{"id":"https://openalex.org/W4393241602","doi":"https://doi.org/10.1109/lsp.2024.3381910","title":"Efficient Parallel Audio Generation Using Group Masked Language Modeling","display_name":"Efficient Parallel Audio Generation Using Group Masked Language Modeling","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4393241602","doi":"https://doi.org/10.1109/lsp.2024.3381910"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2024.3381910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3381910","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5103069095","display_name":"Myeonghun Jeong","orcid":"https://orcid.org/0000-0002-4689-3110"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myeonghun Jeong","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-4689-3110","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027616639","display_name":"Minchan Kim","orcid":"https://orcid.org/0000-0002-8150-765X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minchan Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-8150-765X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042018167","display_name":"Joun Yeop Lee","orcid":"https://orcid.org/0000-0002-3316-4808"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joun Yeop Lee","raw_affiliation_strings":["Samsung Research, Seoul, South Korea","Samsung Research, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-3316-4808","affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]},{"raw_affiliation_string":"Samsung Research, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051356511","display_name":"Nam Soo Kim","orcid":"https://orcid.org/0000-0002-0568-4902"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]},{"id":"https://openalex.org/I4210164379","display_name":"Seoul Media Institute of Technology","ror":"https://ror.org/04ywg4h07","country_code":"KR","type":"education","lineage":["https://openalex.org/I4210164379"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Nam Soo Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0568-4902","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and with the Institute of New Media and Communications, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I4210164379","https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1262,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.75207618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"31","issue":null,"first_page":"979","last_page":"983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9521999955177307,"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":0.9521999955177307,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9448000192642212,"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/computer-science","display_name":"Computer science","score":0.7430838942527771},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.5216168165206909},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4887830913066864}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430838942527771},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.5216168165206909},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4887830913066864},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2024.3381910","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2024.3381910","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2519091744","https://openalex.org/W2752796333","https://openalex.org/W2972359262","https://openalex.org/W3024869864","https://openalex.org/W3097777922","https://openalex.org/W3209984917","https://openalex.org/W3213029956","https://openalex.org/W3215615641","https://openalex.org/W4221166168","https://openalex.org/W4226033575","https://openalex.org/W4307323391","https://openalex.org/W4313021454","https://openalex.org/W4313679638","https://openalex.org/W4322718191","https://openalex.org/W4372279529","https://openalex.org/W4377010126","https://openalex.org/W4380136719","https://openalex.org/W4381786045","https://openalex.org/W4385245566","https://openalex.org/W4390075359","https://openalex.org/W4392909680","https://openalex.org/W6755207826","https://openalex.org/W6778883912","https://openalex.org/W6779823529","https://openalex.org/W6780218876","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6795952400","https://openalex.org/W6796464841","https://openalex.org/W6847363464","https://openalex.org/W6848735303","https://openalex.org/W6850625674","https://openalex.org/W6851724922","https://openalex.org/W6852581948","https://openalex.org/W6853096648","https://openalex.org/W6853188576","https://openalex.org/W6854494257"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,15,73,90],"fast":[3],"and":[4,48,62,102],"high-quality":[5,70],"codec":[6],"language":[7],"model":[8,67,88,112],"for":[9,54],"parallel":[10,17,56],"audio":[11,18,57,71,118],"generation.":[12,58,119],"While":[13],"SoundStorm,":[14],"state-of-the-art":[16],"generation":[19],"model,":[20],"accelerates":[21],"inference":[22,33],"speed":[23],"compared":[24],"to":[25,35,68,93],"autoregressive":[26],"models,":[27],"it":[28],"still":[29],"suffers":[30],"from":[31],"slow":[32],"due":[34],"iterative":[36],"sampling.":[37],"To":[38],"resolve":[39],"this":[40],"problem,":[41],"we":[42],"propose":[43],"Group-Masked":[44],"Language":[45],"Modeling":[46],"(G-MLM)":[47],"Group":[49],"Iterative":[50],"Parallel":[51],"Decoding":[52],"(G-IPD)":[53],"efficient":[55],"Both":[59],"the":[60,66,81,95,99,114],"training":[61],"sampling":[63],"schemes":[64],"enable":[65],"synthesize":[69],"with":[72],"small":[74],"number":[75],"of":[76,98],"iterations":[77],"by":[78],"effectively":[79],"modeling":[80],"group-wise":[82],"conditional":[83],"dependencies.":[84],"In":[85],"addition,":[86],"our":[87,110],"employs":[89],"cross-attention-based":[91],"architecture":[92],"capture":[94],"speaker":[96],"style":[97],"prompt":[100],"voice":[101],"improves":[103],"computational":[104],"efficiency.":[105],"Experimental":[106],"results":[107],"demonstrate":[108],"that":[109],"proposed":[111],"outperforms":[113],"baselines":[115],"in":[116],"prompt-based":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}