{"id":"https://openalex.org/W3044386551","doi":"https://doi.org/10.21437/interspeech.2020-3000","title":"Self-Expressing Autoencoders for Unsupervised Spoken Term Discovery","display_name":"Self-Expressing Autoencoders for Unsupervised Spoken Term Discovery","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3044386551","doi":"https://doi.org/10.21437/interspeech.2020-3000","mag":"3044386551"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-3000","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/2007.13033","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045247662","display_name":"Saurabhchand Bhati","orcid":"https://orcid.org/0000-0001-6477-3895"},"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":"Saurabhchand Bhati","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057010207","display_name":"Jes\u00fas Villalba","orcid":"https://orcid.org/0000-0001-9459-8426"},"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":"Jes\u00fas Villalba","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027217976","display_name":"Piotr \u017belasko","orcid":"https://orcid.org/0000-0002-8245-0413"},"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":"Piotr \u017belasko","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/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"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":"Najim Dehak","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"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":"4876","last_page":"4880"},"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":0.9987999796867371,"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":0.9957000017166138,"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":0.8818128108978271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7852418422698975},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7177292108535767},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6342860460281372},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6128506064414978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5849226713180542},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5632456541061401},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.554015040397644},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5505056381225586},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5322321057319641},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.506107747554779},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.47079387307167053},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4566265046596527},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38245269656181335},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3280295729637146},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.22868311405181885}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8818128108978271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7852418422698975},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7177292108535767},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6342860460281372},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6128506064414978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5849226713180542},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5632456541061401},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.554015040397644},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5505056381225586},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5322321057319641},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.506107747554779},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.47079387307167053},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4566265046596527},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38245269656181335},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3280295729637146},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.22868311405181885},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2020-3000","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-3000","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2007.13033","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.13033","pdf_url":"https://arxiv.org/pdf/2007.13033","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":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2007.13033","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.13033","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":"Preprint"},{"id":"mag:3044386551","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2007.13033","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.13033","pdf_url":"https://arxiv.org/pdf/2007.13033","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3044386551.pdf","grobid_xml":"https://content.openalex.org/works/W3044386551.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W126222424","https://openalex.org/W1545920196","https://openalex.org/W1796128977","https://openalex.org/W1922655562","https://openalex.org/W1994458317","https://openalex.org/W2020607164","https://openalex.org/W2057007397","https://openalex.org/W2078769636","https://openalex.org/W2100768664","https://openalex.org/W2126203737","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2166637769","https://openalex.org/W2170659185","https://openalex.org/W2251025892","https://openalex.org/W2398490608","https://openalex.org/W2400549570","https://openalex.org/W2404799143","https://openalex.org/W2468716020","https://openalex.org/W2747192917","https://openalex.org/W2786608204","https://openalex.org/W2803005441","https://openalex.org/W2890718354","https://openalex.org/W2940544976","https://openalex.org/W2963620343","https://openalex.org/W2964169922","https://openalex.org/W2972794572","https://openalex.org/W2981857663","https://openalex.org/W2991213871"],"related_works":["https://openalex.org/W2468716020","https://openalex.org/W2584414011","https://openalex.org/W3096802056","https://openalex.org/W3095298905","https://openalex.org/W3150635893","https://openalex.org/W1499245496","https://openalex.org/W2962689740","https://openalex.org/W3104842308","https://openalex.org/W2758697525","https://openalex.org/W2188924248","https://openalex.org/W2964079874","https://openalex.org/W3037057938","https://openalex.org/W2259232214","https://openalex.org/W3148040514","https://openalex.org/W2116422968","https://openalex.org/W2759889345","https://openalex.org/W3100202343","https://openalex.org/W2586564256","https://openalex.org/W2792308360","https://openalex.org/W3014528057"],"abstract_inverted_index":{"Unsupervised":[0],"spoken":[1],"term":[2],"discovery":[3,147],"consists":[4,77],"of":[5,59,66,78,99,118,136,159],"two":[6,83],"tasks:":[7],"finding":[8],"the":[9,19,27,30,42,53,56,91,100,105,112,115,122,129,134,137,141,154,157,160],"acoustic":[10],"segment":[11,39,126],"boundaries":[12],"and":[13,82,111,127],"labeling":[14],"acoustically":[15],"similar":[16,36],"segments":[17],"with":[18,85],"same":[20],"labels.":[21],"We":[22,68,120,132],"perform":[23],"segmentation":[24,47],"based":[25],"on":[26],"assumption":[28],"that":[29,52],"frame":[31,61],"feature":[32],"vectors":[33],"are":[34],"more":[35,62],"within":[37],"a":[38,60,72,79,95],"than":[40,63],"across":[41],"segments.":[43],"Therefore,":[44],"for":[45],"strong":[46],"performance,":[48],"it":[49],"is":[50],"crucial":[51],"features":[54,93,124],"represent":[55],"phonetic":[57],"properties":[58],"other":[64,113],"factors":[65],"variability.":[67],"achieve":[69],"this":[70],"via":[71],"self-expressing":[73],"autoencoder":[74],"framework.":[75],"It":[76],"single":[80],"encoder":[81,89],"decoders":[84,101],"shared":[86],"weights.":[87],"The":[88,149],"projects":[90],"input":[92,106],"into":[94],"latent":[96,109],"representation.":[97],"One":[98],"tries":[102],"to":[103,125],"reconstruct":[104],"from":[107,114],"these":[108],"representations":[110],"self-expressed":[116],"version":[117],"them.":[119],"use":[121],"obtained":[123],"cluster":[128],"speech":[130],"data.":[131],"evaluate":[133],"performance":[135],"proposed":[138,150],"method":[139,161],"in":[140,162],"Zero":[142],"Resource":[143],"2020":[144],"challenge":[145],"unit":[146],"task.":[148],"system":[151],"consistently":[152],"outperforms":[153],"baseline,":[155],"demonstrating":[156],"usefulness":[158],"learning":[163],"representations.":[164]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}