Matches in SemOpenAlex for { <https://semopenalex.org/work/W2714701844> ?p ?o ?g. }
- W2714701844 abstract "This paper presents a new approach in understanding how deep neural networks (DNNs) work by applying homomorphic signal processing techniques. Focusing on the task of multi-pitch estimation (MPE), this paper demonstrates the equivalence relation between a generalized cepstrum and a DNN in terms of their structures and functionality. Such an equivalence relation, together with pitch perception theories and the recently established rectified-correlations-on-a-sphere (RECOS) filter analysis, provide an alternative way in explaining the role of the nonlinear activation function and the multi-layer structure, both of which exist in a cepstrum and a DNN. To validate the efficacy of this new approach, a new feature designed in the same fashion is proposed for pitch salience function. The new feature outperforms the one-layer spectrum in the MPE task and, as predicted, it addresses the issue of the missing fundamental effect and also achieves better robustness to noise." @default.
- W2714701844 created "2017-06-30" @default.
- W2714701844 creator A5038264558 @default.
- W2714701844 date "2017-06-26" @default.
- W2714701844 modified "2023-10-16" @default.
- W2714701844 title "Between Homomorphic Signal Processing and Deep Neural Networks: Constructing Deep Algorithms for Polyphonic Music Transcription" @default.
- W2714701844 cites W1732796048 @default.
- W2714701844 cites W1752772649 @default.
- W2714701844 cites W1787224781 @default.
- W2714701844 cites W1890000358 @default.
- W2714701844 cites W1936878994 @default.
- W2714701844 cites W1967488024 @default.
- W2714701844 cites W1970825018 @default.
- W2714701844 cites W2001426554 @default.
- W2714701844 cites W2005608041 @default.
- W2714701844 cites W2029654180 @default.
- W2714701844 cites W2034300186 @default.
- W2714701844 cites W2046788756 @default.
- W2714701844 cites W2055356414 @default.
- W2714701844 cites W2059260101 @default.
- W2714701844 cites W2088632109 @default.
- W2714701844 cites W2091425152 @default.
- W2714701844 cites W2096482524 @default.
- W2714701844 cites W2100050692 @default.
- W2714701844 cites W2105143211 @default.
- W2714701844 cites W2105343238 @default.
- W2714701844 cites W2109770219 @default.
- W2714701844 cites W2110007838 @default.
- W2714701844 cites W2114377386 @default.
- W2714701844 cites W2124340044 @default.
- W2714701844 cites W2141628940 @default.
- W2714701844 cites W2148899569 @default.
- W2714701844 cites W2149180301 @default.
- W2714701844 cites W2155208345 @default.
- W2714701844 cites W2163632146 @default.
- W2714701844 cites W2195388612 @default.
- W2714701844 cites W2196920785 @default.
- W2714701844 cites W2198584637 @default.
- W2714701844 cites W2293113641 @default.
- W2714701844 cites W2395687989 @default.
- W2714701844 cites W2398618787 @default.
- W2714701844 cites W2494437503 @default.
- W2714701844 cites W2516301810 @default.
- W2714701844 cites W2519796145 @default.
- W2714701844 cites W2575864022 @default.
- W2714701844 cites W2608422103 @default.
- W2714701844 cites W2950335938 @default.
- W2714701844 cites W2962845550 @default.
- W2714701844 cites W3006759111 @default.
- W2714701844 cites W2242076280 @default.
- W2714701844 doi "https://doi.org/10.48550/arxiv.1706.08231" @default.
- W2714701844 hasPublicationYear "2017" @default.
- W2714701844 type Work @default.
- W2714701844 sameAs 2714701844 @default.
- W2714701844 citedByCount "1" @default.
- W2714701844 countsByYear W27147018442018 @default.
- W2714701844 crossrefType "posted-content" @default.
- W2714701844 hasAuthorship W2714701844A5038264558 @default.
- W2714701844 hasBestOaLocation W27147018441 @default.
- W2714701844 hasConcept C104317684 @default.
- W2714701844 hasConcept C108154423 @default.
- W2714701844 hasConcept C108583219 @default.
- W2714701844 hasConcept C11413529 @default.
- W2714701844 hasConcept C153180895 @default.
- W2714701844 hasConcept C154945302 @default.
- W2714701844 hasConcept C156103551 @default.
- W2714701844 hasConcept C185592680 @default.
- W2714701844 hasConcept C202444582 @default.
- W2714701844 hasConcept C28490314 @default.
- W2714701844 hasConcept C33923547 @default.
- W2714701844 hasConcept C41008148 @default.
- W2714701844 hasConcept C45273575 @default.
- W2714701844 hasConcept C50644808 @default.
- W2714701844 hasConcept C55493867 @default.
- W2714701844 hasConcept C63479239 @default.
- W2714701844 hasConcept C88485024 @default.
- W2714701844 hasConceptScore W2714701844C104317684 @default.
- W2714701844 hasConceptScore W2714701844C108154423 @default.
- W2714701844 hasConceptScore W2714701844C108583219 @default.
- W2714701844 hasConceptScore W2714701844C11413529 @default.
- W2714701844 hasConceptScore W2714701844C153180895 @default.
- W2714701844 hasConceptScore W2714701844C154945302 @default.
- W2714701844 hasConceptScore W2714701844C156103551 @default.
- W2714701844 hasConceptScore W2714701844C185592680 @default.
- W2714701844 hasConceptScore W2714701844C202444582 @default.
- W2714701844 hasConceptScore W2714701844C28490314 @default.
- W2714701844 hasConceptScore W2714701844C33923547 @default.
- W2714701844 hasConceptScore W2714701844C41008148 @default.
- W2714701844 hasConceptScore W2714701844C45273575 @default.
- W2714701844 hasConceptScore W2714701844C50644808 @default.
- W2714701844 hasConceptScore W2714701844C55493867 @default.
- W2714701844 hasConceptScore W2714701844C63479239 @default.
- W2714701844 hasConceptScore W2714701844C88485024 @default.
- W2714701844 hasLocation W27147018441 @default.
- W2714701844 hasOpenAccess W2714701844 @default.
- W2714701844 hasPrimaryLocation W27147018441 @default.
- W2714701844 hasRelatedWork W106160982 @default.
- W2714701844 hasRelatedWork W2467586369 @default.
- W2714701844 hasRelatedWork W2714701844 @default.
- W2714701844 hasRelatedWork W2773120646 @default.