FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311187170> ?p ?o ?g. }

• W4311187170 endingPage "370" @default.
• W4311187170 startingPage "355" @default.
• W4311187170 abstract "Adaptive filtering algorithms are pervasive throughout signal processing and have had a material impact on a wide variety of domains including audio processing, telecommunications, biomedical sensing, astrophysics and cosmology, seismology, and many more. Adaptive filters typically operate via specialized online, iterative optimization methods such as least-mean squares or recursive least squares and aim to process signals in unknown or nonstationary environments. Such algorithms, however, can be slow and laborious to develop, require domain expertise to create, and necessitate mathematical insight for improvement. In this work, we seek to improve upon hand-derived adaptive filter algorithms and present a comprehensive framework for learning online, adaptive signal processing algorithms or update rules directly from data. To do so, we frame the development of adaptive filters as a meta-learning problem in the context of deep learning and use a form of self-supervision to learn online iterative update rules for adaptive filters. To demonstrate our approach, we focus on audio applications and systematically develop meta-learned adaptive filters for five canonical audio problems including system identification, acoustic echo cancellation, blind equalization, multi-channel dereverberation, and beamforming.We compare our approach against common baselines and/or recent state-of-the-art methods. We show we can learn high-performing adaptive filters that operate in real-time and, in most cases, significantly outperform each method we compare against – all using a single general-purpose configuration of our approach." @default.
• W4311187170 created "2022-12-24" @default.
• W4311187170 creator A5014125577 @default.
• W4311187170 creator A5038903729 @default.
• W4311187170 creator A5045694117 @default.
• W4311187170 date "2023-01-01" @default.
• W4311187170 modified "2023-10-01" @default.
• W4311187170 title "Meta-AF: Meta-Learning for Adaptive Filters" @default.
• W4311187170 cites W123803282 @default.
• W4311187170 cites W1527054173 @default.
• W4311187170 cites W1964934788 @default.
• W4311187170 cites W1969462564 @default.
• W4311187170 cites W1973524311 @default.
• W4311187170 cites W1983812858 @default.
• W4311187170 cites W2010352567 @default.
• W4311187170 cites W2023812473 @default.
• W4311187170 cites W2032676419 @default.
• W4311187170 cites W2037951967 @default.
• W4311187170 cites W2039003912 @default.
• W4311187170 cites W2065804682 @default.
• W4311187170 cites W2086381917 @default.
• W4311187170 cites W2089217417 @default.
• W4311187170 cites W2095711409 @default.
• W4311187170 cites W2098940131 @default.
• W4311187170 cites W2099984896 @default.
• W4311187170 cites W2101609516 @default.
• W4311187170 cites W2117090122 @default.
• W4311187170 cites W2118239006 @default.
• W4311187170 cites W2120020186 @default.
• W4311187170 cites W2126287638 @default.
• W4311187170 cites W2127851351 @default.
• W4311187170 cites W2129142203 @default.
• W4311187170 cites W2129629082 @default.
• W4311187170 cites W2141998673 @default.
• W4311187170 cites W2147154807 @default.
• W4311187170 cites W2150355110 @default.
• W4311187170 cites W2156746018 @default.
• W4311187170 cites W2158596240 @default.
• W4311187170 cites W2162393154 @default.
• W4311187170 cites W2164502538 @default.
• W4311187170 cites W2168729028 @default.
• W4311187170 cites W2168837669 @default.
• W4311187170 cites W2242685705 @default.
• W4311187170 cites W2289394825 @default.
• W4311187170 cites W2398042854 @default.
• W4311187170 cites W2517616541 @default.
• W4311187170 cites W2537124029 @default.
• W4311187170 cites W2559809918 @default.
• W4311187170 cites W2563063012 @default.
• W4311187170 cites W2568308529 @default.
• W4311187170 cites W2622203030 @default.
• W4311187170 cites W2696967604 @default.
• W4311187170 cites W2718043749 @default.
• W4311187170 cites W2747732471 @default.
• W4311187170 cites W2748661748 @default.
• W4311187170 cites W2767845480 @default.
• W4311187170 cites W2773129156 @default.
• W4311187170 cites W2889224938 @default.
• W4311187170 cites W2899625056 @default.
• W4311187170 cites W2937170468 @default.
• W4311187170 cites W2963177459 @default.
• W4311187170 cites W2973044449 @default.
• W4311187170 cites W2987188346 @default.
• W4311187170 cites W3030199831 @default.
• W4311187170 cites W3097284340 @default.
• W4311187170 cites W3113020185 @default.
• W4311187170 cites W3141042598 @default.
• W4311187170 cites W3160394811 @default.
• W4311187170 cites W3162341667 @default.
• W4311187170 cites W3162348042 @default.
• W4311187170 cites W3163136406 @default.
• W4311187170 cites W3163257865 @default.
• W4311187170 cites W3163485292 @default.
• W4311187170 cites W3195155284 @default.
• W4311187170 cites W3197000409 @default.
• W4311187170 cites W3198384207 @default.
• W4311187170 cites W3215005424 @default.
• W4311187170 cites W4205708476 @default.
• W4311187170 cites W4211264489 @default.
• W4311187170 cites W4225272224 @default.
• W4311187170 cites W4226134299 @default.
• W4311187170 doi "https://doi.org/10.1109/taslp.2022.3224288" @default.
• W4311187170 hasPublicationYear "2023" @default.
• W4311187170 type Work @default.
• W4311187170 citedByCount "4" @default.
• W4311187170 countsByYear W43111871702023 @default.
• W4311187170 crossrefType "journal-article" @default.
• W4311187170 hasAuthorship W4311187170A5014125577 @default.
• W4311187170 hasAuthorship W4311187170A5038903729 @default.
• W4311187170 hasAuthorship W4311187170A5045694117 @default.
• W4311187170 hasBestOaLocation W43111871701 @default.
• W4311187170 hasConcept C102248274 @default.
• W4311187170 hasConcept C104267543 @default.
• W4311187170 hasConcept C106131492 @default.
• W4311187170 hasConcept C11413529 @default.
• W4311187170 hasConcept C119857082 @default.
• W4311187170 hasConcept C125014702 @default.
• W4311187170 hasConcept C145249878 @default.

• next