{"id":"https://openalex.org/W4392902968","doi":"https://doi.org/10.1109/icassp48485.2024.10446643","title":"Generating Stereophonic Music with Single-Stage Language Models","display_name":"Generating Stereophonic Music with Single-Stage Language Models","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902968","doi":"https://doi.org/10.1109/icassp48485.2024.10446643"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446643","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446643","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/A5071579165","display_name":"Xingda Li","orcid":null},"institutions":[{"id":"https://openalex.org/I53486688","display_name":"Skyworks Solutions (United States)","ror":"https://ror.org/02jymes45","country_code":"US","type":"company","lineage":["https://openalex.org/I53486688"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xingda Li","raw_affiliation_strings":["Skywork AI PTE. LTD"],"affiliations":[{"raw_affiliation_string":"Skywork AI PTE. LTD","institution_ids":["https://openalex.org/I53486688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101036892","display_name":"Fan Zhuo","orcid":"https://orcid.org/0009-0009-2324-0975"},"institutions":[{"id":"https://openalex.org/I53486688","display_name":"Skyworks Solutions (United States)","ror":"https://ror.org/02jymes45","country_code":"US","type":"company","lineage":["https://openalex.org/I53486688"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan Zhuo","raw_affiliation_strings":["Skywork AI PTE. LTD"],"affiliations":[{"raw_affiliation_string":"Skywork AI PTE. LTD","institution_ids":["https://openalex.org/I53486688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100632528","display_name":"Dan Luo","orcid":"https://orcid.org/0000-0002-7555-0045"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Luo","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022275946","display_name":"Jun Chen","orcid":"https://orcid.org/0000-0002-1966-0063"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Chen","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083463839","display_name":"Shiyin Kang","orcid":"https://orcid.org/0000-0001-8304-5260"},"institutions":[{"id":"https://openalex.org/I53486688","display_name":"Skyworks Solutions (United States)","ror":"https://ror.org/02jymes45","country_code":"US","type":"company","lineage":["https://openalex.org/I53486688"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiyin Kang","raw_affiliation_strings":["Skywork AI PTE. LTD"],"affiliations":[{"raw_affiliation_string":"Skywork AI PTE. LTD","institution_ids":["https://openalex.org/I53486688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"institutions":[{"id":"https://openalex.org/I3131625388","display_name":"University Town of Shenzhen","ror":"https://ror.org/05f5j6225","country_code":"CN","type":"education","lineage":["https://openalex.org/I3131625388"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I3131625388","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100744501","display_name":"Tao Jiang","orcid":"https://orcid.org/0000-0001-9116-2635"},"institutions":[{"id":"https://openalex.org/I53486688","display_name":"Skyworks Solutions (United States)","ror":"https://ror.org/02jymes45","country_code":"US","type":"company","lineage":["https://openalex.org/I53486688"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Jiang","raw_affiliation_strings":["Skywork AI PTE. LTD"],"affiliations":[{"raw_affiliation_string":"Skywork AI PTE. LTD","institution_ids":["https://openalex.org/I53486688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101711789","display_name":"Yang Li","orcid":"https://orcid.org/0000-0003-1784-6638"},"institutions":[{"id":"https://openalex.org/I53486688","display_name":"Skyworks Solutions (United States)","ror":"https://ror.org/02jymes45","country_code":"US","type":"company","lineage":["https://openalex.org/I53486688"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["Skywork AI PTE. LTD"],"affiliations":[{"raw_affiliation_string":"Skywork AI PTE. LTD","institution_ids":["https://openalex.org/I53486688"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Han Fang","orcid":null},"institutions":[{"id":"https://openalex.org/I53486688","display_name":"Skyworks Solutions (United States)","ror":"https://ror.org/02jymes45","country_code":"US","type":"company","lineage":["https://openalex.org/I53486688"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Fang","raw_affiliation_strings":["Skywork AI PTE. LTD"],"affiliations":[{"raw_affiliation_string":"Skywork AI PTE. LTD","institution_ids":["https://openalex.org/I53486688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114136994","display_name":"Yahui Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I53486688","display_name":"Skyworks Solutions (United States)","ror":"https://ror.org/02jymes45","country_code":"US","type":"company","lineage":["https://openalex.org/I53486688"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yahui Zhou","raw_affiliation_strings":["Skywork AI PTE. LTD"],"affiliations":[{"raw_affiliation_string":"Skywork AI PTE. LTD","institution_ids":["https://openalex.org/I53486688"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5071579165"],"corresponding_institution_ids":["https://openalex.org/I53486688"],"apc_list":null,"apc_paid":null,"fwci":0.3386,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47719205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1471","last_page":"1475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9939000010490417,"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/stereophonic-sound","display_name":"Stereophonic sound","score":0.8615550398826599},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7988512516021729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7777878046035767},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6919321417808533},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6507883071899414},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5926732420921326},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5028817057609558},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4840666353702545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3964354991912842},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.12098610401153564},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07703498005867004}],"concepts":[{"id":"https://openalex.org/C140631703","wikidata":"https://www.wikidata.org/wiki/Q34678","display_name":"Stereophonic sound","level":3,"score":0.8615550398826599},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7988512516021729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7777878046035767},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6919321417808533},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6507883071899414},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5926732420921326},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5028817057609558},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4840666353702545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3964354991912842},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.12098610401153564},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07703498005867004},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446643","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10446643","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":27,"referenced_works":["https://openalex.org/W2131738223","https://openalex.org/W2460742184","https://openalex.org/W2752796333","https://openalex.org/W2963992487","https://openalex.org/W3037038648","https://openalex.org/W3215615641","https://openalex.org/W4212774754","https://openalex.org/W4240826525","https://openalex.org/W4244017338","https://openalex.org/W4285528093","https://openalex.org/W4287802874","https://openalex.org/W4298310324","https://openalex.org/W4307323391","https://openalex.org/W4318351475","https://openalex.org/W4319989813","https://openalex.org/W4378499140","https://openalex.org/W4380136719","https://openalex.org/W4381786045","https://openalex.org/W6636170946","https://openalex.org/W6748409065","https://openalex.org/W6762931180","https://openalex.org/W6776218486","https://openalex.org/W6849105126","https://openalex.org/W6849517043","https://openalex.org/W6849635556","https://openalex.org/W6852824296","https://openalex.org/W6853096648"],"related_works":["https://openalex.org/W1963904765","https://openalex.org/W1571600724","https://openalex.org/W2092226312","https://openalex.org/W2063364583","https://openalex.org/W3089290050","https://openalex.org/W3014956419","https://openalex.org/W1498584171","https://openalex.org/W1745769461","https://openalex.org/W4229795187","https://openalex.org/W1514833977"],"abstract_inverted_index":{"The":[0],"recent":[1],"success":[2,25],"of":[3,12,26,72,108,121,129,138,167,188],"audio":[4,18],"language":[5],"models":[6],"(LMs)":[7],"has":[8,22,58,115],"revolutionized":[9],"the":[10,24,55,70,96,127,135,160,172,185,189],"field":[11],"neural":[13,78,131,154],"music":[14,31,53,76,123,191],"generation.":[15],"Among":[16],"all":[17],"LM":[19],"approaches,":[20],"MusicGen":[21],"demonstrated":[23],"a":[27,83,90],"single-stage":[28,101,139,174],"LMs":[29,175],"based":[30,88],"generation":[32,136,192],"framework,":[33],"without":[34],"needing":[35],"to":[36,125],"train":[37],"multiple":[38],"LMs.":[39,140],"Despite":[40],"its":[41],"promising":[42],"performance":[43,128],"in":[44,60,100,165,196],"generating":[45,50],"monophonic":[46],"(mono)":[47],"music,":[48],"directly":[49,73],"stereophonic":[51],"(stereo)":[52],"following":[54],"previous":[56],"framework":[57],"resulted":[59],"perceptible":[61],"quality":[62,137,187],"degradation.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,103],"first":[68],"discuss":[69],"difficulty":[71],"encoding":[74,92,151,163],"stereo":[75,122,130,173],"with":[77,177],"codec,":[79],"and":[80,85,134,170],"then":[81],"provide":[82],"stable":[84],"practical":[86],"solution":[87],"on":[89],"dual":[91,150],"approach.":[93],"To":[94],"utilize":[95],"dually":[97],"encoded":[98],"tokens":[99],"LMs,":[102],"also":[104],"propose":[105],"two":[106],"forms":[107],"token":[109,180],"sequence":[110,181],"patterns.":[111],"An":[112],"extensive":[113],"evaluation":[114],"been":[116],"conducted":[117],"using":[118],"various":[119],"aspects":[120],"audios":[124],"examine":[126],"codec":[132,155],"approaches":[133],"Finally,":[141],"our":[142,148,178],"experimental":[143],"results":[144],"suggest":[145],"that":[146],"(i)":[147],"proposed":[149,179],"approach":[152,164],"for":[153],"is":[156],"significantly":[157],"better":[158],"than":[159],"typical":[161],"joint":[162],"terms":[166],"reconstruction":[168],"quality,":[169],"(ii)":[171],"trained":[176],"patterns":[182],"substantially":[183],"improved":[184],"perceptual":[186],"state-of-the-art":[190],"model":[193],"(i.e.":[194],"MusicGen)":[195],"subjective":[197],"tests.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
