{"id":"https://openalex.org/W3206128255","doi":"https://doi.org/10.1145/3478384.3478420","title":"Visualyre: Multimodal visualization of lyrics","display_name":"Visualyre: Multimodal visualization of lyrics","publication_year":2021,"publication_date":"2021-09-01","ids":{"openalex":"https://openalex.org/W3206128255","doi":"https://doi.org/10.1145/3478384.3478420","mag":"3206128255"},"language":"en","primary_location":{"id":"doi:10.1145/3478384.3478420","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3478384.3478420","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3478384.3478420","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Audio Mostly 2021","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3478384.3478420","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070064590","display_name":"Gamar Azuaje","orcid":"https://orcid.org/0000-0003-2247-6766"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Gamar Azuaje","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102771978","display_name":"Kongmeng Liew","orcid":"https://orcid.org/0000-0002-0755-7173"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kongmeng Liew","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077407955","display_name":"Elena V. Epure","orcid":"https://orcid.org/0000-0002-6930-9482"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Elena Epure","raw_affiliation_strings":["Deezer, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Deezer, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005540314","display_name":"Shuntaro Yada","orcid":"https://orcid.org/0000-0002-6209-1054"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shuntaro Yada","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046718849","display_name":"Shoko Wakamiya","orcid":"https://orcid.org/0000-0002-9371-1340"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Wakamiya","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041089475","display_name":"Eiji Aramaki","orcid":"https://orcid.org/0000-0003-0201-3609"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Eiji Aramaki","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13436433,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"130","last_page":"134"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/lyrics","display_name":"Lyrics","score":0.9599412679672241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7339838147163391},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5815333127975464},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5693607330322266},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4966478943824768},{"id":"https://openalex.org/keywords/mood","display_name":"Mood","score":0.4249486029148102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3505520820617676},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3375791907310486},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3339619040489197},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.33013492822647095},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.17876315116882324},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0859617292881012},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08563357591629028},{"id":"https://openalex.org/keywords/literature","display_name":"Literature","score":0.07820549607276917}],"concepts":[{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.9599412679672241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7339838147163391},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5815333127975464},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5693607330322266},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4966478943824768},{"id":"https://openalex.org/C2780733359","wikidata":"https://www.wikidata.org/wiki/Q331769","display_name":"Mood","level":2,"score":0.4249486029148102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3505520820617676},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3375791907310486},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3339619040489197},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.33013492822647095},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.17876315116882324},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0859617292881012},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08563357591629028},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.07820549607276917},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3478384.3478420","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3478384.3478420","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3478384.3478420","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Audio Mostly 2021","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3478384.3478420","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3478384.3478420","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3478384.3478420","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Audio Mostly 2021","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3206128255.pdf","grobid_xml":"https://content.openalex.org/works/W3206128255.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1885185971","https://openalex.org/W1924619199","https://openalex.org/W2085421468","https://openalex.org/W2107312542","https://openalex.org/W2160464472","https://openalex.org/W2276253945","https://openalex.org/W2293645955","https://openalex.org/W2339754110","https://openalex.org/W2518685123","https://openalex.org/W2912500072","https://openalex.org/W2963525668","https://openalex.org/W2963966654","https://openalex.org/W2964216930","https://openalex.org/W2966792645","https://openalex.org/W3015310419"],"related_works":["https://openalex.org/W2360952181","https://openalex.org/W4310670065","https://openalex.org/W2597614303","https://openalex.org/W634160686","https://openalex.org/W3214861561","https://openalex.org/W2389838651","https://openalex.org/W437317580","https://openalex.org/W2352995288","https://openalex.org/W2365365224","https://openalex.org/W1532663766"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"Visualyre,":[5],"a":[6,27,34,43,47,71],"web":[7],"application":[8],"that":[9],"synthesizes":[10],"images":[11,32,80],"based":[12],"on":[13],"the":[14,17,20,23,39,53,56,64,90,99],"semantics":[15],"of":[16,22,42,55,93],"lyrics,":[18],"and":[19,75],"mood":[21,54],"music.":[24],"We":[25,88],"use":[26],"multimodal":[28],"approach,":[29],"generating":[30],"initial":[31],"with":[33],"text-to-image":[35],"generative":[36],"models":[37],"from":[38],"lyrics":[40],"(text)":[41],"song,":[44],"followed":[45],"by":[46,69],"style":[48],"transfer":[49],"model":[50],"conditioned":[51],"to":[52,77],"music":[57,66,83],"(audio).":[58],"Our":[59],"target":[60],"user":[61],"base":[62],"is":[63],"independent":[65],"artist":[67],"community,":[68],"providing":[70],"means":[72],"for":[73,81],"composers":[74],"songwriters":[76],"generate":[78],"suitable":[79],"their":[82],"(such":[84],"as":[85,96,98],"album":[86],"covers).":[87],"discuss":[89],"possible":[91,100],"usage":[92],"such":[94],"application,":[95],"well":[97],"improvements":[101],"in":[102],"future":[103],"iterations.":[104]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
