{"id":"https://openalex.org/W4214942696","doi":"https://doi.org/10.1109/ieeeconf53345.2021.9723318","title":"The effectiveness of self-supervised representation learning in zero-resource subword modeling","display_name":"The effectiveness of self-supervised representation learning in zero-resource subword modeling","publication_year":2021,"publication_date":"2021-10-31","ids":{"openalex":"https://openalex.org/W4214942696","doi":"https://doi.org/10.1109/ieeeconf53345.2021.9723318"},"language":"en","primary_location":{"id":"doi:10.1109/ieeeconf53345.2021.9723318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf53345.2021.9723318","pdf_url":null,"source":{"id":"https://openalex.org/S4363607877","display_name":"2021 55th Asilomar Conference on Signals, Systems, and Computers","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":"2021 55th Asilomar Conference on Signals, Systems, and Computers","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/A5053373302","display_name":"Siyuan Feng","orcid":"https://orcid.org/0000-0003-2531-8480"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Siyuan Feng","raw_affiliation_strings":["Delft University of Technology,Multimedia Computing Group,Delft,the Netherlands","Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Multimedia Computing Group,Delft,the Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048860892","display_name":"Odette Scharenborg","orcid":"https://orcid.org/0000-0003-0693-8852"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Odette Scharenborg","raw_affiliation_strings":["Delft University of Technology,Multimedia Computing Group,Delft,the Netherlands","Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Multimedia Computing Group,Delft,the Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Multimedia Computing Group, Delft University of Technology, Delft, the Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24362292,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1414","last_page":"1418"},"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":0.9979000091552734,"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":0.9975000023841858,"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":0.7967450618743896},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5366840362548828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5124197602272034},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.4825548529624939},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4364571273326874},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4343900680541992},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.43102627992630005},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.42155298590660095},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3658084273338318},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08287358283996582}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7967450618743896},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5366840362548828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5124197602272034},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.4825548529624939},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4364571273326874},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4343900680541992},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.43102627992630005},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.42155298590660095},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3658084273338318},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08287358283996582},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ieeeconf53345.2021.9723318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ieeeconf53345.2021.9723318","pdf_url":null,"source":{"id":"https://openalex.org/S4363607877","display_name":"2021 55th Asilomar Conference on Signals, Systems, and Computers","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":"2021 55th Asilomar Conference on Signals, Systems, and Computers","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:38006f51-a3d0-40a2-9436-b31e5ffb11e7","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:38006f51-a3d0-40a2-9436-b31e5ffb11e7","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7599999904632568}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W29952999","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W2100768664","https://openalex.org/W2296607128","https://openalex.org/W2347098582","https://openalex.org/W2399576818","https://openalex.org/W2514741789","https://openalex.org/W2752796333","https://openalex.org/W2786608204","https://openalex.org/W2787426069","https://openalex.org/W2787447541","https://openalex.org/W2842511635","https://openalex.org/W2889228998","https://openalex.org/W2963799213","https://openalex.org/W2971041032","https://openalex.org/W2972943112","https://openalex.org/W2995181338","https://openalex.org/W3005578234","https://openalex.org/W3016181583","https://openalex.org/W3040997499","https://openalex.org/W3044483536","https://openalex.org/W3100270690","https://openalex.org/W3112085130","https://openalex.org/W3148101939","https://openalex.org/W3150635893","https://openalex.org/W3160200310","https://openalex.org/W3196459653","https://openalex.org/W4297808394","https://openalex.org/W6601192135","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6675022971","https://openalex.org/W6697293080","https://openalex.org/W6748325621"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"For":[0],"a":[1,36,96,100,109,114,134],"language":[2,167],"with":[3],"no":[4],"transcribed":[5],"speech":[6,67],"available":[7],"(the":[8],"zero-resource":[9,19],"scenario),":[10],"conventional":[11],"acoustic":[12,20],"modeling":[13,21,32],"algorithms":[14],"are":[15],"not":[16],"applicable.":[17],"Recently,":[18],"has":[22,57],"gained":[23],"much":[24],"interest.":[25],"One":[26],"research":[27],"problem":[28],"is":[29,45,73,147,159,185],"unsupervised":[30,70],"subword":[31,42,135],"(USM),":[33],"i.e.,":[34],"learning":[35,55],"feature":[37],"representation":[38,110],"that":[39,53,120],"can":[40],"distinguish":[41],"units":[43],"and":[44,63,90,141,174],"robust":[46],"to":[47,60,107,113],"speaker":[48,62],"variation.":[49],"Previous":[50],"studies":[51],"showed":[52],"self-supervised":[54],"(SSL)":[56],"the":[58,121,126,131,139,153,162,165,170,175],"potential":[59],"separate":[61],"phonetic":[64],"information":[65],"in":[66,68,76,133,155,169],"an":[69],"manner,":[71],"which":[72,158],"highly":[74],"desired":[75],"USM.":[77],"This":[78],"paper":[79],"compares":[80],"two":[81],"representative":[82],"SSL":[83],"algorithms,":[84],"namely,":[85],"contrastive":[86],"predictive":[87,92],"coding":[88,93],"(CPC)":[89],"autoregressive":[91],"(APC),":[94],"as":[95,111,152],"front-end":[97,154],"method":[98],"of":[99,130,161,164,197],"recently":[101],"proposed,":[102],"state-of-the":[103],"art":[104,132],"two-stage":[105],"approach,":[106,157],"learn":[108],"input":[112],"back-end":[115,127,171],"cross-lingual":[116,172],"DNN.":[117],"Experiments":[118],"show":[119],"bottleneck":[122],"features":[123],"extracted":[124],"by":[125],"achieved":[128],"state":[129],"ABX":[136],"task":[137],"on":[138],"Libri-light":[140],"ZeroSpeech":[142],"databases.":[143],"In":[144],"general,":[145],"CPC":[146,192],"more":[148,189],"effective":[149,190],"than":[150,191],"APC":[151,184],"our":[156],"independent":[160],"choice":[163],"out-domain":[166],"identity":[168],"DNN":[173],"training":[176,182],"data":[177,195],"amount.":[178],"With":[179],"very":[180],"limited":[181],"data,":[183],"found":[186],"similar":[187],"or":[188],"when":[193],"test":[194],"consists":[196],"long":[198],"utterances.":[199]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}