Matches in SemOpenAlex for { <https://semopenalex.org/work/W3047125220> ?p ?o ?g. }
Showing items 1 to 97 of
97
with 100 items per page.
- W3047125220 abstract "Informed source separation has recently gained renewed interest with the introduction of neural networks and the availability of large multitrack datasets containing both the mixture and the separated sources. These approaches use prior information about the target source to improve separation. Historically, Music Information Retrieval researchers have focused primarily on score-informed source separation, but more recent approaches explore lyrics-informed source separation. However, because of the lack of multitrack datasets with time-aligned lyrics, models use weak conditioning with non-aligned lyrics. In this paper, we present a multimodal multitrack dataset with lyrics aligned in time at the word level with phonetic information as well as explore strong conditioning using the aligned phonemes. Our model follows a U-Net architecture and takes as input both the magnitude spectrogram of a musical mixture and a matrix with aligned phonetic information. The phoneme matrix is embedded to obtain the parameters that control Feature-wise Linear Modulation (FiLM) layers. These layers condition the U-Net feature maps to adapt the separation process to the presence of different phonemes via affine transformations. We show that phoneme conditioning can be successfully applied to improve singing voice source separation." @default.
- W3047125220 created "2020-08-10" @default.
- W3047125220 creator A5062693009 @default.
- W3047125220 creator A5063097936 @default.
- W3047125220 date "2020-10-15" @default.
- W3047125220 modified "2023-10-01" @default.
- W3047125220 title "CONTENT BASED SINGING VOICE SOURCE SEPARATION VIA STRONG CONDITIONING USING ALIGNED PHONEMES" @default.
- W3047125220 cites W1496920063 @default.
- W3047125220 cites W1716320828 @default.
- W3047125220 cites W1974186229 @default.
- W3047125220 cites W1979654135 @default.
- W3047125220 cites W2017548439 @default.
- W3047125220 cites W2108494558 @default.
- W3047125220 cites W2113217465 @default.
- W3047125220 cites W2127851351 @default.
- W3047125220 cites W2163922914 @default.
- W3047125220 cites W2407685581 @default.
- W3047125220 cites W2408688265 @default.
- W3047125220 cites W2560254426 @default.
- W3047125220 cites W2587994092 @default.
- W3047125220 cites W2669032454 @default.
- W3047125220 cites W2764251778 @default.
- W3047125220 cites W2774707525 @default.
- W3047125220 cites W2799258971 @default.
- W3047125220 cites W2847144333 @default.
- W3047125220 cites W2879390606 @default.
- W3047125220 cites W2898963093 @default.
- W3047125220 cites W2902796839 @default.
- W3047125220 cites W2906098386 @default.
- W3047125220 cites W2917340025 @default.
- W3047125220 cites W2938709889 @default.
- W3047125220 cites W2952218014 @default.
- W3047125220 cites W2962753171 @default.
- W3047125220 cites W2963406748 @default.
- W3047125220 cites W2963452667 @default.
- W3047125220 cites W2963921132 @default.
- W3047125220 cites W2963992487 @default.
- W3047125220 cites W2990666817 @default.
- W3047125220 cites W2991107219 @default.
- W3047125220 cites W2997987128 @default.
- W3047125220 cites W3006196360 @default.
- W3047125220 cites W3015225820 @default.
- W3047125220 cites W3015268063 @default.
- W3047125220 cites W3016156006 @default.
- W3047125220 cites W3016185664 @default.
- W3047125220 cites W3035014310 @default.
- W3047125220 cites W3165246035 @default.
- W3047125220 cites W2755129247 @default.
- W3047125220 hasPublicationYear "2020" @default.
- W3047125220 type Work @default.
- W3047125220 sameAs 3047125220 @default.
- W3047125220 citedByCount "0" @default.
- W3047125220 crossrefType "proceedings-article" @default.
- W3047125220 hasAuthorship W3047125220A5062693009 @default.
- W3047125220 hasAuthorship W3047125220A5063097936 @default.
- W3047125220 hasBestOaLocation W30471252201 @default.
- W3047125220 hasConcept C105795698 @default.
- W3047125220 hasConcept C119857082 @default.
- W3047125220 hasConcept C121332964 @default.
- W3047125220 hasConcept C24890656 @default.
- W3047125220 hasConcept C2776061190 @default.
- W3047125220 hasConcept C2776864781 @default.
- W3047125220 hasConcept C28490314 @default.
- W3047125220 hasConcept C33923547 @default.
- W3047125220 hasConcept C41008148 @default.
- W3047125220 hasConcept C44819458 @default.
- W3047125220 hasConcept C45262634 @default.
- W3047125220 hasConceptScore W3047125220C105795698 @default.
- W3047125220 hasConceptScore W3047125220C119857082 @default.
- W3047125220 hasConceptScore W3047125220C121332964 @default.
- W3047125220 hasConceptScore W3047125220C24890656 @default.
- W3047125220 hasConceptScore W3047125220C2776061190 @default.
- W3047125220 hasConceptScore W3047125220C2776864781 @default.
- W3047125220 hasConceptScore W3047125220C28490314 @default.
- W3047125220 hasConceptScore W3047125220C33923547 @default.
- W3047125220 hasConceptScore W3047125220C41008148 @default.
- W3047125220 hasConceptScore W3047125220C44819458 @default.
- W3047125220 hasConceptScore W3047125220C45262634 @default.
- W3047125220 hasLocation W30471252201 @default.
- W3047125220 hasLocation W30471252202 @default.
- W3047125220 hasLocation W30471252203 @default.
- W3047125220 hasOpenAccess W3047125220 @default.
- W3047125220 hasPrimaryLocation W30471252201 @default.
- W3047125220 hasRelatedWork W162634215 @default.
- W3047125220 hasRelatedWork W2296600244 @default.
- W3047125220 hasRelatedWork W2342978468 @default.
- W3047125220 hasRelatedWork W2402362233 @default.
- W3047125220 hasRelatedWork W2791336153 @default.
- W3047125220 hasRelatedWork W2938709889 @default.
- W3047125220 hasRelatedWork W2997975677 @default.
- W3047125220 hasRelatedWork W3155036195 @default.
- W3047125220 hasRelatedWork W4205247735 @default.
- W3047125220 hasRelatedWork W4309134657 @default.
- W3047125220 isParatext "false" @default.
- W3047125220 isRetracted "false" @default.
- W3047125220 magId "3047125220" @default.
- W3047125220 workType "article" @default.