{"id":"https://openalex.org/W3158953319","doi":"https://doi.org/10.21437/interspeech.2021-1544","title":"Aligned Contrastive Predictive Coding","display_name":"Aligned Contrastive Predictive Coding","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3158953319","doi":"https://doi.org/10.21437/interspeech.2021-1544","mag":"3158953319"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1544","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.11946","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000408865","display_name":"Jan Chorowski","orcid":"https://orcid.org/0000-0002-1570-7610"},"institutions":[{"id":"https://openalex.org/I219388962","display_name":"University of Wroc\u0142aw","ror":"https://ror.org/00yae6e25","country_code":"PL","type":"education","lineage":["https://openalex.org/I219388962"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Jan Chorowski","raw_affiliation_strings":["University of Wroclaw,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wroclaw,","institution_ids":["https://openalex.org/I219388962"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000255685","display_name":"Grzegorz Ciesielski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grzegorz Ciesielski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033464333","display_name":"Jaros\u0142aw Dzikowski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaros\u0142aw Dzikowski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011669714","display_name":"Adrian \u0141a\u0144cucki","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adrian \u0141a\u0144cucki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013266148","display_name":"Ricard Marxer","orcid":"https://orcid.org/0000-0001-5099-5059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ricard Marxer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055459313","display_name":"Mateusz Opala","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mateusz Opala","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001968423","display_name":"Piotr Pusz","orcid":"https://orcid.org/0000-0001-6012-8047"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Piotr Pusz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019910451","display_name":"Pawe\u0142 Rychlikowski","orcid":"https://orcid.org/0000-0002-1364-7167"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pawe\u0142 Rychlikowski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072966449","display_name":"Micha\u0142 Stypu\u0142kowski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Micha\u0142 Stypu\u0142kowski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"976","last_page":"980"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/predictive-coding","display_name":"Predictive coding","score":0.8134053945541382},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7190531492233276},{"id":"https://openalex.org/keywords/abx-test","display_name":"ABX test","score":0.6095700263977051},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.550348699092865},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5473069548606873},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5127242803573608},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.46793338656425476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4639081358909607},{"id":"https://openalex.org/keywords/forcing","display_name":"Forcing (mathematics)","score":0.4592802822589874},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.44995221495628357},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.41420888900756836},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34495896100997925},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34343743324279785},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33542802929878235},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.324399471282959},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16409754753112793},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1169811487197876},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0710272490978241}],"concepts":[{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.8134053945541382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7190531492233276},{"id":"https://openalex.org/C60962613","wikidata":"https://www.wikidata.org/wiki/Q287654","display_name":"ABX test","level":2,"score":0.6095700263977051},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.550348699092865},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5473069548606873},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5127242803573608},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.46793338656425476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4639081358909607},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.4592802822589874},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.44995221495628357},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.41420888900756836},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34495896100997925},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34343743324279785},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33542802929878235},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.324399471282959},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16409754753112793},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1169811487197876},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0710272490978241},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2021-1544","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.11946","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.11946","pdf_url":"https://arxiv.org/pdf/2104.11946","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3158953319","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2104.11946","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:HAL:hal-03408618v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03408618","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2021, Aug 2021, Brno, Czech Republic. pp.976-980, ⟨10.21437/interspeech.2021-1544⟩","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2104.11946","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.11946","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.11946","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.11946","pdf_url":"https://arxiv.org/pdf/2104.11946","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326815","display_name":"Infrastruktura PL-Grid","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1828163288","https://openalex.org/W2064675550","https://openalex.org/W2078993594","https://openalex.org/W2095705004","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2146444479","https://openalex.org/W2535388113","https://openalex.org/W2842511635","https://openalex.org/W2963403868","https://openalex.org/W2963799213","https://openalex.org/W2964308564","https://openalex.org/W3008499099","https://openalex.org/W3016181583","https://openalex.org/W3033038061","https://openalex.org/W3093788532","https://openalex.org/W3095361818","https://openalex.org/W3110458199","https://openalex.org/W3112613336","https://openalex.org/W3125709657","https://openalex.org/W3134881075"],"related_works":["https://openalex.org/W3197974236","https://openalex.org/W2557205271","https://openalex.org/W2773723600","https://openalex.org/W3213809193","https://openalex.org/W2949174760","https://openalex.org/W2975068042","https://openalex.org/W2937808806","https://openalex.org/W2537374808","https://openalex.org/W2765122878","https://openalex.org/W2051771890","https://openalex.org/W2091544142","https://openalex.org/W3142331400","https://openalex.org/W2169724380","https://openalex.org/W3191747585","https://openalex.org/W171514242","https://openalex.org/W115323076","https://openalex.org/W2396814492","https://openalex.org/W2575406636","https://openalex.org/W2996819981","https://openalex.org/W2256540572"],"abstract_inverted_index":{"We":[0,84],"investigate":[1],"the":[2,29,32,43,55,64,73,86,96,123],"possibility":[3],"of":[4,28,37,42,62,126],"forcing":[5],"a":[6,11,35,59,89],"self-supervised":[7],"model":[8,33,87],"trained":[9,77],"using":[10],"contrastive":[12],"predictive":[13],"loss":[14],"to":[15,46,78,104,119,122],"extract":[16],"slowly":[17],"varying":[18],"latent":[19,82],"representations.":[20],"Rather":[21],"than":[22,40],"producing":[23],"individual":[24],"predictions":[25,38],"for":[26],"each":[27],"future":[30],"representations,":[31],"emits":[34],"sequence":[36],"shorter":[39],"that":[41,95],"upcoming":[44],"representations":[45],"which":[47],"they":[48],"will":[49],"be":[50],"aligned.":[51],"In":[52],"this":[53],"way,":[54],"prediction":[56,108,127],"network":[57,75],"solves":[58],"simpler":[60],"task":[61,92],"predicting":[63],"next":[65],"symbols,":[66],"but":[67],"not":[68],"their":[69],"exact":[70],"timing,":[71],"while":[72,115],"encoding":[74],"is":[76],"produce":[79],"piece-wise":[80],"constant":[81],"codes.":[83],"evaluate":[85],"on":[88],"speech":[90],"coding":[91],"and":[93,110],"demonstrate":[94],"proposed":[97],"Aligned":[98],"Contrastive":[99],"Predictive":[100],"Coding":[101],"(ACPC)":[102],"leads":[103],"higher":[105],"linear":[106],"phone":[107],"accuracy":[109],"lower":[111],"ABX":[112],"error":[113],"rates,":[114],"being":[116],"slightly":[117],"faster":[118],"train":[120],"due":[121],"reduced":[124],"number":[125],"heads.":[128]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}