{"id":"https://openalex.org/W7133356446","doi":"https://doi.org/10.1145/3742413.3789072","title":"Visual Lyrics: Generating Animated Text for Music Lyric Videos with an Augmented Text Editor","display_name":"Visual Lyrics: Generating Animated Text for Music Lyric Videos with an Augmented Text Editor","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133356446","doi":"https://doi.org/10.1145/3742413.3789072"},"language":null,"primary_location":{"id":"doi:10.1145/3742413.3789072","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742413.3789072","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3742413.3789072","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000156461","display_name":"David Chuan-En Lin","orcid":"https://orcid.org/0000-0003-0116-0463"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"David Chuan-En Lin","raw_affiliation_strings":["Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"raw_orcid":"https://orcid.org/0000-0003-0116-0463","affiliations":[{"raw_affiliation_string":"Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027672529","display_name":"Cuong Nguyen","orcid":"https://orcid.org/0000-0001-9234-9960"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cuong Nguyen","raw_affiliation_strings":["Adobe Research, San Francisco, California, USA"],"raw_orcid":"https://orcid.org/0000-0001-9234-9960","affiliations":[{"raw_affiliation_string":"Adobe Research, San Francisco, California, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037455703","display_name":"Hijung Valentina Shin","orcid":"https://orcid.org/0000-0001-8798-4580"},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hijung Valentina Shin","raw_affiliation_strings":["Adobe Research, Cambridge, Massachusetts, USA"],"raw_orcid":"https://orcid.org/0000-0001-8798-4580","affiliations":[{"raw_affiliation_string":"Adobe Research, Cambridge, Massachusetts, USA","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075763217","display_name":"Nikolas Martelaro","orcid":"https://orcid.org/0000-0002-1824-0243"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolas Martelaro","raw_affiliation_strings":["Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA"],"raw_orcid":"https://orcid.org/0000-0002-1824-0243","affiliations":[{"raw_affiliation_string":"Human-Computer Interaction Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000156461"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40847115,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1514","last_page":"1525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.5131999850273132,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11574","display_name":"Artificial Intelligence in Games","score":0.5131999850273132,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12290","display_name":"Human Motion and Animation","score":0.1469999998807907,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.026000000536441803,"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":0.6898000240325928},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5983999967575073},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5569000244140625},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.4927000105381012},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.44859999418258667},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.39879998564720154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7943999767303467},{"id":"https://openalex.org/C2776436406","wikidata":"https://www.wikidata.org/wiki/Q602446","display_name":"Lyrics","level":2,"score":0.6898000240325928},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5983999967575073},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5569000244140625},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.39879998564720154},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39480000734329224},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3732999861240387},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27900001406669617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2759999930858612},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C15724806","wikidata":"https://www.wikidata.org/wiki/Q185925","display_name":"Graphic design","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C41022531","wikidata":"https://www.wikidata.org/wiki/Q333657","display_name":"Communication design","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3742413.3789072","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742413.3789072","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3742413.3789072","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3742413.3789072","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st International Conference on Intelligent User Interfaces","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1997249373","https://openalex.org/W2001642682","https://openalex.org/W2005872581","https://openalex.org/W2030626427","https://openalex.org/W2070869225","https://openalex.org/W2081211779","https://openalex.org/W2087641817","https://openalex.org/W2090625014","https://openalex.org/W2091425152","https://openalex.org/W2114779318","https://openalex.org/W2122532446","https://openalex.org/W2134387846","https://openalex.org/W2167196792","https://openalex.org/W2191779130","https://openalex.org/W2586846154","https://openalex.org/W2795274753","https://openalex.org/W3037149862","https://openalex.org/W4366547544","https://openalex.org/W4385822293","https://openalex.org/W4385945128","https://openalex.org/W4386302151","https://openalex.org/W4388009985","https://openalex.org/W4390874209","https://openalex.org/W4402727764","https://openalex.org/W7133233106"],"related_works":[],"abstract_inverted_index":{"Animated":[0],"lyric":[1,54,66,148],"videos":[2,23,55,67,149],"transform":[3],"song":[4],"lyrics":[5],"into":[6],"dynamic":[7],"visual":[8],"experiences,":[9],"offering":[10],"a":[11,48,70,85,114,136],"powerful":[12],"medium":[13],"for":[14,51,127],"artistic":[15],"expression":[16],"and":[17,33,72,94,101,108,156],"audience":[18],"engagement.":[19],"However,":[20],"creating":[21],"these":[22],"is":[24,84],"challenging,":[25],"requiring":[26],"expertise":[27],"in":[28],"audio,":[29],"typography,":[30],"graphic":[31],"design,":[32],"animation,":[34],"making":[35],"it":[36],"inaccessible":[37],"to":[38,68,105,123,143],"novices.":[39],"To":[40],"address":[41],"this":[42],"challenge,":[43],"we":[44,132],"introduce":[45],"Visual":[46,79,139],"Lyrics,":[47],"proof-of-concept":[49],"system":[50],"generating":[52],"animated":[53,147],"controlled":[56],"with":[57,150],"an":[58],"augmented":[59],"text":[60,121],"editor":[61],"interface.":[62],"We":[63,112],"examined":[64],"existing":[65],"distill":[69],"taxonomy":[71,93],"design":[73,77],"guidelines,":[74],"informing":[75],"the":[76,92],"of":[78,116,153],"Lyrics.":[80],"Our":[81],"key":[82],"insight":[83],"multimodal":[86],"music":[87],"analysis":[88],"pipeline":[89],"based":[90],"on":[91],"leveraging":[95],"LLM\u2019s":[96],"strong":[97],"natural":[98],"language":[99],"understanding":[100],"code":[102],"generation":[103],"capabilities":[104],"synthesize":[106],"creative":[107,120],"semantically":[109],"meaningful":[110],"animations.":[111],"collected":[113],"dataset":[115],"over":[117],"300":[118],"code-driven":[119],"animations":[122],"serve":[124],"as":[125],"inspiration":[126],"our":[128],"LLM-driven":[129],"pipeline,":[130],"which":[131],"open":[133],"source.":[134],"In":[135],"user":[137],"study,":[138],"Lyrics":[140],"enabled":[141],"novices":[142],"easily":[144],"create":[145],"high-quality":[146],"high":[151],"ratings":[152],"enjoyment,":[154],"inspiration,":[155],"exploration.":[157]},"counts_by_year":[],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2026-03-04T00:00:00"}
