Litcius/Paper detail

Toward Universal Text-To-Music Retrieval

SeungHeon Doh, Minz Won, Keunwoo Choi, Juhan Nam

202319 citationsDOI

Abstract

This paper introduces effective design choices for text-to-music retrieval systems. An ideal text-based retrieval system would support various input queries such as pre-defined tags, unseen tags, and sentence-level descriptions. In reality, most previous works mainly focused on a single query type (tag or sentence) which may not generalize to another input type. Hence, we review recent text-based music retrieval systems using our proposed benchmark in two main aspects: input text representation and training objectives. Our findings enable a universal text-to-music retrieval system that achieves comparable retrieval performances in both tag- and sentence-level inputs. Furthermore, the proposed multimodal representation generalizes to 9 different downstream music classification tasks. We present the code and demo online. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

Topics & Concepts

Computer scienceSentenceInformation retrievalText retrievalRepresentation (politics)Benchmark (surveying)Code (set theory)Natural language processingMusic information retrievalIdeal (ethics)Document retrievalArtificial intelligenceProgramming languageMusicalLawArtGeodesySet (abstract data type)PhilosophyGeographyEpistemologyVisual artsPoliticsPolitical scienceMusic and Audio ProcessingTopic ModelingNatural Language Processing Techniques