{"id":"https://openalex.org/W3178584664","doi":"https://doi.org/10.21437/interspeech.2021-1503","title":"Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021","display_name":"Speech Representation Learning Combining Conformer CPC with Deep Cluster for the ZeroSpeech Challenge 2021","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3178584664","doi":"https://doi.org/10.21437/interspeech.2021-1503","mag":"3178584664"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1503","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1503","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/2107.05899","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059612504","display_name":"Takashi Maekaku","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Takashi Maekaku","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050058892","display_name":"Xuankai Chang","orcid":"https://orcid.org/0000-0002-5221-5412"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuankai Chang","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040732498","display_name":"Yuya Fujita","orcid":"https://orcid.org/0000-0001-8155-6040"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuya Fujita","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625784","display_name":"Liwei Chen","orcid":"https://orcid.org/0000-0002-9858-0765"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li-Wei Chen","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040668817","display_name":"Alexander I. Rudnicky","orcid":"https://orcid.org/0000-0003-2044-8446"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Rudnicky","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"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":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1564","last_page":"1568"},"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":0.9988999962806702,"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/metric","display_name":"Metric (unit)","score":0.7071529626846313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6197983026504517},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6060954928398132},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6008033156394958},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5374190807342529},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5222126841545105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5097607970237732},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4759875535964966},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44199782609939575},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3765150010585785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3556435704231262},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26398688554763794},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10093960165977478},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0727098286151886}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7071529626846313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6197983026504517},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6060954928398132},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6008033156394958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5374190807342529},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5222126841545105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5097607970237732},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4759875535964966},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44199782609939575},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3765150010585785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3556435704231262},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26398688554763794},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10093960165977478},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0727098286151886},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1503","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1503","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:2107.05899","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.05899","pdf_url":"https://arxiv.org/pdf/2107.05899","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3178584664","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2107.05899v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.2107.05899","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.05899","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2107.05899","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.05899","pdf_url":"https://arxiv.org/pdf/2107.05899","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3178584664.pdf","grobid_xml":"https://content.openalex.org/works/W3178584664.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1538131130","https://openalex.org/W1836465849","https://openalex.org/W2064675550","https://openalex.org/W2095705004","https://openalex.org/W2152790380","https://openalex.org/W2395899413","https://openalex.org/W2765741717","https://openalex.org/W2842511635","https://openalex.org/W2883725317","https://openalex.org/W2963403868","https://openalex.org/W2964074409","https://openalex.org/W2965373594","https://openalex.org/W2973157397","https://openalex.org/W2982223350","https://openalex.org/W2995181338","https://openalex.org/W2996383576","https://openalex.org/W2996728628","https://openalex.org/W3015737168","https://openalex.org/W3016011332","https://openalex.org/W3025165719","https://openalex.org/W3026041220","https://openalex.org/W3093579165","https://openalex.org/W3094800360","https://openalex.org/W3095783102","https://openalex.org/W3096338464","https://openalex.org/W3099782249","https://openalex.org/W3110458199"],"related_works":["https://openalex.org/W2588127192","https://openalex.org/W3209059054","https://openalex.org/W2956699086","https://openalex.org/W2118942159","https://openalex.org/W2027315203","https://openalex.org/W3137093496","https://openalex.org/W2181974327","https://openalex.org/W137723034","https://openalex.org/W3205920203","https://openalex.org/W2102767294","https://openalex.org/W3087775747","https://openalex.org/W2166339243","https://openalex.org/W2403962673","https://openalex.org/W1422898552","https://openalex.org/W1843295064","https://openalex.org/W2899420204","https://openalex.org/W3098361150","https://openalex.org/W2541478194","https://openalex.org/W3018320627","https://openalex.org/W2403713357"],"abstract_inverted_index":{"We":[0,77,137],"present":[1],"a":[2,13,34,53,81,85,90,94,101,107,118,125],"system":[3],"for":[4],"the":[5,31,48,63,67,70,74,112,145],"Zero":[6],"Resource":[7],"Speech":[8],"Challenge":[9],"2021,":[10],"which":[11,130],"combines":[12],"Contrastive":[14],"Predictive":[15],"Coding":[16],"(CPC)":[17],"with":[18,37,66,84,144],"deep":[19,22],"cluster.":[20],"In":[21],"cluster,":[23],"we":[24,40],"first":[25],"prepare":[26],"pseudo-labels":[27,51],"obtained":[28,50],"by":[29,61],"clustering":[30,65],"outputs":[32,68],"of":[33,69,73,104,128],"CPC":[35],"network":[36],"k-means.":[38],"Then,":[39],"train":[41],"an":[42],"additional":[43],"autoregressive":[44,75],"model":[45],"to":[46,89,124],"classify":[47],"previously":[49],"in":[52,93,106,111,117,141],"supervised":[54],"manner.":[55],"Phoneme":[56],"discriminative":[57],"representation":[58],"is":[59,131],"achieved":[60,122],"executing":[62],"second-round":[64],"final":[71],"layer":[72,83,87],"model.":[76],"show":[78,99],"that":[79,100],"replacing":[80],"Transformer":[82],"Conformer":[86],"leads":[88],"further":[91],"gain":[92],"lexical":[95,113],"metric.":[96,147],"Experimental":[97],"results":[98,140],"relative":[102],"improvement":[103],"35%":[105],"phonetic":[108],"metric,":[109,114],"1.5%":[110],"and":[115],"2.3%":[116],"syntactic":[119,146],"metric":[120],"are":[121],"compared":[123],"baseline":[126],"method":[127],"CPC-small":[129],"trained":[132],"on":[133],"LibriSpeech":[134],"460h":[135],"data.":[136],"achieve":[138],"top":[139],"this":[142],"challenge":[143]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}