Matches in SemOpenAlex for { <https://semopenalex.org/work/W2620021285> ?p ?o ?g. }
- W2620021285 abstract "Automatic music transcription is usually approached by using a time-frequency (TF) representation such as the short-time Fourier transform (STFT) spectrogram or the constant-Q transform. In this paper, we propose a novel yet simple TF representation that capitalizes the effectiveness of spectral flux features in highlighting note onset times. We refer to this representation as the differential spectrogram and investigate its usefulness for note-level piano transcription using two different non-negative matrix factorization (NMF) algorithms. Experiments on the MAPS ENSTDkCl dataset validate the advantages of the differential spectrogram over the STFT spectrogram for this task. Moreover, by adapting a state-of-the-art convolutional NMF algorithm with the differential spectrogram, we can achieve even better accuracy than the state-of-the-art on this dataset. Our analysis shows that the new representation suppresses unwanted TF patterns and performs particularly well in improving the recall rate." @default.
- W2620021285 created "2017-06-05" @default.
- W2620021285 creator A5001795601 @default.
- W2620021285 creator A5038264558 @default.
- W2620021285 creator A5056645597 @default.
- W2620021285 creator A5061291906 @default.
- W2620021285 date "2017-03-01" @default.
- W2620021285 modified "2023-09-22" @default.
- W2620021285 title "Polyphonic piano note transcription with non-negative matrix factorization of differential spectrogram" @default.
- W2620021285 cites W13237084 @default.
- W2620021285 cites W173399573 @default.
- W2620021285 cites W2017578549 @default.
- W2620021285 cites W2054770976 @default.
- W2620021285 cites W2055356414 @default.
- W2620021285 cites W2096354165 @default.
- W2620021285 cites W2096482524 @default.
- W2620021285 cites W2104298926 @default.
- W2620021285 cites W2104484487 @default.
- W2620021285 cites W2110007838 @default.
- W2620021285 cites W2124149378 @default.
- W2620021285 cites W2129638017 @default.
- W2620021285 cites W2144414181 @default.
- W2620021285 cites W2148899569 @default.
- W2620021285 cites W2150415460 @default.
- W2620021285 cites W2152937398 @default.
- W2620021285 cites W2158983491 @default.
- W2620021285 cites W2188829427 @default.
- W2620021285 cites W2295460171 @default.
- W2620021285 cites W2403393451 @default.
- W2620021285 cites W2531457347 @default.
- W2620021285 cites W89231944 @default.
- W2620021285 cites W97505134 @default.
- W2620021285 doi "https://doi.org/10.1109/icassp.2017.7952164" @default.
- W2620021285 hasPublicationYear "2017" @default.
- W2620021285 type Work @default.
- W2620021285 sameAs 2620021285 @default.
- W2620021285 citedByCount "5" @default.
- W2620021285 countsByYear W26200212852017 @default.
- W2620021285 countsByYear W26200212852018 @default.
- W2620021285 countsByYear W26200212852019 @default.
- W2620021285 countsByYear W26200212852020 @default.
- W2620021285 crossrefType "proceedings-article" @default.
- W2620021285 hasAuthorship W2620021285A5001795601 @default.
- W2620021285 hasAuthorship W2620021285A5038264558 @default.
- W2620021285 hasAuthorship W2620021285A5056645597 @default.
- W2620021285 hasAuthorship W2620021285A5061291906 @default.
- W2620021285 hasConcept C102519508 @default.
- W2620021285 hasConcept C106131492 @default.
- W2620021285 hasConcept C121332964 @default.
- W2620021285 hasConcept C134306372 @default.
- W2620021285 hasConcept C138885662 @default.
- W2620021285 hasConcept C142433447 @default.
- W2620021285 hasConcept C152671427 @default.
- W2620021285 hasConcept C153180895 @default.
- W2620021285 hasConcept C154945302 @default.
- W2620021285 hasConcept C158693339 @default.
- W2620021285 hasConcept C166386157 @default.
- W2620021285 hasConcept C179926584 @default.
- W2620021285 hasConcept C203024314 @default.
- W2620021285 hasConcept C28490314 @default.
- W2620021285 hasConcept C31972630 @default.
- W2620021285 hasConcept C33923547 @default.
- W2620021285 hasConcept C41008148 @default.
- W2620021285 hasConcept C41895202 @default.
- W2620021285 hasConcept C42355184 @default.
- W2620021285 hasConcept C45273575 @default.
- W2620021285 hasConcept C62520636 @default.
- W2620021285 hasConceptScore W2620021285C102519508 @default.
- W2620021285 hasConceptScore W2620021285C106131492 @default.
- W2620021285 hasConceptScore W2620021285C121332964 @default.
- W2620021285 hasConceptScore W2620021285C134306372 @default.
- W2620021285 hasConceptScore W2620021285C138885662 @default.
- W2620021285 hasConceptScore W2620021285C142433447 @default.
- W2620021285 hasConceptScore W2620021285C152671427 @default.
- W2620021285 hasConceptScore W2620021285C153180895 @default.
- W2620021285 hasConceptScore W2620021285C154945302 @default.
- W2620021285 hasConceptScore W2620021285C158693339 @default.
- W2620021285 hasConceptScore W2620021285C166386157 @default.
- W2620021285 hasConceptScore W2620021285C179926584 @default.
- W2620021285 hasConceptScore W2620021285C203024314 @default.
- W2620021285 hasConceptScore W2620021285C28490314 @default.
- W2620021285 hasConceptScore W2620021285C31972630 @default.
- W2620021285 hasConceptScore W2620021285C33923547 @default.
- W2620021285 hasConceptScore W2620021285C41008148 @default.
- W2620021285 hasConceptScore W2620021285C41895202 @default.
- W2620021285 hasConceptScore W2620021285C42355184 @default.
- W2620021285 hasConceptScore W2620021285C45273575 @default.
- W2620021285 hasConceptScore W2620021285C62520636 @default.
- W2620021285 hasLocation W26200212851 @default.
- W2620021285 hasOpenAccess W2620021285 @default.
- W2620021285 hasPrimaryLocation W26200212851 @default.
- W2620021285 hasRelatedWork W1987463951 @default.
- W2620021285 hasRelatedWork W2110007838 @default.
- W2620021285 hasRelatedWork W2115158120 @default.
- W2620021285 hasRelatedWork W2139153330 @default.
- W2620021285 hasRelatedWork W2294938120 @default.
- W2620021285 hasRelatedWork W2295104115 @default.
- W2620021285 hasRelatedWork W2296659092 @default.
- W2620021285 hasRelatedWork W2521227201 @default.
- W2620021285 hasRelatedWork W2617524636 @default.