W4375869056 hasConceptScore W4375869056C157138929 @default.
- W4375869056 hasConceptScore W4375869056C186886427 @default.
- W4375869056 hasConceptScore W4375869056C2775924081 @default.
- W4375869056 hasConceptScore W4375869056C2778263558 @default.
- W4375869056 hasConceptScore W4375869056C28490314 @default.
- W4375869056 hasConceptScore W4375869056C38652104 @default.
- W4375869056 hasConceptScore W4375869056C38956757 @default.
- W4375869056 hasConceptScore W4375869056C41008148 @default.
- W4375869056 hasConceptScore W4375869056C47446073 @default.
- W4375869056 hasConceptScore W4375869056C50644808 @default.
- W4375869056 hasLocation W43758690561 @default.
- W4375869056 hasOpenAccess W4375869056 @default.
- W4375869056 hasPrimaryLocation W43758690561 @default.
- W4375869056 hasRelatedWork W1529558362 @default.
- W4375869056 hasRelatedWork W185047939 @default.
- W4375869056 hasRelatedWork W2018880997 @default.
- W4375869056 hasRelatedWork W2021577189 @default.
- W4375869056 hasRelatedWork W2092185782 @default.
- W4375869056 hasRelatedWork W2102031346 @default.
- W4375869056 hasRelatedWork W2404760595 @default.
- W4375869056 hasRelatedWork W3082684561 @default.
- W4375869056 hasRelatedWork W3165319659 @default.
- W4375869056 hasRelatedWork W3185718121 @default.
- W4375869056 isParatext "false" @default.
- W4375869056 isRetracted "false" @default.
- W4375869056 workType "article" @default.