{"id":"https://openalex.org/W1796128977","doi":"https://doi.org/10.21437/interspeech.2015-644","title":"A comparison of neural network methods for unsupervised representation learning on the zero resource speech challenge","display_name":"A comparison of neural network methods for unsupervised representation learning on the zero resource speech challenge","publication_year":2015,"publication_date":"2015-09-06","ids":{"openalex":"https://openalex.org/W1796128977","doi":"https://doi.org/10.21437/interspeech.2015-644","mag":"1796128977"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2015-644","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.pure.ed.ac.uk/ws/files/19869954/Renshaw_Kamper_ET_AL_2015_A_Comparison_of_Neural_Network_Methods.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064618827","display_name":"Daniel Renshaw","orcid":null},"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":"Daniel Renshaw","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","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":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"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":["Johns Hopkins University ("],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University (","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sharon Goldwater","raw_affiliation_strings":["School of Informatics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":95,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3199","last_page":"3203"},"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":0.9983999729156494,"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":0.9976000189781189,"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/computer-science","display_name":"Computer science","score":0.7174611687660217},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.6562067866325378},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6371189951896667},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5678701400756836},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5171862840652466},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4732300043106079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47130072116851807},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42234712839126587},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3408936858177185},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0636347234249115},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.056596070528030396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7174611687660217},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.6562067866325378},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6371189951896667},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5678701400756836},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5171862840652466},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4732300043106079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47130072116851807},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42234712839126587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3408936858177185},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0636347234249115},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.056596070528030396},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":3,"locations":[{"id":"doi:10.21437/interspeech.2015-644","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2015-644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2015","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:publications/746d90d3-5ff9-4609-907e-bd64916cd082","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/746d90d3-5ff9-4609-907e-bd64916cd082","pdf_url":"https://www.pure.ed.ac.uk/ws/files/19869954/Renshaw_Kamper_ET_AL_2015_A_Comparison_of_Neural_Network_Methods.pdf","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":""},{"id":"pmh:oai:pure.ed.ac.uk:openaire/746d90d3-5ff9-4609-907e-bd64916cd082","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/746d90d3-5ff9-4609-907e-bd64916cd082","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":"Renshaw, D, Kamper, H, Jansen, A & Goldwater, S 2015, A Comparison of Neural Network Methods for Unsupervised Representation Learning on the Zero Resource Speech Challenge. in INTERSPEECH 2015 16th Annual Conference of the International Speech Communication Association. International Speech Communication Association, pp. 3199-3203. < http://www.isca-speech.org/archive/interspeech_2015/i15_3199.html >","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:publications/746d90d3-5ff9-4609-907e-bd64916cd082","is_oa":true,"landing_page_url":"http://hdl.handle.net/20.500.11820/746d90d3-5ff9-4609-907e-bd64916cd082","pdf_url":"https://www.pure.ed.ac.uk/ws/files/19869954/Renshaw_Kamper_ET_AL_2015_A_Comparison_of_Neural_Network_Methods.pdf","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":""},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306183","display_name":"James S. McDonnell Foundation","ror":"https://ror.org/03dy4aq19"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1796128977.pdf","grobid_xml":"https://content.openalex.org/works/W1796128977.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W66167291","https://openalex.org/W1524333225","https://openalex.org/W1545920196","https://openalex.org/W1606347560","https://openalex.org/W2002318609","https://openalex.org/W2017257315","https://openalex.org/W2020607164","https://openalex.org/W2025768430","https://openalex.org/W2026369565","https://openalex.org/W2044138293","https://openalex.org/W2052697931","https://openalex.org/W2057007397","https://openalex.org/W2100495367","https://openalex.org/W2107878631","https://openalex.org/W2112688413","https://openalex.org/W2145094598","https://openalex.org/W2145410271","https://openalex.org/W2146502635","https://openalex.org/W2148154194","https://openalex.org/W2395899413","https://openalex.org/W2406349064","https://openalex.org/W2407151108","https://openalex.org/W2786608204","https://openalex.org/W3028642772","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3013650182","https://openalex.org/W2062195135","https://openalex.org/W4249605382","https://openalex.org/W4313491656","https://openalex.org/W2989283631","https://openalex.org/W2800717388","https://openalex.org/W2250701745","https://openalex.org/W2953266770","https://openalex.org/W4287625546","https://openalex.org/W2957129171"],"abstract_inverted_index":{"The":[0,93],"success":[1],"of":[2,82,100,156,175,195],"supervised":[3,177],"deep":[4],"neural":[5,26],"networks":[6],"(DNNs)":[7],"in":[8,39],"speech":[9],"recognition":[10],"cannot":[11],"be":[12,183],"transferred":[13],"to":[14,47,110,132,144,159],"zero-resource":[15,146],"languages":[16],"where":[17],"the":[18,59,96,103,113,121,160,172,187],"requisite":[19],"transcriptions":[20],"are":[21],"unavailable.":[22],"We":[23,57,119,163],"investigate":[24],"unsupervised":[25,88],"network":[27],"based":[28],"methods":[29],"for":[30,51],"learning":[31],"frame-level":[32],"representations.":[33],"Good":[34],"frame":[35,77,168],"representations":[36,78,169],"eliminate":[37],"differences":[38],"accent,":[40],"gender,":[41],"channel":[42],"characteristics,":[43],"and":[44,53,63,141],"other":[45],"factors":[46],"model":[48],"subword":[49],"units":[50],"within-":[52],"across-speaker":[54],"phonetic":[55],"discrimination.":[56],"enhance":[58],"correspondence":[60],"autoencoder":[61],"(cAE)":[62],"show":[64,165],"that":[65,166],"it":[66,143],"can":[67,182],"transform":[68],"Mel":[69],"Frequency":[70],"Cepstral":[71],"Coefficients":[72],"(MFCCs)":[73],"into":[74],"more":[75],"effective":[76],"given":[79],"a":[80,137,145,151,176,190],"set":[81],"matched":[83],"word":[84],"pairs":[85,109],"from":[86,107,171],"an":[87],"term":[89],"discovery":[90],"(UTD)":[91],"system.":[92],"cAE":[94,138],"combines":[95],"feature":[97],"extraction":[98],"power":[99],"autoencoders":[101],"with":[102],"weak":[104],"supervision":[105],"signal":[106],"UTD":[108],"better":[111],"approximate":[112],"extrinsic":[114],"task\u2019s":[115],"objective":[116],"during":[117],"training.":[118],"use":[120],"Zero":[122],"Resource":[123],"Speech":[124],"Challenge\u2019s":[125],"minimal":[126],"triphone":[127],"pair":[128],"ABX":[129],"discrimination":[130],"task":[131],"evaluate":[133],"our":[134],"methods.":[135],"Optimizing":[136],"architecture":[139],"on<br/>English":[140],"applying":[142],"language,":[147],"Xitsonga,":[148],"we":[149],"obtain":[150],"relative":[152,191],"error":[153,192],"rate":[154,193],"reduction":[155,194],"35%":[157],"compared":[158],"original":[161],"MFCCs.":[162],"also":[164],"Xitsonga":[167],"extracted":[170],"bottleneck":[173],"layer":[174],"DNN":[178],"trained":[179],"on":[180],"English":[181],"further":[184],"enhanced":[185],"by":[186],"cAE,":[188],"yielding":[189],"39%.<br/>":[196]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}