{"id":"https://openalex.org/W2259232214","doi":"https://doi.org/10.1109/asru.2015.7404801","title":"An iterative deep learning framework for unsupervised discovery of speech features and linguistic units with applications on spoken term detection","display_name":"An iterative deep learning framework for unsupervised discovery of speech features and linguistic units with applications on spoken term detection","publication_year":2015,"publication_date":"2015-12-01","ids":{"openalex":"https://openalex.org/W2259232214","doi":"https://doi.org/10.1109/asru.2015.7404801","mag":"2259232214"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2015.7404801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","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/1602.00426","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102330488","display_name":"Cheng-Tao Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Tao Chung","raw_affiliation_strings":["Graduate Institute of Electrical Engineering, National Taiwan University","[Graduate Institute of Electrical Engineering, National Taiwan University]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[Graduate Institute of Electrical Engineering, National Taiwan University]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028459162","display_name":"Cheng\u2010Yu Tsai","orcid":"https://orcid.org/0000-0001-6150-4577"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Cheng-Yu Tsai","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080149033","display_name":"Hsiang-Hung Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsiang-Hung Lu","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024856346","display_name":"Chia-Hsiang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Hsiang Liu","raw_affiliation_strings":["Graduate Institute of Electrical Engineering, National Taiwan University","[Graduate Institute of Electrical Engineering, National Taiwan University]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[Graduate Institute of Electrical Engineering, National Taiwan University]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["Graduate Institute of Electrical Engineering, National Taiwan University","[Graduate Institute of Electrical Engineering, National Taiwan University]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Electrical Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[Graduate Institute of Electrical Engineering, National Taiwan University]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044010123","display_name":"Lin-shan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lin-shan Lee","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.12776137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"3","issue":null,"first_page":"245","last_page":"251"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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":0.9979000091552734,"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":0.8541582822799683},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7701634168624878},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.591253399848938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5723810791969299},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5708269476890564},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5666183829307556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5344148874282837},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4681171774864197},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.45320725440979004},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.43292269110679626},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37845081090927124},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.325683057308197}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8541582822799683},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7701634168624878},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.591253399848938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5723810791969299},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5708269476890564},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5666183829307556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5344148874282837},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4681171774864197},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.45320725440979004},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.43292269110679626},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37845081090927124},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.325683057308197},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru.2015.7404801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2015.7404801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1602.00426","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1602.00426","pdf_url":"https://arxiv.org/pdf/1602.00426","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"mag:2259232214","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1602.00426","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.1602.00426","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1602.00426","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1602.00426","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1602.00426","pdf_url":"https://arxiv.org/pdf/1602.00426","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2259232214.pdf","grobid_xml":"https://content.openalex.org/works/W2259232214.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W51277926","https://openalex.org/W67277430","https://openalex.org/W308497914","https://openalex.org/W1545920196","https://openalex.org/W1577418252","https://openalex.org/W1631260214","https://openalex.org/W1880262756","https://openalex.org/W1970890968","https://openalex.org/W2033178790","https://openalex.org/W2053306448","https://openalex.org/W2057007397","https://openalex.org/W2064675550","https://openalex.org/W2078769636","https://openalex.org/W2100768664","https://openalex.org/W2105016867","https://openalex.org/W2107653054","https://openalex.org/W2116422968","https://openalex.org/W2155893237","https://openalex.org/W2160815625","https://openalex.org/W2251025892","https://openalex.org/W2401464865","https://openalex.org/W2402196427","https://openalex.org/W2950094539","https://openalex.org/W6602762607","https://openalex.org/W6607775107","https://openalex.org/W6631362777","https://openalex.org/W6636811518","https://openalex.org/W6639619044","https://openalex.org/W6675022971","https://openalex.org/W6691362072","https://openalex.org/W6712444837","https://openalex.org/W6713463742"],"related_works":["https://openalex.org/W2737331776","https://openalex.org/W2963206684","https://openalex.org/W2971766686","https://openalex.org/W2116422968","https://openalex.org/W3095049654","https://openalex.org/W3029023844","https://openalex.org/W3104842308","https://openalex.org/W2188924248","https://openalex.org/W2567545547","https://openalex.org/W2584414011","https://openalex.org/W2955397069","https://openalex.org/W3111336239","https://openalex.org/W3091088345","https://openalex.org/W3044386551","https://openalex.org/W2586564256","https://openalex.org/W1522720415","https://openalex.org/W1499245496","https://openalex.org/W2182155920","https://openalex.org/W1484397692","https://openalex.org/W1983300351"],"abstract_inverted_index":{"In":[0,188],"this":[1,151],"work":[2],"we":[3,190],"aim":[4],"to":[5,138,222],"discover":[6],"high":[7,167],"quality":[8,168],"speech":[9,17,169,225],"features":[10,126,170,226],"and":[11,31,92,141,178,227],"Linguistic":[12],"units":[13],"directly":[14],"from":[15,60,128],"unlabeled":[16],"data":[18],"in":[19,34,145],"a":[20,71,114],"zero":[21],"resource":[22],"scenario.":[23],"The":[24,101,206],"results":[25,208],"are":[26,107,131],"evaluated":[27],"using":[28],"the":[29,35,61,77,89,93,111,129,135,139,142,146,156,172,176,182,186,195,199,210,218],"metrics":[30],"corpora":[32,197],"proposed":[33,50],"Zero":[36],"Resource":[37],"Speech":[38],"Challenge":[39,177],"organized":[40],"at":[41],"Interspeech":[42],"2015.":[43],"A":[44],"Multi-layered":[45,157],"Acoustic":[46,158],"Tokenizer":[47],"(MAT)":[48],"was":[49],"for":[51,171,181],"automatic":[52],"discovery":[53],"of":[54,57,73,82,104,113,175,185,201,215],"multiple":[55,102],"sets":[56,81,103],"acoustic":[58,65,83,123,179,228],"tokens":[59,84,180],"given":[62,90],"corpus.":[63],"Each":[64],"token":[66,105],"set":[67,72],"is":[68],"specified":[69],"by":[70],"hyperparameters":[74],"that":[75],"describe":[76],"model":[78],"configuration.":[79],"These":[80],"carry":[85],"different":[86],"characteristics":[87],"fof":[88],"corpus":[91],"language":[94],"behind,":[95],"thus":[96],"can":[97],"be":[98],"mutually":[99],"reinforced.":[100],"labels":[106],"then":[108,132],"used":[109,133],"as":[110,134],"targets":[112],"Multi-target":[115],"Deep":[116,160],"Neural":[117,161],"Network":[118,162],"(MDNN)":[119],"trained":[120],"on":[121,194,198],"low-level":[122],"features.":[124],"Bottleneck":[125],"extracted":[127],"MDNN":[130,143],"feedback":[136],"input":[137],"MAT":[140],"itself":[144],"next":[147],"iteration.":[148],"We":[149],"call":[150],"iterative":[152,211],"deep":[153,212],"learning":[154,213],"framework":[155,214],"Tokenizing":[159],"(MAT-DNN),":[163],"which":[164],"generates":[165],"both":[166],"Track":[173,183],"1":[174],"2":[184],"Challenge.":[187],"addition,":[189],"performed":[191],"extra":[192],"experiments":[193],"same":[196],"application":[200],"query-by-example":[202],"spoken":[203],"term":[204],"detection.":[205],"experimental":[207],"showed":[209],"MAT-DNN":[216],"improved":[217],"detection":[219],"performance":[220],"due":[221],"better":[223],"underlying":[224],"tokens.":[229]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}