{"id":"https://openalex.org/W3016011332","doi":"https://doi.org/10.1109/icassp40776.2020.9054438","title":"Generative Pre-Training for Speech with Autoregressive Predictive Coding","display_name":"Generative Pre-Training for Speech with Autoregressive Predictive Coding","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3016011332","doi":"https://doi.org/10.1109/icassp40776.2020.9054438","mag":"3016011332"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5008107321","display_name":"Yu-An Chung","orcid":"https://orcid.org/0000-0001-9451-7956"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yu-An Chung","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112758056","display_name":"James Glass","orcid":"https://orcid.org/0000-0002-3097-360X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Glass","raw_affiliation_strings":["Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008107321"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":17.3187,"has_fulltext":false,"cited_by_count":156,"citation_normalized_percentile":{"value":0.9937764,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3497","last_page":"3501"},"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":0.9986000061035156,"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":0.9983999729156494,"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":0.7738238573074341},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.6694762706756592},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6170726418495178},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6076083779335022},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5622889399528503},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5476502180099487},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5254867672920227},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5142862200737},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.488722562789917},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.47048261761665344},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.45136475563049316},{"id":"https://openalex.org/keywords/predictive-coding","display_name":"Predictive coding","score":0.4404424726963043},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4330781400203705},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35167890787124634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738238573074341},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6694762706756592},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6170726418495178},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6076083779335022},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5622889399528503},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5476502180099487},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5254867672920227},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5142862200737},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.488722562789917},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.47048261761665344},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.45136475563049316},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.4404424726963043},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4330781400203705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35167890787124634},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W2024490156","https://openalex.org/W2101105183","https://openalex.org/W2194775991","https://openalex.org/W2758785877","https://openalex.org/W2785350307","https://openalex.org/W2808706139","https://openalex.org/W2842511635","https://openalex.org/W2884305338","https://openalex.org/W2889028433","https://openalex.org/W2896457183","https://openalex.org/W2899134946","https://openalex.org/W2899663614","https://openalex.org/W2941814890","https://openalex.org/W2943845043","https://openalex.org/W2952127920","https://openalex.org/W2962739339","https://openalex.org/W2963026768","https://openalex.org/W2963045354","https://openalex.org/W2963317665","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2963425185","https://openalex.org/W2963432880","https://openalex.org/W2963618559","https://openalex.org/W2963720603","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W2965373594","https://openalex.org/W2972943112","https://openalex.org/W2973034126","https://openalex.org/W2973048981","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2973217961","https://openalex.org/W3100270690","https://openalex.org/W3125709657","https://openalex.org/W4297808394","https://openalex.org/W4300558631","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6745117592","https://openalex.org/W6748148878","https://openalex.org/W6748215858","https://openalex.org/W6752888775","https://openalex.org/W6755207826","https://openalex.org/W6755977528","https://openalex.org/W6761563299","https://openalex.org/W6764498146","https://openalex.org/W6766673545","https://openalex.org/W6898505805"],"related_works":["https://openalex.org/W2383072803","https://openalex.org/W1555348406","https://openalex.org/W2095808012","https://openalex.org/W1161053017","https://openalex.org/W2280595606","https://openalex.org/W147502095","https://openalex.org/W2352223112","https://openalex.org/W1589999460","https://openalex.org/W3110733896","https://openalex.org/W4287325290"],"abstract_inverted_index":{"Learning":[0],"meaningful":[1],"and":[2,44,55,78,95,115,128],"general":[3],"representations":[4],"from":[5],"unannotated":[6],"speech":[7,46,62,69,74,76],"that":[8,64,84],"are":[9],"applicable":[10],"to":[11,24,71,132],"a":[12,30,36],"wide":[13],"range":[14],"of":[15,123],"tasks":[16],"remains":[17],"challenging.":[18],"In":[19],"this":[20],"paper":[21],"we":[22],"propose":[23],"use":[25,122],"autoregressive":[26],"predictive":[27],"coding":[28],"(APC),":[29],"recently":[31],"proposed":[32],"self-supervised":[33],"objective,":[34],"as":[35],"generative":[37],"pre-training":[38],"approach":[39],"for":[40,125],"learning":[41,58,99],"meaningful,":[42],"non-specific,":[43],"transferable":[45],"representations.":[47],"We":[48,118],"pre-train":[49],"APC":[50,85,127],"on":[51,60,101],"large-scale":[52],"unlabeled":[53],"data":[54,113],"conduct":[56],"transfer":[57],"experiments":[59,82],"three":[61,103],"applications":[63],"require":[65],"different":[66],"information":[67],"about":[68],"characteristics":[70],"perform":[72],"well:":[73],"recognition,":[75],"translation,":[77],"speaker":[79],"identification.":[80],"Extensive":[81],"show":[83],"not":[86],"only":[87],"outperforms":[88],"surface":[89],"features":[90],"(e.g.,":[91],"log":[92],"Mel":[93],"spectrograms)":[94],"other":[96],"popular":[97],"representation":[98],"methods":[100],"all":[102],"tasks,":[104],"but":[105],"is":[106],"also":[107,119],"effective":[108],"at":[109],"reducing":[110],"downstream":[111],"labeled":[112],"size":[114],"model":[116],"parameters.":[117],"investigate":[120],"the":[121],"Transformers":[124],"modeling":[126],"find":[129],"it":[130],"superior":[131],"RNNs.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":36},{"year":2021,"cited_by_count":50},{"year":2020,"cited_by_count":20}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}