{"id":"https://openalex.org/W3190032417","doi":"https://doi.org/10.21437/interspeech.2021-1182","title":"Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing","display_name":"Analyzing Speaker Information in Self-Supervised Models to Improve Zero-Resource Speech Processing","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3190032417","doi":"https://doi.org/10.21437/interspeech.2021-1182","mag":"3190032417"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1182","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1182","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2108.00917","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046382731","display_name":"Benjamin van Niekerk","orcid":"https://orcid.org/0000-0001-9207-6309"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":true,"raw_author_name":"Benjamin van Niekerk","raw_affiliation_strings":["Stellenbosch University, Stellenbosch, South Africa"],"affiliations":[{"raw_affiliation_string":"Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020033363","display_name":"Leanne Nortje","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leanne Nortje","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085677838","display_name":"Matthew Baas","orcid":"https://orcid.org/0000-0003-3001-6292"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Matthew Baas","raw_affiliation_strings":["Stellenbosch University, Stellenbosch, South Africa"],"affiliations":[{"raw_affiliation_string":"Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["StellenBosch University"],"affiliations":[{"raw_affiliation_string":"StellenBosch University","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5046382731"],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":null,"apc_paid":null,"fwci":0.1398,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55132678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1554","last_page":"1558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9977999925613403,"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/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/computer-science","display_name":"Computer science","score":0.8088977336883545},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7289160490036011},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6839039325714111},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6786323189735413},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5815739631652832},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5326476097106934},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5275344848632812},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5210965871810913},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.49493473768234253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47127029299736023},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44121071696281433},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4008384644985199},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32219916582107544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8088977336883545},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7289160490036011},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6839039325714111},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6786323189735413},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5815739631652832},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5326476097106934},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5275344848632812},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5210965871810913},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.49493473768234253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47127029299736023},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44121071696281433},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4008384644985199},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32219916582107544},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2021-1182","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1182","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:2108.00917","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.00917","pdf_url":"https://arxiv.org/pdf/2108.00917","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":"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:3190032417","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2108.00917.pdf","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":"doi:10.48550/arxiv.2108.00917","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2108.00917","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2108.00917","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2108.00917","pdf_url":"https://arxiv.org/pdf/2108.00917","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":"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":[{"id":"https://metadata.un.org/sdg/4","score":0.6700000166893005,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3190032417.pdf","grobid_xml":"https://content.openalex.org/works/W3190032417.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2014307400","https://openalex.org/W2025482506","https://openalex.org/W2100768664","https://openalex.org/W2113054345","https://openalex.org/W2117041980","https://openalex.org/W2138615112","https://openalex.org/W2347098582","https://openalex.org/W2395899413","https://openalex.org/W2747874407","https://openalex.org/W2766049740","https://openalex.org/W2787447541","https://openalex.org/W2842511635","https://openalex.org/W2889326414","https://openalex.org/W2962689740","https://openalex.org/W2963620343","https://openalex.org/W2972943112","https://openalex.org/W2973026522","https://openalex.org/W2996383576","https://openalex.org/W2996728628","https://openalex.org/W3003875258","https://openalex.org/W3093096176","https://openalex.org/W3095361818","https://openalex.org/W3099782249","https://openalex.org/W3110458199","https://openalex.org/W3125709657","https://openalex.org/W3129009457","https://openalex.org/W3158802984","https://openalex.org/W3197349023","https://openalex.org/W3197381195"],"related_works":["https://openalex.org/W2165340520","https://openalex.org/W2951130829","https://openalex.org/W13110487","https://openalex.org/W2269033948","https://openalex.org/W2939913319","https://openalex.org/W2962832278","https://openalex.org/W2106767322","https://openalex.org/W3044308976","https://openalex.org/W3015219411","https://openalex.org/W2920796740","https://openalex.org/W2607725416","https://openalex.org/W3103120760","https://openalex.org/W64940049","https://openalex.org/W2899351468","https://openalex.org/W3036173644","https://openalex.org/W2900944893","https://openalex.org/W3099992561","https://openalex.org/W2091802891","https://openalex.org/W3206252155","https://openalex.org/W3096802056"],"abstract_inverted_index":{"Contrastive":[0],"predictive":[1],"coding":[2],"(CPC)":[3],"aims":[4],"to":[5,56,83,122],"learn":[6],"representations":[7],"of":[8,17,77,130,147],"speech":[9],"by":[10],"distinguishing":[11],"future":[12],"observations":[13],"from":[14],"a":[15,84,96,118,137],"set":[16],"negative":[18],"examples.":[19],"Previous":[20],"work":[21],"has":[22],"shown":[23],"that":[24,73,90,104,136],"linear":[25],"classifiers":[26],"trained":[27,140],"on":[28,63,95,113,141],"CPC":[29,78,131],"features":[30,44,79,107],"can":[31],"accurately":[32],"predict":[33],"speaker":[34,47,81,97,110,119],"and":[35,48,51],"phone":[36],"labels.":[37],"However,":[38],"it":[39,53],"is":[40,54],"unclear":[41],"how":[42],"the":[43,59,64,74,106,142,148,152],"actually":[45],"capture":[46],"phonetic":[49],"information,":[50],"whether":[52],"possible":[55],"normalize":[57],"out":[58],"irrelevant":[60],"details":[61],"(depending":[62],"downstream":[65],"task).":[66],"In":[67],"this":[68,114],"paper,":[69],"we":[70,88,116,134],"first":[71],"show":[72,103,135],"per-utterance":[75],"mean":[76],"captures":[80],"information":[82],"large":[85],"extent.":[86],"Concretely,":[87],"find":[89],"comparing":[91],"means":[92],"performs":[93],"well":[94],"verification":[98],"task.":[99],"Next,":[100],"probing":[101],"experiments":[102],"standardizing":[105],"effectively":[108],"removes":[109],"information.":[111],"Based":[112],"observation,":[115],"propose":[117],"normalization":[120],"step":[121],"improve":[123],"acoustic":[124],"unit":[125],"discovery":[126],"using":[127],"K-means":[128],"clustering":[129],"features.":[132],"Finally,":[133],"language":[138],"model":[139],"resulting":[143],"units":[144],"achieves":[145],"some":[146],"best":[149],"results":[150],"in":[151],"ZeroSpeech2021~Challenge.":[153]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2022-07-25T00:00:00"}
