{"id":"https://openalex.org/W3209993061","doi":"https://doi.org/10.1109/icassp43922.2022.9746102","title":"Contrastive Prediction Strategies for Unsupervised Segmentation and Categorization of Phonemes and Words","display_name":"Contrastive Prediction Strategies for Unsupervised Segmentation and Categorization of Phonemes and Words","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3209993061","doi":"https://doi.org/10.1109/icassp43922.2022.9746102","mag":"3209993061"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746102","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746102","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.15909","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076491406","display_name":"Santiago Cuervo","orcid":null},"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":"Santiago Cuervo","raw_affiliation_strings":["University of Wroclaw,Poland","University of Wroclaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wroclaw,Poland","institution_ids":["https://openalex.org/I219388962"]},{"raw_affiliation_string":"University of Wroclaw, Poland","institution_ids":["https://openalex.org/I219388962"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053728978","display_name":"Maciej Grabias","orcid":null},"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":"Maciej Grabias","raw_affiliation_strings":["University of Wroclaw,Poland","University of Wroclaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wroclaw,Poland","institution_ids":["https://openalex.org/I219388962"]},{"raw_affiliation_string":"University of Wroclaw, Poland","institution_ids":["https://openalex.org/I219388962"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000408865","display_name":"Jan Chorowski","orcid":"https://orcid.org/0000-0002-1570-7610"},"institutions":[{"id":"https://openalex.org/I4210137815","display_name":"Naval Group (France)","ror":"https://ror.org/03rks9355","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210137815"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jan Chorowski","raw_affiliation_strings":["NavAlgo,France","NavAlgo, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NavAlgo,France","institution_ids":["https://openalex.org/I4210137815"]},{"raw_affiliation_string":"NavAlgo, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000255685","display_name":"Grzegorz Ciesielski","orcid":null},"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":"Grzegorz Ciesielski","raw_affiliation_strings":["University of Wroclaw,Poland","University of Wroclaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wroclaw,Poland","institution_ids":["https://openalex.org/I219388962"]},{"raw_affiliation_string":"University of Wroclaw, Poland","institution_ids":["https://openalex.org/I219388962"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011669714","display_name":"Adrian \u0141a\u0144cucki","orcid":null},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Adrian Lancucki","raw_affiliation_strings":["Nvidia,Poland","Nvidia, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia,Poland","institution_ids":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"raw_affiliation_string":"Nvidia, Poland","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019910451","display_name":"Pawe\u0142 Rychlikowski","orcid":"https://orcid.org/0000-0002-1364-7167"},"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":"Pawel Rychlikowski","raw_affiliation_strings":["University of Wroclaw,Poland","University of Wroclaw, Poland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Wroclaw,Poland","institution_ids":["https://openalex.org/I219388962"]},{"raw_affiliation_string":"University of Wroclaw, Poland","institution_ids":["https://openalex.org/I219388962"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013266148","display_name":"Ricard Marxer","orcid":"https://orcid.org/0000-0001-5099-5059"},"institutions":[{"id":"https://openalex.org/I143002897","display_name":"Universit\u00e9 de Toulon","ror":"https://ror.org/02m9kbe37","country_code":"FR","type":"education","lineage":["https://openalex.org/I143002897"]},{"id":"https://openalex.org/I4210114274","display_name":"Laboratoire d\u2019Informatique et Syst\u00e8mes","ror":"https://ror.org/0257sgk90","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I143002897","https://openalex.org/I21491767","https://openalex.org/I4210114274"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ricard Marxer","raw_affiliation_strings":["Universit&#x00E9; de Toulon, Aix Marseille Univ,Cnrs, LIS,Toulon,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit&#x00E9; de Toulon, Aix Marseille Univ,Cnrs, LIS,Toulon,France","institution_ids":["https://openalex.org/I143002897","https://openalex.org/I4210114274"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3189","last_page":"3193"},"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":0.9990000128746033,"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":0.996999979019165,"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/categorization","display_name":"Categorization","score":0.8878298401832581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7955340147018433},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7820473909378052},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6462184190750122},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5390580892562866},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4828272759914398},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4462062418460846},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4337308406829834},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.42913520336151123},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.42036372423171997},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39809995889663696},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07434579730033875},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.05966681241989136}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8878298401832581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955340147018433},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7820473909378052},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6462184190750122},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5390580892562866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4828272759914398},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4462062418460846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4337308406829834},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.42913520336151123},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.42036372423171997},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39809995889663696},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07434579730033875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.05966681241989136},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746102","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746102","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2110.15909","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.15909","pdf_url":"https://arxiv.org/pdf/2110.15909","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":"pmh:oai:HAL:hal-03824772v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03824772","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), May 2022, Singapore, Singapore. pp.3189-3193, &#x27E8;10.1109/ICASSP43922.2022.9746102&#x27E9;","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.15909","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.15909","pdf_url":"https://arxiv.org/pdf/2110.15909","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":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3570594198","display_name":"Microscopic Intelligibility Modeling","funder_award_id":"ANR-20-CE23-0012","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W130754613","https://openalex.org/W1494198834","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2127141656","https://openalex.org/W2145410271","https://openalex.org/W2842511635","https://openalex.org/W2963403868","https://openalex.org/W3096656254","https://openalex.org/W3110458199","https://openalex.org/W3112613336","https://openalex.org/W3127686677","https://openalex.org/W3197974236","https://openalex.org/W3198134274","https://openalex.org/W3198782837","https://openalex.org/W4287591426","https://openalex.org/W4297808394","https://openalex.org/W4385245566","https://openalex.org/W6674330103","https://openalex.org/W6739901393","https://openalex.org/W6786696081","https://openalex.org/W6787178341","https://openalex.org/W6917638038"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":{"We":[0],"identify":[1],"a":[2,47,80],"performance":[3,38,44,88,114],"trade-off":[4],"between":[5],"the":[6,51,63,86],"tasks":[7],"of":[8,82,100],"phoneme":[9,12],"categorization":[10,40,90,109],"and":[11,13,68,92,96,111],"word":[14,116],"segmentation":[15,43,67],"in":[16,106,115],"several":[17],"self-supervised":[18],"learning":[19],"algorithms":[20],"based":[21],"on":[22,39,50,66,76,89],"Contrastive":[23],"Predictive":[24],"Coding":[25],"(CPC).":[26],"Our":[27,103],"experiments":[28],"suggest":[29],"that":[30],"context":[31],"building":[32],"networks,":[33],"albeit":[34],"necessary":[35],"for":[36,98],"high":[37],"tasks,":[41,91],"harm":[42],"by":[45],"causing":[46],"temporal":[48],"shift":[49],"learned":[52],"representations.":[53],"Aiming":[54],"to":[55],"tackle":[56],"this":[57],"trade-off,":[58],"we":[59],"take":[60],"inspiration":[61],"from":[62],"leading":[64],"approaches":[65],"propose":[69],"multi-level":[70,94],"Aligned":[71,77],"CPC":[72,78,83],"(mACPC).":[73],"It":[74],"builds":[75],"(ACPC),":[79],"variant":[81],"which":[84],"exhibits":[85],"best":[87],"incorporates":[93],"modeling":[95],"optimization":[97],"detection":[99],"spectral":[101],"changes.":[102],"methods":[104],"improve":[105],"all":[107],"tested":[108],"metrics":[110],"achieve":[112],"state-of-the-art":[113],"segmentation.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
