Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386425034> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4386425034 endingPage "100254" @default.
- W4386425034 startingPage "100254" @default.
- W4386425034 abstract "This paper presents two systems for extracting the vocals from a musical piece. Vocals extraction finds extensive application in automated lyrics transcription, music information retrieval systems and professional music remixing. However, the current research is dominated by training-intensive models and has not exploited several promising architectures for appreciably accurate yet computationally inexpensive inference. Neural networks can be leveraged to understand the underlying mathematical patterns of human speech and its harmonic overtones as distinguished from those of instruments. A first principles approach behind two distinct model architectures as well as the data processing steps has been described. Semantic segmentation techniques are used to discriminate between the magnitude spectrogram of the vocals and the mixture which is then applied to the first CNN-based model. The second architecture uses gated recurrent units to leverage the unique temporal dependencies of human speech. This model directly performs inference on the entire spectrogram to concurrently learn the frequency distribution of both the vocals as well as the accompaniment. The second architecture is shown to be an improvement upon the first model and intermittently approaches state-of-the-art predictions on the MIR-1K dataset. The novel GRU-based system in particular highlights the feasibility of rapid inference with smaller datasets. These features play a significant role towards source separation research oriented towards the deployment of real-time inference systems." @default.
- W4386425034 created "2023-09-05" @default.
- W4386425034 creator A5004790060 @default.
- W4386425034 creator A5025891306 @default.
- W4386425034 date "2023-09-01" @default.
- W4386425034 modified "2023-10-14" @default.
- W4386425034 title "AUDIO SOURCE SEPARATION AS APPLIED TO VOCALS-ACCOMPANIMENT EXTRACTION" @default.
- W4386425034 cites W1790748249 @default.
- W4386425034 cites W1901129140 @default.
- W4386425034 cites W2037487247 @default.
- W4386425034 cites W2064675550 @default.
- W4386425034 cites W2124539664 @default.
- W4386425034 cites W2127851351 @default.
- W4386425034 cites W2157331557 @default.
- W4386425034 cites W2164098335 @default.
- W4386425034 cites W2292645603 @default.
- W4386425034 cites W2794209590 @default.
- W4386425034 cites W2902808043 @default.
- W4386425034 cites W2916985722 @default.
- W4386425034 cites W2962935966 @default.
- W4386425034 cites W2963723765 @default.
- W4386425034 cites W2964054038 @default.
- W4386425034 cites W2964199361 @default.
- W4386425034 cites W2972653970 @default.
- W4386425034 doi "https://doi.org/10.1016/j.prime.2023.100254" @default.
- W4386425034 hasPublicationYear "2023" @default.
- W4386425034 type Work @default.
- W4386425034 citedByCount "0" @default.
- W4386425034 crossrefType "journal-article" @default.
- W4386425034 hasAuthorship W4386425034A5004790060 @default.
- W4386425034 hasAuthorship W4386425034A5025891306 @default.
- W4386425034 hasBestOaLocation W43864250341 @default.
- W4386425034 hasConcept C119857082 @default.
- W4386425034 hasConcept C124952713 @default.
- W4386425034 hasConcept C142362112 @default.
- W4386425034 hasConcept C153180895 @default.
- W4386425034 hasConcept C154945302 @default.
- W4386425034 hasConcept C2776214188 @default.
- W4386425034 hasConcept C2776436406 @default.
- W4386425034 hasConcept C2776864781 @default.
- W4386425034 hasConcept C28490314 @default.
- W4386425034 hasConcept C41008148 @default.
- W4386425034 hasConcept C45273575 @default.
- W4386425034 hasConcept C89600930 @default.
- W4386425034 hasConceptScore W4386425034C119857082 @default.
- W4386425034 hasConceptScore W4386425034C124952713 @default.
- W4386425034 hasConceptScore W4386425034C142362112 @default.
- W4386425034 hasConceptScore W4386425034C153180895 @default.
- W4386425034 hasConceptScore W4386425034C154945302 @default.
- W4386425034 hasConceptScore W4386425034C2776214188 @default.
- W4386425034 hasConceptScore W4386425034C2776436406 @default.
- W4386425034 hasConceptScore W4386425034C2776864781 @default.
- W4386425034 hasConceptScore W4386425034C28490314 @default.
- W4386425034 hasConceptScore W4386425034C41008148 @default.
- W4386425034 hasConceptScore W4386425034C45273575 @default.
- W4386425034 hasConceptScore W4386425034C89600930 @default.
- W4386425034 hasLocation W43864250341 @default.
- W4386425034 hasOpenAccess W4386425034 @default.
- W4386425034 hasPrimaryLocation W43864250341 @default.
- W4386425034 hasRelatedWork W1488912948 @default.
- W4386425034 hasRelatedWork W1965243342 @default.
- W4386425034 hasRelatedWork W2037487247 @default.
- W4386425034 hasRelatedWork W2152457943 @default.
- W4386425034 hasRelatedWork W2159898352 @default.
- W4386425034 hasRelatedWork W2408298504 @default.
- W4386425034 hasRelatedWork W2558565288 @default.
- W4386425034 hasRelatedWork W2997975677 @default.
- W4386425034 hasRelatedWork W3000647100 @default.
- W4386425034 hasRelatedWork W3120099295 @default.
- W4386425034 isParatext "false" @default.
- W4386425034 isRetracted "false" @default.
- W4386425034 workType "article" @default.