{"id":"https://openalex.org/W4392909390","doi":"https://doi.org/10.1109/icassp48485.2024.10447027","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","display_name":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909390","doi":"https://doi.org/10.1109/icassp48485.2024.10447027"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066070154","display_name":"Shansong Liu","orcid":"https://orcid.org/0000-0001-6202-5615"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shansong Liu","raw_affiliation_strings":["Tencent PCG,ARC Lab","ARC Lab, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"Tencent PCG,ARC Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039165844","display_name":"Atin Sakkeer Hussain","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Atin Sakkeer Hussain","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075627636","display_name":"Chenshuo Sun","orcid":"https://orcid.org/0000-0001-7708-2671"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chenshuo Sun","raw_affiliation_strings":["National University of Singapore"],"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102004349","display_name":"Ying Shan","orcid":"https://orcid.org/0000-0001-7673-8325"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Shan","raw_affiliation_strings":["Tencent PCG,ARC Lab","ARC Lab, Tencent PCG"],"affiliations":[{"raw_affiliation_string":"Tencent PCG,ARC Lab","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"ARC Lab, Tencent PCG","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066070154"],"corresponding_institution_ids":["https://openalex.org/I2250653659"],"apc_list":null,"apc_paid":null,"fwci":7.947,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.98197912,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"286","last_page":"290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9890000224113464,"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/T10028","display_name":"Topic Modeling","score":0.973800003528595,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.8394982218742371},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6857435703277588},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.529364824295044},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47377753257751465},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41308891773223877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3479394316673279}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8394982218742371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6857435703277588},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.529364824295044},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47377753257751465},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41308891773223877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3479394316673279},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447027","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447027","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W2154652894","https://openalex.org/W2936695845","https://openalex.org/W2939574508","https://openalex.org/W2950060770","https://openalex.org/W3180663620","https://openalex.org/W3185739472","https://openalex.org/W3201326582","https://openalex.org/W4226358929","https://openalex.org/W4284898017","https://openalex.org/W4287802874","https://openalex.org/W4292794290","https://openalex.org/W4318351475","https://openalex.org/W4322718191","https://openalex.org/W4361229539","https://openalex.org/W4367628410","https://openalex.org/W4372260310","https://openalex.org/W4377130946","https://openalex.org/W4379251869","https://openalex.org/W4380136719","https://openalex.org/W4384918448","https://openalex.org/W4385474092","https://openalex.org/W4386071707","https://openalex.org/W6678262379","https://openalex.org/W6678969435","https://openalex.org/W6682631176","https://openalex.org/W6761205521","https://openalex.org/W6763945542","https://openalex.org/W6776218486","https://openalex.org/W6791353385","https://openalex.org/W6798597329","https://openalex.org/W6798955355","https://openalex.org/W6811051256","https://openalex.org/W6849105126","https://openalex.org/W6849517043","https://openalex.org/W6850625674","https://openalex.org/W6851948999","https://openalex.org/W6852489829","https://openalex.org/W6853096648","https://openalex.org/W6853249747","https://openalex.org/W6853393314","https://openalex.org/W6854866820","https://openalex.org/W6855932524","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Text-to-music":[0],"generation":[1,138],"(T2M-Gen)":[2],"faces":[3],"a":[4,48,58,91,152],"major":[5],"obstacle":[6],"due":[7],"to":[8,52],"the":[9,26,63,77,104,117,156],"scarcity":[10],"of":[11,32],"large-scale":[12],"publicly":[13,70],"available":[14],"music":[15,40,54,82,132,136],"datasets":[16,75,101],"with":[17],"natural":[18],"language":[19],"captions.":[20],"To":[21,85],"address":[22],"this,":[23],"we":[24,89],"propose":[25],"Music":[27],"Understanding":[28],"LLaMA":[29],"(MU-LLaMA),":[30],"capable":[31],"answering":[33,74,109,134],"music-related":[34,111],"questions":[35],"and":[36,102,135,150],"generating":[37,94],"captions":[38],"for":[39,61,80,93,108],"files.":[41],"Our":[42],"model":[43,51,65],"utilizes":[44],"audio":[45,72,99],"representations":[46],"from":[47,97],"pretrained":[49],"MERT":[50],"extract":[53],"features.":[55],"However,":[56],"obtaining":[57],"suitable":[59],"dataset":[60],"training":[62],"MU-LLaMA":[64,119],"remains":[66],"challenging,":[67],"as":[68],"existing":[69,98],"accessible":[71],"question":[73,83,133],"lack":[76],"necessary":[78],"depth":[79],"open-ended":[81,110],"answering.":[84],"fill":[86],"this":[87],"gap,":[88],"present":[90],"methodology":[92],"question-answer":[95],"pairs":[96],"captioning":[100],"introduce":[103],"MusicQA":[105,125],"Dataset":[106],"designed":[107,124],"questions.":[112],"The":[113],"experiments":[114],"demonstrate":[115],"that":[116],"proposed":[118],"model,":[120],"trained":[121],"on":[122],"our":[123],"dataset,":[126],"achieves":[127],"outstanding":[128],"performance":[129],"in":[130,147,155],"both":[131,148],"caption":[137],"across":[139],"various":[140],"metrics,":[141],"outperforming":[142],"current":[143],"state-of-the-art":[144],"(SOTA)":[145],"models":[146],"fields":[149],"offering":[151],"promising":[153],"advancement":[154],"T2M-Gen":[157],"research":[158],"field.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}