{"id":"https://openalex.org/W1545920196","doi":"https://doi.org/10.1109/icassp.2015.7179087","title":"Unsupervised neural network based feature extraction using weak top-down constraints","display_name":"Unsupervised neural network based feature extraction using weak top-down constraints","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1545920196","doi":"https://doi.org/10.1109/icassp.2015.7179087","mag":"1545920196"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7179087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7179087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/f40c3e1a-8f4b-4170-be99-c2a16e9d1edc","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040305929","display_name":"Herman Kamper","orcid":"https://orcid.org/0000-0003-2980-3475"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Herman Kamper","raw_affiliation_strings":["CSTR","ILCC, University of Edinburgh, UK","[CSTR, School of Informatics, University of Edinburgh, UK]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSTR","institution_ids":[]},{"raw_affiliation_string":"ILCC, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"[CSTR, School of Informatics, University of Edinburgh, UK]","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017409643","display_name":"Micha Elsner","orcid":"https://orcid.org/0000-0002-1432-2129"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Micha Elsner","raw_affiliation_strings":["Department of Linguistics, The Ohio State University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Linguistics, The Ohio State University, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103622427","display_name":"Aren Jansen","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aren Jansen","raw_affiliation_strings":["HLTCOE and CLSP, Johns Hopkins University, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HLTCOE and CLSP, Johns Hopkins University, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075564798","display_name":"Sharon Goldwater","orcid":"https://orcid.org/0000-0002-7298-0947"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sharon Goldwater","raw_affiliation_strings":["ILCC, University of Edinburgh, UK","ILCC, School of Informatics, University of Edinburgh, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ILCC, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]},{"raw_affiliation_string":"ILCC, School of Informatics, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":26.2652,"has_fulltext":true,"cited_by_count":116,"citation_normalized_percentile":{"value":0.99579661,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5818","last_page":"5822"},"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":0.9997000098228455,"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":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8161818385124207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8032472133636475},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6899714469909668},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.6310213804244995},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6244008541107178},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.610328733921051},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5750126838684082},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5658037066459656},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4838096499443054},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.46561264991760254},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4442508816719055},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.44006410241127014},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4379728138446808},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3494889736175537},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.071719229221344},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07167121767997742}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8161818385124207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8032472133636475},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6899714469909668},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.6310213804244995},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6244008541107178},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.610328733921051},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5750126838684082},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5658037066459656},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4838096499443054},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.46561264991760254},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4442508816719055},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.44006410241127014},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4379728138446808},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3494889736175537},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.071719229221344},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07167121767997742},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2015.7179087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7179087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/f40c3e1a-8f4b-4170-be99-c2a16e9d1edc","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f40c3e1a-8f4b-4170-be99-c2a16e9d1edc","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kamper, H, Elsner, M, Jansen, A & Goldwater, S 2015, Unsupervised neural network based feature extraction using weak top-down constraints. in 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, Brisbane, QLD, Australia, pp. 5818-5822, 40th IEEE International Conference on Acoustics, Speech and Signal Processing , Brisbane, Australia, 19/04/15. https://doi.org/10.1109/ICASSP.2015.7179087","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/f40c3e1a-8f4b-4170-be99-c2a16e9d1edc","is_oa":false,"landing_page_url":"http://hdl.handle.net/20.500.11820/f40c3e1a-8f4b-4170-be99-c2a16e9d1edc","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/f40c3e1a-8f4b-4170-be99-c2a16e9d1edc","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/f40c3e1a-8f4b-4170-be99-c2a16e9d1edc","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","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":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kamper, H, Elsner, M, Jansen, A & Goldwater, S 2015, Unsupervised neural network based feature extraction using weak top-down constraints. in 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, Brisbane, QLD, Australia, pp. 5818-5822, 40th IEEE International Conference on Acoustics, Speech and Signal Processing , Brisbane, Australia, 19/04/15. https://doi.org/10.1109/ICASSP.2015.7179087","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.5299999713897705},{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W30845872","https://openalex.org/W51277926","https://openalex.org/W1872489089","https://openalex.org/W1967924372","https://openalex.org/W1991352039","https://openalex.org/W2020607164","https://openalex.org/W2022058071","https://openalex.org/W2025768430","https://openalex.org/W2035424729","https://openalex.org/W2052697931","https://openalex.org/W2057007397","https://openalex.org/W2063224314","https://openalex.org/W2072128103","https://openalex.org/W2100495367","https://openalex.org/W2100768664","https://openalex.org/W2110798204","https://openalex.org/W2126203737","https://openalex.org/W2128160875","https://openalex.org/W2140277151","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2401464865","https://openalex.org/W2407151108","https://openalex.org/W2799046698","https://openalex.org/W2964138484","https://openalex.org/W4231109964","https://openalex.org/W4293460823","https://openalex.org/W6601311673","https://openalex.org/W6639260565","https://openalex.org/W6675022971","https://openalex.org/W6676481782"],"related_works":["https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W2806873178","https://openalex.org/W2965146396","https://openalex.org/W2770818364","https://openalex.org/W4312416532"],"abstract_inverted_index":{"Deep":[0],"neural":[1,105],"networks":[2],"(DNNs)":[3],"have":[4],"become":[5],"a":[6,26,40,101,114,124,132,143],"standard":[7],"component":[8],"in":[9,13,53,113],"supervised":[10,144],"ASR,":[11],"used":[12,83],"both":[14],"data-driven":[15],"feature":[16,44,87,111],"extraction":[17],"and":[18,36,137],"acoustic":[19],"modelling.":[20],"Supervision":[21],"is":[22,82],"typically":[23],"obtained":[24],"from":[25],"forced":[27],"alignment":[28],"that":[29,46],"provides":[30],"phone":[31],"class":[32],"targets,":[33],"requiring":[34],"transcriptions":[35],"pronunciations.":[37],"We":[38],"propose":[39],"novel":[41],"unsupervised":[42,57],"DNN-based":[43],"extractor":[45,112],"can":[47],"be":[48],"trained":[49,134],"without":[50],"these":[51,72],"resources":[52],"zero-resource":[54],"settings.":[55],"Using":[56,107],"term":[58],"discovery,":[59],"we":[60,118],"find":[61],"pairs":[62,99],"of":[63,67,89,142],"isolated":[64],"word":[65,115],"examples":[66],"the":[68,86,90],"same":[69],"unknown":[70],"type;":[71],"provide":[73],"weak":[74],"top-down":[75],"supervision.":[76],"For":[77],"each":[78],"pair,":[79],"dynamic":[80],"programming":[81],"to":[84,100,131,139],"align":[85],"frames":[88,94],"two":[91],"words.":[92],"Matching":[93],"are":[95],"presented":[96],"as":[97,110],"input-output":[98],"deep":[102,135],"autoencoder":[103],"(AE)":[104],"network.":[106],"this":[108],"AE":[109],"discrimination":[116],"task,":[117],"achieve":[119],"64%":[120],"relative":[121,130],"improvement":[122,129],"over":[123],"previous":[125],"state-of-the-art":[126],"system,":[127],"57%":[128],"bottom-up":[133],"AE,":[136],"come":[138],"within":[140],"23%":[141],"system.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":23},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":10}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}