Matches in SemOpenAlex for { <https://semopenalex.org/work/W3097469673> ?p ?o ?g. }
- W3097469673 endingPage "836" @default.
- W3097469673 startingPage "828" @default.
- W3097469673 abstract "A major bottleneck in the evaluation of music generation is that music appreciation is a highly subjective matter. When considering an average appreciation as an evaluation metric, user studies can be helpful. The challenge of generating personalized content, however, has been examined only rarely in the literature. In this paper, we address generation of personalized music and propose a novel pipeline for music generation that learns and optimizes user-specific musical taste. We focus on the task of symbol-based, monophonic, harmony-constrained jazz improvisations. Our personalization pipeline begins with BebopNet, a music language model trained on a corpus of jazz improvisations by Bebop giants. BebopNet is able to generate improvisations based on any given chord progression. We then assemble a personalized dataset, labeled by a specific user, and train a user-specific metric that reflects this user's unique musical taste. Finally, we employ a personalized variant of beam-search with BebopNet to optimize the generated jazz improvisations for that user. We present an extensive empirical study in which we apply this pipeline to extract individual models as implicitly defined by several human listeners. Our approach enables an objective examination of subjective personalized models whose performance is quantifiable. The results indicate that it is possible to model and optimize personal jazz preferences and offer a foundation for future research in personalized generation of art. We also briefly discuss opportunities, challenges, and questions that arise from our work, including issues related to creativity." @default.
- W3097469673 created "2020-11-09" @default.
- W3097469673 creator A5004008495 @default.
- W3097469673 creator A5025669300 @default.
- W3097469673 creator A5037165507 @default.
- W3097469673 date "2020-10-11" @default.
- W3097469673 modified "2023-09-24" @default.
- W3097469673 title "BebopNet: Deep Neural Models for Personalized Jazz Improvisations." @default.
- W3097469673 cites W1563345886 @default.
- W3097469673 cites W183744577 @default.
- W3097469673 cites W1868569225 @default.
- W3097469673 cites W1976953209 @default.
- W3097469673 cites W2018587114 @default.
- W3097469673 cites W2034806191 @default.
- W3097469673 cites W2063485450 @default.
- W3097469673 cites W2064675550 @default.
- W3097469673 cites W2116064496 @default.
- W3097469673 cites W2169264582 @default.
- W3097469673 cites W2564034046 @default.
- W3097469673 cites W2746068898 @default.
- W3097469673 cites W2949382160 @default.
- W3097469673 cites W2951394837 @default.
- W3097469673 cites W2963088785 @default.
- W3097469673 cites W2963347649 @default.
- W3097469673 cites W2963403868 @default.
- W3097469673 cites W2963575853 @default.
- W3097469673 cites W2963985773 @default.
- W3097469673 cites W2964265128 @default.
- W3097469673 hasPublicationYear "2020" @default.
- W3097469673 type Work @default.
- W3097469673 sameAs 3097469673 @default.
- W3097469673 citedByCount "3" @default.
- W3097469673 countsByYear W30974696732020 @default.
- W3097469673 countsByYear W30974696732021 @default.
- W3097469673 crossrefType "proceedings-article" @default.
- W3097469673 hasAuthorship W3097469673A5004008495 @default.
- W3097469673 hasAuthorship W3097469673A5025669300 @default.
- W3097469673 hasAuthorship W3097469673A5037165507 @default.
- W3097469673 hasConcept C107457646 @default.
- W3097469673 hasConcept C11012388 @default.
- W3097469673 hasConcept C120314980 @default.
- W3097469673 hasConcept C136764020 @default.
- W3097469673 hasConcept C142362112 @default.
- W3097469673 hasConcept C153349607 @default.
- W3097469673 hasConcept C154945302 @default.
- W3097469673 hasConcept C17744445 @default.
- W3097469673 hasConcept C183003079 @default.
- W3097469673 hasConcept C194147245 @default.
- W3097469673 hasConcept C199360897 @default.
- W3097469673 hasConcept C199539241 @default.
- W3097469673 hasConcept C2980749 @default.
- W3097469673 hasConcept C41008148 @default.
- W3097469673 hasConcept C43521106 @default.
- W3097469673 hasConcept C47350684 @default.
- W3097469673 hasConcept C49774154 @default.
- W3097469673 hasConceptScore W3097469673C107457646 @default.
- W3097469673 hasConceptScore W3097469673C11012388 @default.
- W3097469673 hasConceptScore W3097469673C120314980 @default.
- W3097469673 hasConceptScore W3097469673C136764020 @default.
- W3097469673 hasConceptScore W3097469673C142362112 @default.
- W3097469673 hasConceptScore W3097469673C153349607 @default.
- W3097469673 hasConceptScore W3097469673C154945302 @default.
- W3097469673 hasConceptScore W3097469673C17744445 @default.
- W3097469673 hasConceptScore W3097469673C183003079 @default.
- W3097469673 hasConceptScore W3097469673C194147245 @default.
- W3097469673 hasConceptScore W3097469673C199360897 @default.
- W3097469673 hasConceptScore W3097469673C199539241 @default.
- W3097469673 hasConceptScore W3097469673C2980749 @default.
- W3097469673 hasConceptScore W3097469673C41008148 @default.
- W3097469673 hasConceptScore W3097469673C43521106 @default.
- W3097469673 hasConceptScore W3097469673C47350684 @default.
- W3097469673 hasConceptScore W3097469673C49774154 @default.
- W3097469673 hasLocation W30974696731 @default.
- W3097469673 hasOpenAccess W3097469673 @default.
- W3097469673 hasPrimaryLocation W30974696731 @default.
- W3097469673 hasRelatedWork W1024719787 @default.
- W3097469673 hasRelatedWork W1506221550 @default.
- W3097469673 hasRelatedWork W163326684 @default.
- W3097469673 hasRelatedWork W2010190193 @default.
- W3097469673 hasRelatedWork W2080640820 @default.
- W3097469673 hasRelatedWork W2488043602 @default.
- W3097469673 hasRelatedWork W2587897362 @default.
- W3097469673 hasRelatedWork W2618371569 @default.
- W3097469673 hasRelatedWork W2883088021 @default.
- W3097469673 hasRelatedWork W2904596301 @default.
- W3097469673 hasRelatedWork W2920065820 @default.
- W3097469673 hasRelatedWork W2977586069 @default.
- W3097469673 hasRelatedWork W3104194627 @default.
- W3097469673 hasRelatedWork W3130450715 @default.
- W3097469673 hasRelatedWork W3158472478 @default.
- W3097469673 hasRelatedWork W3162151557 @default.
- W3097469673 hasRelatedWork W3169481230 @default.
- W3097469673 hasRelatedWork W3173531154 @default.
- W3097469673 hasRelatedWork W3196710247 @default.
- W3097469673 hasRelatedWork W3205091761 @default.
- W3097469673 isParatext "false" @default.
- W3097469673 isRetracted "false" @default.
- W3097469673 magId "3097469673" @default.