{"id":"https://openalex.org/W3006358483","doi":"https://doi.org/10.1109/lsp.2020.2973798","title":"Unsupervised Feature Learning for Speech Using Correspondence and Siamese Networks","display_name":"Unsupervised Feature Learning for Speech Using Correspondence and Siamese Networks","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3006358483","doi":"https://doi.org/10.1109/lsp.2020.2973798","mag":"3006358483"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2020.2973798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2020.2973798","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.12799","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Petri-Johan Last","orcid":null},"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":"Petri-Johan Last","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Faculty of Engineering, Stellenbosch University, Stellenbosch, South Africa"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Faculty of Engineering, Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Herman A. Engelbrecht","orcid":"https://orcid.org/0000-0001-8753-8994"},"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 A. Engelbrecht","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Faculty of Engineering, Stellenbosch University, Stellenbosch, South Africa"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Faculty of Engineering, Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"last","author":{"id":null,"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":["Department of Electrical and Electronic Engineering, Faculty of Engineering, Stellenbosch University, Stellenbosch, South Africa"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Faculty of Engineering, Stellenbosch University, Stellenbosch, South Africa","institution_ids":["https://openalex.org/I26092322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I26092322"],"apc_list":null,"apc_paid":null,"fwci":1.5085,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.86004289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"27","issue":null,"first_page":"421","last_page":"425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.5360000133514404,"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":0.5360000133514404,"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":0.1678999960422516,"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/T10860","display_name":"Speech and Audio Processing","score":0.08510000258684158,"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/autoencoder","display_name":"Autoencoder","score":0.7541000247001648},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6542999744415283},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5996000170707703},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5910999774932861},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5235999822616577},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5205000042915344},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5177000164985657},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5099999904632568},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.39079999923706055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7800999879837036},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7541000247001648},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6542999744415283},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6427000164985657},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5996000170707703},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5910999774932861},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5748000144958496},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5205000042915344},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5177000164985657},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5099999904632568},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.39079999923706055},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.32440000772476196},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3118000030517578},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29670000076293945},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.2906000018119812},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.29030001163482666},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.288100004196167},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26829999685287476}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2020.2973798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2020.2973798","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2003.12799","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.12799","pdf_url":"https://arxiv.org/pdf/2003.12799","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.12799","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.12799","pdf_url":"https://arxiv.org/pdf/2003.12799","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":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1545920196","https://openalex.org/W1577418252","https://openalex.org/W1967924372","https://openalex.org/W2020607164","https://openalex.org/W2025482506","https://openalex.org/W2044138293","https://openalex.org/W2052697931","https://openalex.org/W2057007397","https://openalex.org/W2091746061","https://openalex.org/W2114347655","https://openalex.org/W2126203737","https://openalex.org/W2145410271","https://openalex.org/W2171590421","https://openalex.org/W2346964103","https://openalex.org/W2400549570","https://openalex.org/W2404799143","https://openalex.org/W2468716020","https://openalex.org/W2516890051","https://openalex.org/W2780786457","https://openalex.org/W2787447541","https://openalex.org/W2791647162","https://openalex.org/W2802557066","https://openalex.org/W2826003142","https://openalex.org/W2940544976","https://openalex.org/W2962850179","https://openalex.org/W2962980711","https://openalex.org/W2963620343","https://openalex.org/W2963720603","https://openalex.org/W2972764223","https://openalex.org/W2972867623","https://openalex.org/W6600284362","https://openalex.org/W6633682082","https://openalex.org/W6638159135","https://openalex.org/W6712202099","https://openalex.org/W6712444837","https://openalex.org/W6714100551","https://openalex.org/W6734095835","https://openalex.org/W6734901337","https://openalex.org/W6973666849"],"related_works":[],"abstract_inverted_index":{"In":[0],"zero-resource":[1],"settings":[2],"where":[3],"transcribed":[4],"speech":[5,16],"audio":[6],"is":[7,12,36,51],"unavailable,":[8],"unsupervised":[9,33],"feature":[10,28,57,115],"learning":[11],"essential":[13],"for":[14,25,68],"downstream":[15],"processing":[17],"tasks.":[18],"Here":[19],"we":[20,146],"compare":[21],"two":[22,70,135],"recent":[23],"methods":[24],"frame-level":[26],"acoustic":[27],"learning.":[29],"For":[30,72,110],"both":[31,157,173],"methods,":[32],"term":[34],"discovery":[35],"used":[37,53],"to":[38,54,91],"find":[39,131],"pairs":[40],"of":[41,44,97,165],"word":[42,61,101],"examples":[43],"the":[45,56,69,73,93,98,105,111,120,125,134,139,142,158],"same":[46,99,121,126],"unknown":[47],"type.":[48],"Dynamic":[49],"programming":[50],"then":[52],"align":[55],"frames":[58,78,96],"between":[59,95,107],"each":[60],"pair,":[62],"serving":[63],"as":[64,81],"weak":[65,127],"top-down":[66],"supervision":[67,128],"models.":[71],"correspondence":[74],"autoencoder":[75],"(CAE),":[76],"matching":[77],"are":[79,117],"presented":[80],"input-output":[82],"pairs.":[83,129],"The":[84],"Triamese":[85,143,161],"network":[86],"uses":[87],"a":[88,149],"contrastive":[89],"loss":[90],"reduce":[92],"distance":[94,106],"predicted":[100],"type":[102],"while":[103],"increasing":[104],"negative":[108],"examples.":[109],"first":[112],"time,":[113],"these":[114],"extractors":[116],"compared":[118],"on":[119,133,172],"discrimination":[122],"tasks":[123],"using":[124],"We":[130],"that,":[132],"datasets":[136],"considered":[137],"here,":[138],"CAE":[140,159],"outperforms":[141,156],"network.":[144],"However,":[145],"show":[147],"that":[148],"new":[150],"hybrid":[151],"correspondence-Triamese":[152],"approach":[153],"(CTriamese),":[154],"consistently":[155],"and":[160,168,175],"models":[162],"in":[163],"terms":[164],"average":[166],"precision":[167],"ABX":[169],"error":[170],"rates":[171],"English":[174],"Xitsonga":[176],"evaluation":[177],"data.":[178]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-02-24T00:00:00"}