{"id":"https://openalex.org/W4381786045","doi":"https://doi.org/10.1109/taslp.2023.3288409","title":"AudioLM: A Language Modeling Approach to Audio Generation","display_name":"AudioLM: A Language Modeling Approach to Audio Generation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4381786045","doi":"https://doi.org/10.1109/taslp.2023.3288409"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3288409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3288409","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","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/A5026110001","display_name":"Zal\u00e1n Borsos","orcid":"https://orcid.org/0000-0003-0007-829X"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Zal\u00e1n Borsos","raw_affiliation_strings":["Google, Research, Zurich, Switzerland","Research, Google, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google, Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]},{"raw_affiliation_string":"Research, Google, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040382220","display_name":"Rapha\u00ebl Marinier","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Rapha\u00ebl Marinier","raw_affiliation_strings":["Google, Research, Paris, France","Research, Google, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google, Research, Paris, France","institution_ids":[]},{"raw_affiliation_string":"Research, Google, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058616625","display_name":"Damien Vincent","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Damien Vincent","raw_affiliation_strings":["Google, Research, Zurich, Switzerland","Research, Google, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google, Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]},{"raw_affiliation_string":"Research, Google, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102924622","display_name":"Eugene Kharitonov","orcid":"https://orcid.org/0009-0000-8653-721X"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Eugene Kharitonov","raw_affiliation_strings":["Google, Research, Paris, France","Research, Google, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google, Research, Paris, France","institution_ids":[]},{"raw_affiliation_string":"Research, Google, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065100569","display_name":"Olivier Pietquin","orcid":"https://orcid.org/0000-0002-5386-465X"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Olivier Pietquin","raw_affiliation_strings":["Google, Research, Paris, France","Research, Google, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google, Research, Paris, France","institution_ids":[]},{"raw_affiliation_string":"Research, Google, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081709307","display_name":"Matt Sharifi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Matt Sharifi","raw_affiliation_strings":["Google, Research, Zurich, Switzerland","Research, Google, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google, Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]},{"raw_affiliation_string":"Research, Google, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011258273","display_name":"Dominik Roblek","orcid":"https://orcid.org/0000-0002-2155-450X"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Dominik Roblek","raw_affiliation_strings":["Google, Research, Zurich, Switzerland","Research, Google, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google, Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]},{"raw_affiliation_string":"Research, Google, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050982379","display_name":"Olivier Teboul","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH","US"],"is_corresponding":false,"raw_author_name":"Olivier Teboul","raw_affiliation_strings":["Google, Research, Paris, CA, France","Research, Google, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google, Research, Paris, CA, France","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Research, Google, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065912572","display_name":"David Grangier","orcid":"https://orcid.org/0000-0002-8847-9532"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Grangier","raw_affiliation_strings":["Google, Research, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google, Research, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033341878","display_name":"Marco Tagliasacchi","orcid":"https://orcid.org/0000-0002-7682-6795"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Marco Tagliasacchi","raw_affiliation_strings":["Google, Research, Zurich, Switzerland","Research, Google, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google, Research, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]},{"raw_affiliation_string":"Research, Google, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047639590","display_name":"Neil Zeghidour","orcid":"https://orcid.org/0000-0001-6896-3987"},"institutions":[{"id":"https://openalex.org/I4210100430","display_name":"Google (Switzerland)","ror":"https://ror.org/014f9c269","country_code":"CH","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210100430","https://openalex.org/I4210128969"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Neil Zeghidour","raw_affiliation_strings":["Google, Research, Paris, France","Research, Google, Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"Google, Research, Paris, France","institution_ids":[]},{"raw_affiliation_string":"Research, Google, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210100430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5026110001"],"corresponding_institution_ids":["https://openalex.org/I4210100430"],"apc_list":null,"apc_paid":null,"fwci":57.0969,"has_fulltext":false,"cited_by_count":334,"citation_normalized_percentile":{"value":0.99929771,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"2523","last_page":"2533"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8441276550292969},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6484261155128479},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.49493664503097534},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.45639604330062866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40794527530670166},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.33289384841918945},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.26440513134002686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8441276550292969},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6484261155128479},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.49493664503097534},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.45639604330062866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40794527530670166},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.33289384841918945},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26440513134002686}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2023.3288409","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3288409","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","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":92,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1728888090","https://openalex.org/W2395899413","https://openalex.org/W2519091744","https://openalex.org/W2593779438","https://openalex.org/W2604231067","https://openalex.org/W2752796333","https://openalex.org/W2896457183","https://openalex.org/W2950547518","https://openalex.org/W2963182577","https://openalex.org/W2963799213","https://openalex.org/W2970006822","https://openalex.org/W2971074500","https://openalex.org/W2972354707","https://openalex.org/W2979476256","https://openalex.org/W2995181338","https://openalex.org/W2995359496","https://openalex.org/W2996286887","https://openalex.org/W3036601975","https://openalex.org/W3037038648","https://openalex.org/W3092028330","https://openalex.org/W3095095816","https://openalex.org/W3097777922","https://openalex.org/W3123097577","https://openalex.org/W3129651364","https://openalex.org/W3131922516","https://openalex.org/W3144810982","https://openalex.org/W3148101939","https://openalex.org/W3160799772","https://openalex.org/W3162391496","https://openalex.org/W3177813494","https://openalex.org/W3180355996","https://openalex.org/W3186609711","https://openalex.org/W3197259906","https://openalex.org/W3198123200","https://openalex.org/W3198217962","https://openalex.org/W3198815374","https://openalex.org/W3206395542","https://openalex.org/W3209059054","https://openalex.org/W3215615641","https://openalex.org/W4221161768","https://openalex.org/W4224308101","https://openalex.org/W4225680573","https://openalex.org/W4226033575","https://openalex.org/W4226275767","https://openalex.org/W4226380987","https://openalex.org/W4283388932","https://openalex.org/W4287802874","https://openalex.org/W4287887366","https://openalex.org/W4288089799","https://openalex.org/W4288348042","https://openalex.org/W4292779060","https://openalex.org/W4292825791","https://openalex.org/W4294619240","https://openalex.org/W4296068815","https://openalex.org/W4297808394","https://openalex.org/W4298580827","https://openalex.org/W4309793872","https://openalex.org/W4312633146","https://openalex.org/W4385245566","https://openalex.org/W4394671563","https://openalex.org/W6734901337","https://openalex.org/W6735849998","https://openalex.org/W6739901393","https://openalex.org/W6748409065","https://openalex.org/W6755182157","https://openalex.org/W6755207826","https://openalex.org/W6762931180","https://openalex.org/W6767111847","https://openalex.org/W6768435317","https://openalex.org/W6769196770","https://openalex.org/W6769627184","https://openalex.org/W6771324808","https://openalex.org/W6776218486","https://openalex.org/W6778883912","https://openalex.org/W6780218876","https://openalex.org/W6782760101","https://openalex.org/W6783182287","https://openalex.org/W6783867762","https://openalex.org/W6783944145","https://openalex.org/W6790356757","https://openalex.org/W6798182279","https://openalex.org/W6800767084","https://openalex.org/W6802517614","https://openalex.org/W6805710207","https://openalex.org/W6809593508","https://openalex.org/W6810081322","https://openalex.org/W6810311916","https://openalex.org/W6839643428","https://openalex.org/W6840487619","https://openalex.org/W6843673214","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W3192589309","https://openalex.org/W2539919382","https://openalex.org/W2122924390","https://openalex.org/W22517275","https://openalex.org/W2131711534","https://openalex.org/W4281389974","https://openalex.org/W4383605217","https://openalex.org/W1911859126","https://openalex.org/W2537070497","https://openalex.org/W1560013842"],"abstract_inverted_index":{"We":[0,36],"introduce":[1],"AudioLM,":[2],"a":[3,18,28,54,69,86],"framework":[4],"for":[5,139],"high-quality":[6,92],"audio":[7,16,25,40,75,88,101],"generation":[8,26],"with":[9],"long-term":[10,49,78],"consistency.":[11],"AudioLM":[12,103,124],"maps":[13],"the":[14,65,81],"input":[15],"to":[17,58,76,90,105],"sequence":[19],"of":[20,68,99,164],"discrete":[21,82],"tokens":[22],"and":[23,48,51,80,108,118,127,137],"casts":[24],"as":[27],"language":[29,71],"modeling":[30],"task":[31],"in":[32],"this":[33],"representation":[34,163],"space.":[35],"show":[37],"how":[38,145],"existing":[39],"tokenizers":[41],"provide":[42],"different":[43],"trade-offs":[44],"between":[45],"reconstruction":[46],"quality":[47],"structure,":[50],"we":[52,63,143],"propose":[53],"hybrid":[55],"tokenization":[56],"scheme":[57],"achieve":[59,91],"both":[60],"objectives.":[61],"Namely,":[62],"leverage":[64],"discretized":[66],"activations":[67],"masked":[70],"model":[72],"pre-trained":[73],"on":[74,96,116],"capture":[77],"structure":[79],"codes":[83],"produced":[84],"by":[85,151],"neural":[87],"codec":[89],"synthesis.":[93],"By":[94],"training":[95],"large":[97],"corpora":[98],"raw":[100],"waveforms,":[102],"learns":[104],"generate":[106],"natural":[107],"coherent":[109,153],"continuations":[110,131],"given":[111],"short":[112],"prompts.":[113],"When":[114],"trained":[115,159],"speech,":[117],"without":[119,160],"any":[120,161],"transcript":[121],"or":[122],"annotation,":[123],"generates":[125],"syntactically":[126],"semantically":[128],"plausible":[129],"speech":[130,150],"while":[132],"also":[133],"maintaining":[134],"speaker":[135],"identity":[136],"prosody":[138],"unseen":[140],"speakers.":[141],"Furthermore,":[142],"demonstrate":[144],"our":[146],"approach":[147],"extends":[148],"beyond":[149],"generating":[152],"piano":[154],"music":[155],"continuations,":[156],"despite":[157],"being":[158],"symbolic":[162],"music.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":143},{"year":2024,"cited_by_count":126},{"year":2023,"cited_by_count":51},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}